HOME
QUICK SEARCH
AUTHORS
KEYWORDS
HELP
BUGSPharmaSUG 2014 Papers - Index
205 papers. Source: PharmaSUG (Pharmaceutical Software Users Group) conference proceedings.
| # | Title× | Authors× | Abstract× | Keywords× | Extras | Pages |
|---|---|---|---|---|---|---|
| 1 | %IC_LOGISTIC: A SAS Macro to Produce Sorted Information Criteria (AIC/BIC) List for PROC LOGISTIC for Model Selection | Qinlei Huang, Liang Zhu |
Model selection is one of the fundamental questions in statistics. One of the most popular and widely used strategies is model selection based on information criteria, such as Akaike Information Criterion (AIC) and Sawa Bayesian Information Criterion (BIC). It considers both fit and complexity, and enables multiple models to be compared simultaneously. PROC LOGISTIC is one of the most popular SAS procedures to perform logistic regression analysis on discrete responses including binary responses, ordinal responses, and nominal responses. However, there is no existing SAS procedure to perform model selection automatically based on Information Criteria for PROC LOGISTIC, given a set of covariates. This paper provides a SAS macro %ic_logistic to select a final model with the smallest value of AIC/BIC |
feature selection, proc logistic, logistic distribution, macro definition, proc step, dataset, logistic regression, regression analysis, proc report, predictor variable, response variable, work library, data science, in= | source | 12 |
| 2 | %ME: A SAS Macro to Assess Measurement Equivalence for Patient-Reported Outcome Measures | Qinlei Huang | Patient-reported outcomes (PROs) are the consequences of diseases, their treatment, or both as reported by patients. PRO measures are important for evaluating new treatments, drugs, biological agents, and devices when used as effectiveness end points in clinical trials. Measurement equivalence is a function of the comparability of the psychometric properties of the data obtained via mixed modes (e.g., paper-and-pencil questionnaires, web-based questionnaires); in paired data (e.g., patient-reported outcome, parent-reported outcome); and/or at different time points. Measurement equivalence must be established prior to using a PRO measure for further statistical analysis and modeling. Multiple statistical methods have been developed to test measurement equivalence by evaluating means (TOST, TTest), variances (Levene's test), or correlations and agreements (Pearson Product Moment Correlation, Intra-class correlation, Weighted Kappa, and Spearman's Rho) | dataset, macro definition, equivalence testing, effect size, out=, standard deviation, class variable, response variable, work library, correlation, confidence interval, parallel group, sas library, proc step, null hypothesis, proc ttest, treatment arm, sample, proc glm | source | 8 |
| 3 | 'V' for ... Variable Information Functions to the Rescue | Richann J. Watson, Karl Miller |
There are times when we need to use the attributes of a variable within a data set. Normally, this can be done with a simple CONTENTS procedure. The information can be viewed prior to programming and then hardcoded within the program or it can be saved to a data set that can be joined back to the main data set. If the attributes are hardcoded then what happens if the data set changes structure, then the program would need to be updated accordingly. If the information from PROC CONTENTS is saved and then joined with the main data set, then this would need to be done for all data sets that need to be processed. This is where knowing your 'V' functions can come in handy. The 'V' functions can be used to return the label, format, length, name, type and/or value of a variable or a string within the DATA STEP. These functions can come quite in handy when you need to create summary statistics and if you need to perform an algorithm on a variable with a specific naming convention |
proc means, proc step, macro variable, character variable, numeric variable, baseline characteristics, data step, label statement, sample, proc contents | source | 15 |
| 4 | 1 of N Methods to Automate the Y- Axis | Sanjiv Ramalingam | Methodologies for automating the Y-axis has been discussed previously [1,2,3]. The motivation to share this code is to not only present readers an another algorithm but because the methodology is simple, robust in that it can accommodate not only integer data but also floating point data and has comparatively very few lines of code. The algorithm allows the user to specify how many divisions they would like their data to be visualized. Even though SAS 9.3 handles Y-axis automation, reasons as to why automation by the user is warranted in certain situations have been elucidated | macro variable, do loop | source | 5 |
| 5 | A Guide for Front-Line Managers to Retain Talented Statistical SAS Programmers | R. Mouly Satyavarapu | SAS programmers have a variety of functional and technical skills, coding preferences, personality types, and communication styles. And those programmers, who aspire to make the career move to a manager role, should be aware of the skills that comprise a manager's skill set. I am presuming that a statistical SAS programmer who has been working towards a management role has gained the initial management title and is aware of the fundamental skills (grouped under): Project Management, Personnel Management, Communication, Negotiation, Team Motivation, Conflict Resolution, and Financial Management, which is referred in the paper - manager's skill set (La Brec 2010) [1]. In this paper, I will provide tips for front-line managers or project team leaders to - build a strong and productive Statistical SAS programming team; focus on developing the team; recognize and reward the effort by each team member; and retain the programming team's talent | source | 6 | |
| 6 | A Guide to the ADaM Basic Data Structure for Dataset Designers | Michelle Barrick, John K. Troxell |
The Clinical Data Interchange Standards Consortium (CDISC) Analysis Data Model (ADaM) Implementation Guide (ADaMIG), published in 2009, describes the many components of a very powerful and flexible analysis dataset structure called the Basic Data Structure (BDS), and provides some rules and examples. The BDS is unique among CDISC data structures in the flexibility it provides for the addition of various kinds of derived rows to meet analysis needs. A companion CDISC document, "CDISC Analysis Data Model (ADaM) Examples in Commonly Used Statistical Methods," published in 2011, provides more in-depth examples of ADaM data and metadata solutions in particular scenarios. However, neither of the two documents provides a holistic explanation of the BDS that describes how the structurally-important variables and kinds of observed and derived rows function together. In this paper, the authors define categories of observed and derived rows | bds, filtering, flag variable, imputation, cdisc | source | 12 |
| 7 | A Hands-on Introduction to SAS Dictionary Tables | Peter W. Eberhardt | SAS maintains a wealth of information about the active SAS session, including information on libraries, tables, files and system options; this information is contained in the Dictionary Tables. Understanding and using these tables will help you build interactive and dynamic applications. Unfortunately, Dictionary Tables are often considered an 'Advanced' topic to SAS programmers. This paper will help novice and intermediate SAS programmers get started with their mastery of the Dictionary tables. Ever needed a list of the tables (datasets) in a library? How about the columns (variables) in a table? Need to make sure you reset any titles after you run a report? Got some pesky warning messages in your SAS log you would like to clean up? Sure, you can look them up in the table and column properties in the explorer window. Or you can run a PROC CONTENTS and check the listing. And of course you can ignore the warnings and errors in the SAS log since they 'almost always appear' |
dictionary tables, proc sql, proc step, sas log, data step, sas programmer, sashelp, sas library | source | 15 |
| 8 | A Macro to Automate Symbol Statements in Line Plots | Deli Wang, Chunxia Lin |
When processing PROC GPLOT procedure to generate line plots, SAS programmers may have to write several symbol statements and customize specific colors for different groups. The process might be very annoying when data have multiple groups, or programmers are asked to generate/update tons of plots within tight timelines. So isn't wonderful if the symbols in line plots can be assigned based on the input data and line attributes defined in DATA STEP, hence programmers take accurate control of line attributes? This paper is trying to write a small macro to empower the programmers with an easy control of symbol statements. The macro provides several advantages: 1. Accurately assign the line attributes like writing a datastep; 2. No longer need to figure out how many symbol statements needed and which symbol is for which line;3. Can easily modify the macro to fit other plotting needs, program once and use it always |
call execute, proc step, line chart, proc gplot, proc print, class variable, data step, macro call, macro definition | source | 8 |
| 9 | A Macro to Create Occurrence Flags for Analysis Datasets | Ed Lombardi | The different paths available for occurrence analysis are fairly straightforward. The path that takes a little longer ends up giving a better end product. This approach is to create occurrence flags in analysis datasets as described in ADaM's ADAE structure. These flags allow for standardized table programs while also providing traceability to allow reviewers to know what records are being used in analysis. The code to create these flags is straightforward and repetitive so it's an excellent situation to use a macro. Otherwise, creating these flags can lead to cluttered sections of analysis dataset programs | flag variable, macro call, adverse events, adam dataset, keyword parameter, %macro parameters, cdisc | source | 4 |
| 10 | A Mental Health and Risk Behavior Analysis of American Youth Using PROC FACTOR and SURVEYLOGISTIC | Deanna Naomi Schreiber-Gregory | The current study looks at recent health trends and behavior analyses of youth in America. Data used in this analysis was provided by the Center for Disease Control and Prevention and gathered using the Youth Risk Behavior Surveillance System (YRBSS). A factor analysis was performed to identify and define latent mental health and risk behavior variables. A series of logistic regression analyses were then performed using the risk behavior and demographic variables as potential contributing factors to each of the mental health variables. Mental health variables included disordered eating and depression/suicidal ideation data while the risk behavior variables included smoking, consumption of alcohol and drugs, violence, vehicle safety, and sexual behavior data. Implications derived from the results of this research are a primary focus of this study. Risks and benefits of using a factor analysis with logistic regression in social science research will also be discussed in depth | likelihood function, maximum likelihood estimation, odds ratio, regression analysis, factor analysis, logistic regression, binary variable, logistic distribution, response variable, factor loading, proc step, correlation, proc freq, sample, proc means | source | 23 |
| 11 | A New Trend in the industry - Partnerships between CROs and Pharma. Do we know how to work in this new relationship? | Kevin Lee | There is a new trend in the working relationships between CROs and Drug companies. The relationships evolve from the traditional transactional model to a partnership in the recent years. The partnership in the pharmaceutical industry is a new adventure to both CROs and Drug companies, and it also impacts programmers. The partnerships will bring the new challenges and opportunities to programmers. We will work with not only our colleagues, but also employees from other vendors and clients. The partnership working environments will require the new set of rules and behaviors. The paper will discuss what kind of challenges and opportunities we will encounter and how we will resolve and succeed in the partnership working environments. The paper will specifically discuss the role of a project leader in CRO who are working directly with the clients and other vendors in the partnership environments | service provider, sas programming | source | 4 |
| 12 | A Parameterized SAS Macro to Select an Appropriate Covariance Structure in Repeated Measures Data Analysis Using PROC MIXED | Leela Aertker, Paul Nguyen, Charity Quick |
In clinical trials we often encounter multiple measurements on a subject or experimental unit over a period of time. When analyzing longitudinal data using SAS PROC MIXED, it is critical to specify the covariance or correlation structure of the repeated measures. Unless stated a priori, one must determine the most appropriate covariance structure by comparing and contrasting the best fit of different covariance structures based on AIC, AICc, BIC, or -2 log likelihood. This paper will describe an efficient macro to determine the covariance structure for a model. The %COVSTRUC macro includes several user-specified parameters: goodness-of-fit statistic, model information, and whether a particular covariance structure has priority given convergence. The covariance structure with the best fit (i.e., lowest value of specified fit statistic) will be chosen and outputted to a macro variable, which can then be called into the final analysis model |
covariance structure, covariance, proc mixed, final analysis, longitudinal data, proc step, correlation, repeated measures, likelihood function | source | 3 |
| 13 | A Road Map to Successful CDISC ADaM Submission to FDA: Guidelines, Best Practices & Case Studies | Vikash Jain, Sandra Minjoe |
Submitting a filing to the FDA (Food and Drug Administration) using Clinical Data Interchange Standards Consortium (CDISC) data standards has become a norm in the pharmaceutical industry in recent years. This standard has been strongly encouraged by the agency to help expedite their review process, plus it also helps the sponsors and service providers have a means of efficient collaboration using these common industry standards. This paper elaborate s on the following fundamental and core components to be considered for the ADaM (A nalysis Data Model) piece of submission: 1) Use of ADaM or ADaM-like data 2) Checking for ADaM compliance 3) Use of Define and other Metadata We also present handful of case studies based on real time CDISC submission project experiences while collaboration with our sponsors | adam dataset, adamig, data standard, cdisc | source | 9 |
| 14 | A SAS Macro to address PK timing variables issues | Timothy J. Harrington | This paper discusses and lists a SAS macro w hich addresses the challenge of evaluating timing variables and chronological sequencing for collected PK sampling and patient dosing data w hen sample and dose dates and times are not alw ays recorded correctly on, or are omitted from, the case report form input. Examples of such datasets are PKS, POPPK, and NONMEM. This macro is intended for use w ith the input data in CDISC format for a single dose per visit, w ith a single pre- dose sample and follow ing post dose samples | sample, imputation, crf, study day, in=, out=, time., cdisc | source | 14 |
| 15 | A SAS Macro to Evaluate Balance after Propensity Score Matching | Erin Hulbert, Lee Brekke |
Propensity score matching is a method used to reduce bias in observational studies by creating two populations that are similar (i.e., balanced) across a number of covariates using a match on only a single scalar, the propensity score. The matched samples are then treated as a quasi-experimental population, allowing for simplified analysis of study outcomes. Whenever a propensity match is performed, the balance between the two samples should be evaluated. Balance checking may be used to compare matches from multiple iterations of the propensity score model or from different matching algorithms and to provide information for any trade-offs between the closeness of the match and final sample size. Additionally, imbalances in the final matched sample should be kept in mind and possibly adjusted for when analyzing study outcomes. The published literature encourages using a variety of methods to evaluate balance | propensity score, sample, sample size, propensity score matching, macro definition, standard deviation, proc freq, proc step | source | 12 |
| 16 | A SAS Macro Tool for Visualizing Data Comparison Results in an Intuitive Way | Hui Wang, Weizhen Ying |
In clinical data analysis, PROC COMPARE is widely used in data quality control. Howeve r, sometimes the results of this procedure can be quite challenging to understand. For example, it only disp lays the first 20 characters in value comparison output. Consequently, character mismatches in leng thy text strings may not be seen directly. In addition, it shows mismatches separately and does not simultaneously show values of variables that might be relevant to mismatches, which leads to difficulty in figuring out why mismatches happen. This paper intends to introduce a SAS macro tool whic h is based on PROC COMPARE but gives an intuitive comparison report. First of all, this macro juxtaposes mismat ched values vertically and thus allows the display of whole variable content. Secondly, the macro can extract unique rows from datasets comp ared and then tells directly which rows are missing in which dataset |
proc compare, proc step, call execute, create table, concomitant medications, proc sql, macro parameter | source | 12 |
| 17 | A SAS Macro Utility to Modify and Validate RTF Outputs for Regional Analyses | Jagan Mohan Achi, Joshua N. Winters |
Clinical Study Reports (CSRs) of clinical trials require the development of the tables, listings, and figures (TLFs) in Rich Text Format (RTF) outputs. The analyses are usually complex and the number of RTF outputs is fairly large depending on the magnitude of the studies. It is not uncommon to see requests to repeat the analyses by region and/or country for multicenter trials to understand the differences in geographical locations. For regional analyses, changes to an RTF output can be but not limited to changing the FILENAME, adding additional information in the title, and modifying the hidden bookmark which is used to ensure that the report refers to the specific TLF from CSRs. Such changes have to be made to the original TLF programs which are time consuming |
ods rtf, macro variable | source | 5 |
| 18 | A Shout-out to Specification Review: Techniques for an efficient review of Programming Specifications | Sajeet Pavate, Jhelum Naik |
One of the most common reasons for poor quality of programming output, higher costs due to large number of programming hours and missed timelines is poorly written programming specifications (specs). A thorough independent review of the specifications by competent programmers and/or statisticians prior to programming activities is an important safety net to ensure the specs are in a suitable form for programming. This early intervention eliminates the risks to deliverable in terms of quality, costs and timelines. This paper provides clear guidelines, tips and techniques to empower spec reviewers to perform an efficient spec review. This paper provides techniques for spec review that can be implemented for different types of deliverables such as Transformed/Mapped Data, Analysis Database, Tables, Listings and Figures and for different types of organizations such as CROs and pharmaceutical companies | raw data, sample, excel | source | 5 |
| 19 | A Toolkit to Check Dictionary Terms in SDTM | Huei-Ling Chen, Helen Wang |
WHO Drug Dictionary (WHO-DD) and MedDRA are two important dictionaries used in the SDTM datasets. In the intervention domains, WHO-DD is used to derive the standardized medication name. In the event domains, the standardized text description of an event is based on dictionary MedDRA. A standardized dictionary term can be derived from an original term when its value exists in the dictionaries. Sometimes an original term fails to facilitate coding due to its value does not exist in the dictionary. In a busy project team, preparing SDTM packages for multiple studies is very common. It will be helpful if there is a checking toolkit to quickly identify records that fail to have dictionary term derived when preparing SDTM packages. This paper will first briefly summarize the application of WHO-DD and MedDRA and list out the dictionary-derived variables commonly used in clinical trial studies | sdtm domain, dictionary tables, proc sql, cdisc | source | 8 |
| 20 | A User Friendly Tool to Facilitate the Data Integration Process | Yang Wang, Boxun Zhang |
For any clinical program, meta-analysis, including Development Safety Update Report (DSUR), Integrated Summary of Safety (ISS), and Integrated Summary of Efficacy (ISE), integrating data is a challenging process and is often labor-intensive and error-prone. The challenges arise primarily due to the following reasons: (1) different study designs and data standards, (2) evolving industry standards including CDISC , MedDRA and WHODrug, and (3) different data collection methods across vendors. In order to ensure all the variables can be integrated for analysis, we built a user-friendly tool to dynamically display the differences in variable attributes and values across multiple clinical studies. This paper, with examples and programming components, shows how this tool can be used to facilitate data integration by identifying and resolving issues resulting from variable inconsistencies | excel, label statement, missing value, clinical trial, cdisc | source | 6 |
| 21 | Add Dropdowns and Redirects to Your SAS Output | Barbara Ross | Outputting attractive and interactive reports via SAS onto the web doesn't have to be complicated. For most internal purposes, a webpage directory that links to static reports that update regularly is enough. This paper introduces simple ways to add dropdown menus and redirects within your SAS output. All webpages are created using Base SAS and website directories are managed using an open source FTP client for Windows (WinSCP in this case). Techniques used include: JavaScript to select item on click, PHP to collect form entries, and HTML for hyperlinks. The SQL procedure and DATA STEP are used for data transformations |
macro variable, options statement, sas output, character functions, proc sql | source | 16 |
| 22 | Additional Metadata for Common Catalog Entry Types | Kenneth W. Borowiak | Anyone who has worked with SAS has probably added descriptive attributes to entities such as variables (labels and formats), data sets (labels), reports (titles and foo tnotes), and programs (comments). Though not as well known, one can add descriptive labels to commonly used catalog entry types, namely formats and macros This paper will demonstrate how to add, modify and retrieve this metadata. Keywords: format, macros, PROC CATALOG, metadata |
proc step, proc catalog, catalog entry, sas log | source | 5 |
| 23 | Adopted Changes for SDTMIG v3.1.3 and 2013 OpenCDISC Upgrades | Yi Liu, Stephen Read |
There have been several enhancements and upgrades to CDISC Study Data Tabulations Model (SDTM) data standards and associated implementation guides over recent years. August 2012 saw the release of SDTMIG v3.1.3 and adoption of SDTMIG v3.1.2 Amended 1 recommendations, in advance of the more recent and comprehensive SDTMIG v3.2 upgrade as released in December 2013. In support of these SDTM enhancements the OpenCDISC community released 2 new SDTM validators in 2013. OpenCDISC Version 1.4 released in March 2013 and OpenCDISC 1.4.1 released in September 2013. Adoption of these enhanced SDTM data standards and associated validation applications has led to the need for SAS programmers or data mapping/submission specialists to consider implementing significant revisions across SDTM related SAS programs, processes and applications | study day, sdtm domain, character variable, length statement, data cleaning, clinical trial, data standard, error message, sas programmer, dataset, clinical data, excel, adverse events, macro definition, cdisc | source | 17 |
| 24 | An ADaM Interim Dataset for Time-to-Event Analysis Needs | Tom Santopoli, Kimberly Minkalis, Sandra Minjoe |
The Clinical Data Interchange Standards Consortium (CDISC) Analysis Data Model (ADaM) Implementation Guide (IG) Version 1.0 and the appendix document titled "The ADaM Basic Data Structure for Time-to-Event Analyses" each provide guidance for how to set up a dataset for producing a Time-to-Event (TTE) analysis. In practice, a single TTE analysis dataset is often used for analysis of many different events and censoring times. In fact, this TTE analysis dataset is often one of the most complicated created for a study. One of the biggest issues with TTE analyses is that there can be many different dates to consider for both the event and/or the censor. Some of these dates can be options for many different analyses - for example, date of death is the event in survival analysis, but can also be a censor date in time-to-response analysis | survival analysis, imputation, bds, adam dataset, randomization, cdisc | source | 9 |
| 25 | An Alternative Way to Create Define.XML for ADaM with SAS Macro Automation | Yiwen Li | Define.XML for ADaM is required for most FDA submissions, as it describes the structure and contents of the ADaM data. It includes five sections: Data Metadata, Variable Metadata, Value Level Metadata, Computational Algorithm, and Controlled Terminology. Previously programmers used to create it with more support from filling out many EXCEL sheets as input. This paper provides a Linux SAS based simple method to extract almost all needed information from ADaM data with coding-logic-info-capture to create the whole Define.XML output. The only other importing source besides SAS is one EXCEL tab which stores description for variables derived with more complicated logic. It has been successfully implemented to HIV Phase1 study and significantly increased the efficiency of creating Define.XML by at least 50%. Highlighted Strengths: 1. Build most columns on Define.XML from SAS Libraries 2. Build Origin/Comment columns with coding logic information capture |
excel, proc step, macro definition, cdisc | source | 4 |
| 26 | An Alternative Way to Detect Invalid Reference Records in Supplemental Domains | Steven Wang | Quite often in the process of development of SDTM datasets, we may just be interested in how to identify some specific errors in certain domains without the time and effort of running the OpenCDISC validator. The purpose of this paper is to demonstrate an alternative way to identify the invalid cross-referenced records with error code SD0077 in the supplemental domains by utilizing the SAS macro language | create table, proc sql, proc step, cdisc | source | 5 |
| 27 | An Overview of REDCap, a secure web-based application for Electronic Data Capture | Kevin R. Viel | REDCap (Research Electronic Data Cap ture) is a secure web application for building and managing online surveys and databases. With the simplest use, REDCap automates the interactions with the SAS System, providing an option to manually download files, including SAS code to create a SAS dataset and format library. Involvement of the SAS System in order of increasing sophistication includes using SAS to write the "data dictionary" or template f or the electronic forms, using an API to access the projects, or to read the MySQL databases directly. This paper provides a very brief introduction to REDCap and a superficial overview of the using SAS System with REDCap | sas programmer, data dictionary, dataset, mysql, audit trail, data cleaning | source | 14 |
| 28 | Applying ADaM BDS Standards to Therapeutic Area Ophthalmology | Songhui Zhu | Most of the ADaM datasets are in BDS data structure. So statistical programmers spend a lot of time implementing BDS datasets. In this paper, the author's thoughts and practices are illustrated using examples about how to implement ADaM-compliant BDS datasets when facing some complex situations in ophthalmology studies considering that each subjects can have 0 or 1 study eye and 1 or 2 fellow eyes, that the measurements can be performed on various segments of each eye, and that measurements can done at different time points | adam dataset, laboratory data, cdisc | source | 10 |
| 29 | Are You Missing Out? Working with Missing Values to Make the Most of What is not There | Arthur L. Carpenter | Everyone uses and works with missing values, however many SAS programmers are unaware of the variety of tools, options, and techniques associated with using missing values. Did you know that there are 28 types of numeric missing values? Did you know tha t the numeric missing value (.) is neither the smallest or largest possible numeric missing value? Are you aware of the System options, DATA STEP functions, and DATA STEP routines that specifically deal with missing values? Do you understand how the macr o null value is the same, and different from DATA STEP missing values? Are you aware that observations with missing classification variables may or may not be excluded from analyses depending on the procedure and various options? This paper explores various aspects of the world of missing values. The above questions and others are discussed. Learn more about missing values and make sure that you are not missing out |
missing value, proc step, options statement, macro variable, %if-%then-%else, macro loop, macro facility, proc print, proc report, macro quoting function, proc freq | source | 11 |
| 30 | Attain 100% Confidence in Your 95% Confidence Interval | Indu Nair, Binal Patel |
A very common mistake in the calculation of a confidence interval occurs when there are no qualifying subjects in a by group for a category being tested. It is very tempting to assume that the confidence interval will be missing when the count is zero, which is incorrect. This tends to get overlooked since the usual methods of calculating confidence intervals, such as using a simple PROC FREQ in SAS, will not take care of the situation without manipulating the code further. This paper will present the different methods in PROC FREQ that allow you to calculate the confidence intervals and discuss which methods are more appropriate to use. This paper will also explain how to use a formula instead of PROC FREQ to calculate confidence intervals correctly and with confidence |
proc freq, confidence interval, proc step, binomial distribution, sample, confidence level, clinical trial, f distribution | source | 9 |
| 31 | Atypical Application of PROC SUMMARY | John Henry King | This paper describes using PROC SUMMARY combined with a few other DATA and PROC steps to produce stacked frequency tables of a large or small number of categorical variables. This technique uses a single pass of the analysis data preserving the variable order and the order of the levels of each variable, while providing complete rows and complete columns of zero counts (something from nothing) and BIGN. We will discuss applications of PROC FORMAT options NOTSORTED and MULTILABEL; PROC SUMMARY options CHARTYPES, PRELOADFMT, COMPLETETYPES, DESCENDTYPES, LEVELS, WAYS, ORDER=DATA, and the TYPES statement; the PROC FREQ WEIGHT statement, ZEROS option and ODS table CROSSTABFREQS; a DATA STEP view; PROC TRANSPOSE statements ID and IDLABEL; interesting functions FINDC, VNAME, VLABEL, VVALUE, VFORMATD, CATX and CATS all in the context of a simple extensible program that you can use every day |
proc step, proc means, class variable, proc freq, variable list, numeric variable | source | 14 |
| 32 | Automate the Process of Image Recognizing a Scatter Plot: An Application of Non-parametric Cluster Analysis in Capturing Data from Graphical Output | Zhaojie Wang | A fundamental method of pharmaceutical research is to compare the indication between a new drug and an existing competitor drug. Sometimes, the original data of the competitor drug may not always be available. What a researcher can access is only a plot from a published paper. To make the comparison, the researcher has to capture tabular data from this legacy graphical output. Previously, several methods[1][13] were introduced to digitalize a graphic al output into a set of coordinates of pixels, which are the minimum components of a graph. With the pixel coordinates, the graphical output of a competitor drug can be copied and relayed on the graph of the new drug for comparison purpose. These methods are more helpful for reverse-engineering the trend of a curve plot than recognizing a scatter plot , because it is more challenging to recognize a scatter plot. An individual spot, even in the smallest size and the simplest pattern, is composed by multiple pixels | scatter plot, cluster analysis, proc step, structured data, out=, proc freq | source | 11 |
| 33 | Automated Validation - Really? | Sneha Sarmukadam, Seeja Shetty |
In Clinical Programming, data quality takes priority over all other aspects. Since, it is health-related data that is being processed, it becomes crucial that accurate analysis is performed and the results are displayed exactly the way they are in the analysis datasets. There are two ways to validate outputs - Manual method and Automated method. It has been observed that Automated Validation has superseded Manual Validation lately due to many factors such as efficiency, 100% data check, code reusability, etc. However, even if Automated Validation has successfully checked the data, it does not mean that the output generated is perfect. Automated Validation methods are known to have some limitations [1], but there are some other underlying issues which may not be spotted easily and can be missed out. This paper tries to highlight such errors and oversights that occur during validations at data display level which can lead to serious quality issues | data cleaning, proc step, proc report, proc compare | source | 5 |
| 34 | Automatic Access Control via SAS: More Efficient and Smart | Yuichi Koretaka, Masakazu Fujiwara, Yuki Yoshida, Yoshitake Kitanishi |
A wide variety of information is accumulated during clinical trials. In Shionogi & Co. Ltd., as is usual with most of the pharmaceutical companies, the accumulated information is stored as electronic data at specified folders of a server attached to an in-house database system (managed by the Biostatistics Department), considering the property of the information. Development of a drug during clinical phase is carried by a project team consisted of persons from various clinical related departments. Hence, me mbers of Biostatics Department are allocated to the development project team as ones of data analysis team, and can access all the folders in the server. Though, some of the information needs confidential treatment. As for high confidential information (e.g. clinical study report, clinical data, programs and analysis results etc.), the access rights should be given to limited members who have roles deemed appropriate to access respective information (or folders) | macro parameter, excel, clinical research, data science | source | 10 |
| 35 | Automating Pharmaceutical Safety Surveillance process | Pankaj Bhardwaj, Chandramouli Raghuram |
Pharmaceutical companies invest huge amount of effort and cost in launching a drug into the market , keeping the two aspects in mind i.e. safety and efficacy. Post launching the drugs into the market, the organisations then need to monitor the adverse events from these drugs , and need to take the action accordingly. In this white paper few approaches are discussed for automating the post market safety surveillance processes in a cost effective manner. The pharmaceutical companies collect the adverse events data from various he terogeneous sources, and this collected data need to be analysed for the safety surveillance. Generally in post market safety surveillance processes, each Drug -Event case is processed record by record which is causing the exponentially rise of the records and finally leading to the high computational complexity and Analytics performances issues in the system | adverse events, case management, sas base | source | 8 |
| 36 | Automating Production of the blankcrf.pdf | Walter H. Hufford Jr. | The annotated blank Case Report Form (blankcrf.pdf) is a critical component of the NDA submission. Per FDA guidance, source data domain, variable name and controlled terminology for each case report form (CRF) item included in the tabulation datasets submitted should be displayed on the blankcrf.pdf. Production of the blankcrf.pdf is a tedious, non-programming task that is increasingly becoming the responsibility of the statistical programmer. This paper describes an easy to use, automated method of annotating the CRF | crf, controlled terminology, cdisc | source | 5 |
| 37 | Automating the Number of Treatment Columns for a Dose Escalation Study | Catherine DeVerter, Sonali Garg |
In dose escalation studies, there is the need to increase or decrease the number of treatment columns in table output when a new treatment arm is added to the trial. If programs are not written to add the new columns dynamically, they often need to be edited repeatedly. What if we can automate the number of columns to be displayed in the table without having to go and edit the program? This paper will show how SAS programmers can automate and control the number of columns in the table output without having to change the PROC REPORT's COLUMN and DEFINE statements again and again. The method discussed in this paper will make use of the SQL procedure |
proc report, proc step, macro variable, dose escalation, proc sql | source | 5 |
| 38 | Automation of ADAM Dataset Creation with a Retrospective, Prospective and Pragmatic Process | Karin LaPann, Terek J. Peterson |
In the CDISC Standards, analysis datasets (ADaM) hold a unique place in the end to end process and must be created with both a prospective and retrospective view of the entire clinical trial process. Analysis datasets must support the statistical analysis plan (SAP) by providing accurate efficacy and safety analyses. Companies must be pragmatic in deciding which processes can be automated by tools. Industry has tools to effectively transform data to the SDTM structure. These tools should be able build a large portion of the appropriate ADaM datasets with maximum efficiency. The burning question: Can ADaM datasets be built with a mapping tool just like SDTM? | adam dataset, data science, cdisc | source | 6 |
| 39 | Automation of Appending TLFs | William Coar | SAS reports presenting data from clinical trials are typically in the form of summary tables, listings, and figures (TLFs). Whether a small or large set of reports, a single document that appends output files containing bookmarks and a hyperlinked table of contents may better facilitate review and simplify document management. Although numerous techniques exist to append reports, there is much room for improvement when creating a single document composed of multiple TLFs as well as a table of contents directly from SAS. The proposed process takes advantage of external data used to track SAS programming, ODS Document, and PROC DOCUMENT. Generation of the concatenated report requires two primary functions: identification of TLFs to be appended, and then the actual appending. Many companies already have infrastructure for tracking generation and testing individual TLFs produced using SAS |
proc step, proc report, macro variable, character variable, sample, excel | source | 10 |
| 40 | Bad Date: How to find true love with Partial Dates! | Namrata Pokhrel | This poster will discuss the difficulties encountered while trying to impute for partial dates for a specific ISS/ISE study with particularly dirty data. This study contained multiple types of partial dates within a data set. Character dates were in a smorgasbord of DATE9, YYMMDD10, YYYYMMDD, YYMMDD8, formats. Some dates had dashes, some had UNK or UK or nothing at all to represent the missing piece of the date. There were also many partial dates that were simply invalid. The poster will discuss the lessons learned while trying to impute for these partial dates in DATE9 and YYYYMMDD formats in particular and will provide recommendations for future programmers | date variable, clinical trial | source | 11 |
| 41 | Basics of Macro Processing - 'Q' Way | Usha Kumar | Macros have been one of the challenging areas of SAS programming. This paper is an attempt to make the fundamentals of macro processing easy th rough the 'Q' way. It is so named because we will look at the Macro Quoting functions to understand how the Macro works. Ther e are numerous articles on the Macro Quoting functions. To understand the stages of Macr o processing is what is differentiating this paper with other papers/article on the subject | macro variable, macro put, macro quoting function, symbol table, &variable, macro definition, character functions, macro trigger, call symput, put statement, error message, macro function, macro facility | source | 9 |
| 42 | BreakOnWord: A Macro for Partitioning Long Text Strings at Natural Breaks | Richard Addy, Charity Quick |
Breaking long text strings into smaller strings can be tricky, if splitting the string needs to be based on something more than simply length. For example, in SDTM domains, character variables are limited to 200 characters. Excess text need to be placed into supplemental datasets (and the variables there are also limited to 200 characters) - but it's not sufficient to just break the text into 200-character chunks; the text needs to be split between words. This paper presents the BreakOnWord macro, which breaks a long text variable into a set of smaller variables of a length specified by the user. The original text is partitioned text at natural breaks - spaces, as well as user-supplied character values. The macro will create as many variables as necessary, and the variables are named using a user- supplied prefix and an ascending suffix | character variable, macro loop, cdisc | source | 8 |
| 43 | Building Better Programming Teams with Situational Exposure Training | Elizabeth Reinbolt, Steven R. Kirby |
clinical trial, vital signs | source | 3 | |
| 44 | Call me Maybe? Using LinkedIn to make sure you get the call for the job | Tara Potter, Adel Lesniak |
LinkedIn is one of the world's most popular social networking websites and is the leading networking site among professionals today. Whether you are job searching or not, it is critical that you understand the importance of a well written profile and how exactly recruiters and other hiring professionals use this information when searching for top talent. It goes well beyond the basics of your job title, employment history and whether or not you have applied to a posted position. LinkedIn is an excellent tool to help you position yourself accurately within the pharmaceutical and biotech industry and one that recruiters are now using more than ever to find top talent for their organizations | pharmaceutical industry, sas programmer | source | 2 |
| 45 | Career Planning - How to Make it Work for You? - Tips for Programmers, Managers, and Senior Leaders | Vijay Moolaveesala | Most employees depend on their employer's processes to define their career progress and career ladder. Realizing these expectations, many organizations have taken the responsibility of investing in employees' career planning. But, do we need to depend on others for our career growth? Do we need to depend on management or organization's initiative to plan our career? Do we feel that these initiatives are producing the results to the satisfaction of associates? Do we use them effectively? This paper will provide tips to approach career planning which can result in individual employee satisfaction and organization wide positive impact | source | 4 | |
| 46 | Careers in Biostatistics and Clinical SAS Programming: An Overview for the Uninitiated | Justina M. Flavin | In the biopharmaceutical industry, biostatistics plays an important and essential role in the research and development of drugs, diagnostics, and medical devices. Familiarity with biostatistics combined with knowledge of SAS can lead to a challenging and rewarding career that also positively impacts and transforms patients' lives. This paper will provide a broad overview of the different types of jobs and career paths available, discuss the education and skill sets needed for each, and present some ideas for overcoming entry barriers into careers in biostatistics and clinical SAS programming | clinical trial, sas programming, clinical data, data science, pharma programming, csr, clinical research, clinical sas, biostatistician, statistical software, macro definition, proc sql | source | 5 |
| 47 | CDISC Electronic Submission | Kevin Lee | FDA singed FDA Safety and Innovation Act (FDASIA) into law on July 9th, 2012 and announced Prescription Drug user Fee Act (PDUFA) V. And, FDA strongly recommended CDISC as electronic submission formats. The paper will introduce FDASIA, PDUFA V and Data Standard Strategy from FDA. Then, the paper will discuss what it means to programmers who prepare FDA submission. The paper will introduce where programmers can find FDA electronic submission guidelines and CDISC guidelines such as eCTD (electronic common technical document) specification, SDTM implementation guideline, ADaM implementation guideline and etc. First, the paper will provide the brief introduction of regulatory electronic submission such as its methods, five modules in CTD especially m5, technical deficiencies in submission and etc | adam dataset, sdtm domain, data cleaning, character variable, cdisc | source | 6 |
| 48 | CDISC Mapping and Supplemental Qualifiers | Arun Raj Vidhyadharan, Sunil Mohan Jairath |
Mapping of datasets from sponsor defined data structure, otherwise known as Clinical Data Management (CDM) data structure, to CDISC SDTM structure can be one of most trickiest and complex programming situations. There are several methods devised by companies for this purpose. Some use SAS Mapping tools, some use tools based on SAS, VB and EXCEL while some use just SAS programs. Irrespective of the technique used, the basic fundamentals of mapping remain the same. This paper covers the various factors to be considered while mapping, certain unique scenarios one can encounter and possible solutions to them. This paper also covers the creation of SUPPLEMENTAL QUALIFIERS and custom domains and talks about a powerful SAS procedure to validate your SDTM datasets |
sdtm domain, vital signs, cdisc | source | 6 |
| 49 | Challenges in Moving to a Multi-tier Server Platform | Carey G. Smoak | Moving from a simple server to a multi-tier server environment poses many challenges. The multi-tier server environment in this paper includes a physical application (SAS version 9.3) server and a virtual metadata server. No mid-tier (web) server is included in this configuration. The SAS Management Console 9.3 is used to administer the metadata (users, groups, roles and permissions). Two types of clients (SAS Enterprise Guide and the SAS Add- in to Microsoft Office) are used to perform various tasks using the data on the application server. Challenges include: (1) validating SAS on a multi-tier system, (2) understanding and administering metadata using SAS Management Console, and (3) training users on Enterprise Guide and the Add-in to Microsoft Office. The business need for moving to this type of environment was to allow non-SAS users to have read-only access to SAS datasets to monitor and query clinical trial data. This can be accomplished through the Add-in to Microsoft Office | dataset, sas management console, data cleaning, sas enterprise guide, excel, sas programmer, clinical trial, sas administrator, sas programming, stress testing | source | 5 |
| 50 | Challenges in Processing Clinical Lab Data | Alan Meier | Processing Clinical Laboratory data can be among the most complex tasks during analysis data set creation, particularly if the data are coming from local labs. This paper will explore some of these complexities within the CDISC SDTM LB data set structure, including: Determination of how to identify and group the lab tests: Starting with assigning test codes and high-level groupings (hematology, chemistry, urinalysis, etc.), deciding which codes to use, especially if the tests are not in the standard terminologies, and the need to sub-group the tests (proteins, WBC differentials, etc.). Dealing with different lab units: Where can conversion factors be found and how an organization can maintain and reuse them? Safety labs "pesky" urine dipstick textual results (trace, 1+, etc.): What can be done with them? Abnormality Criteria: What criteria can be used to identify abnormalities and what are the complexities involved with them? | sample, laboratory data, controlled terminology, proc sql, cdisc controlled terminology, label statement, ctcae grade, proc step, adverse events, cdisc | source | 15 |
| 51 | Challenges of Processing Questionnaire Data from Collection to SDTM to ADaM and Solutions Using SAS | Karin LaPann, Terek J. Peterson |
Often in a clinical trial, measures are needed to describe pain, discomfort, or physical constraints which are visible but not measurable through lab tests or other vital signs. In these cases, researchers turn to questionnaires to provide documentation of improvement or statistically meaningful change in support of safety and efficacy hypotheses. For example, in studies (i.e. Parkinson's) where pain or depression are serious non-motor symptoms of the disease, these questionnaires provide primary endpoints for analysis. Questionnaire data presents unique challenges in both collection and analysis in the world of CDISC standards. The questions are usually aggregated into scale scores, as the underlying questions by themselves provide little additional usefulness. The SAS system is a powerful tool for extraction of the raw data from the collection databases and transposition of columns into a basic data structure in SDTM which is vertical | adam dataset, controlled terminology, raw data, imputation, sample, change from baseline, data science, missing value, output, annotated crf, edc, vital signs, proc step, data cleaning, proc sql, cdisc | source | 20 |
| 52 | Cleaning up your SAS log: Overwritten Variable Info Messages | Jennifer M. Srivastava | As a SAS programmer, you probably spend some of your time reading and possibly creating specifications. Your job also includes writing and testing SAS code to produce the final product, whether it is SDTM datasets, ADaM datasets or statistical outputs such as tables, listings or figures. You reach the point where you have completed the initial programming, removed all obvious errors and warnings from your SAS log and checked your outputs for accuracy. You are almost done with your programming task, but one important step remains. It is considered best practice to check your SAS log for any questionable messages generated by the SAS system. In addition to messages that begin with the words WARNING or ERROR, there are also messages that begin with the words NOTE or INFO | sas log, by group processing, missing value, laboratory data, cdisc | source | 6 |
| 53 | Clinical Data Dashboards for Centralized Monitoring Using SAS and Microsoft SharePoint | Jagan Mohan Achi | In recent guidance on risk-based monitoring practices, the Food and Drug Administration identified options for monitoring the data quality of a clinical investigation. Centralized monitoring is a practice in which clinical data management, statisticians, and/or clinical monitors1 review the data on an ongoing basis and can easily identify the accuracy, completeness, and integrity of data. In this paper, we would like to describe the methods of developing an in-house tool using SAS BASE (SAS Institute, Cary, NC), GRAPH procedures (SAS Institute, Cary, NC), and Microsoft SharePoint (Microsoft Corporation, Redmond, WA) to achieve this goal. Centralized monitoring may decrease the cost of a clinical investigation and ensure identification of problems with the trial early on by maximizing the value of electronic data capture systems | edc, adverse events, clinical trial, data governance | source | 9 |
| 54 | Clinical Study Report Review: Statistician's Approach | Amita Dalvi | A clinical study report (CSR) is one of many types of regulatory documents that comprise a marketing application for a drug, biologic, or device. A study statistician is a co-author of CSR which is a descriptive account of a single clinical trial accompanied by tables, listings, and figures (TLFs) displaying all study data and results. The study statistician works closely with the medical writer to ensure clarity and accuracy in conveying statistical findings and interpreting results, and addresses any statistical questions. This paper will discuss study statistician's responsibilities in preparing and reviewing CSR. The checklist for study statistician will make clinical study report review relatively easy | clinical trial, csr, database lock, mock shell, randomization, data science | source | 6 |
| 55 | Clinical Trial Data Integration: The Strategy, Benefits, and Logistics of Integrating Across a Compound | Natalie Reynolds, Keith Hibbetts |
From the 2012 FDA/PhUSE Computational Science Symposium Working Group 3 Vision Statement: "Data integration has always been a challenge both for industry and the agency." One approach to address the challenges of integrating and converting data across studies is to build a clinical trial integrated database (IDB). This paper explores the strategy of creating and maintaining IDBs across studies and throughout the life cycle of a compound, the benefits IDBs provide and an effective and efficient metadata-driven system to deal with the logistics of delivering a portfolio of IDBs. First, we'll explore the principles behind the strategy of clinical trial data integration. These principles drive decisions regarding when to create and update IDBs for a compound. Next, we'll discuss how IDBs provide cost and time savings by supporting many objectives including regulatory submissions, answering customer questions and data mining | data cleaning, clinical trial, data integration, data mining, data standard, in=, regulatory submission, logistic distribution, clinical data, data transformation | source | 12 |
| 56 | Come Out of Your Shell: A Dynamic Approach to Shell Implementation in Table and Listing Programs | Paul Burmenko, Tony Cardozo |
In clinical trials, the SAS programmer uses the Statistical Analysis Plan (SAP) provided by the statistician to create Table, Figure and Listing (TFL) programs to support the clinical trial submission. Table and listing shells or mock-ups from the SAP are the SAS programmer's roadmap in generating clinical study reporting outputs. Statisticians or SAS programmers often spend many hours to create shells manually in a word processing application, and then a SAS programmer must spend additional time mimicking the shell's text content and formatting in a table or listing SAS program. What if the shell designer's efforts could be harnessed to reduce the programmer's efforts? This paper presents a case study of how shell content and rich text formatting can be automatically read in from a shell document to create a SAS PROC REPORT shell as a starting point for a table or listing SAS program |
clinical trial, macro variable, sas programmer, proc report, sas output, proc step, sample, adverse events | source | 13 |
| 57 | Common and Comparative Incidence Indicators of Adverse Events for Well-Defined Study Pools | John R. Gerlach | Consider a large Integrated Safety Summary (ISS) study where the analysis of adverse events (AE) is based on well- defined study pools, such that each pool represents a unique collection of subjects. A subject might belong to more than one study pool, perhaps having a particular indication or some other criterion of clinical interest. Besides the standard adverse event reports, that is, a categorized event across treatment groups, it may be required to show incidence with respect to the degree of incidence, very common versus common, as well as in comparison between the study drug and placebo. The task of imputing so-called Common and Comparative incidence indicators becomes more involved since each indicator is determined by its own study pool. Moreover, the workload and its complexity have increased substantially. This paper explains the process of expanding the data set of adverse events (ADAE) and imputing these indicator variables for subsequent analysis | binary variable, adverse events, system organ class, preferred term, trial elements, analysis set, missing value | source | 7 |
| 58 | Common Variables in Adverse Event and Exposure analysis datasets specific for Oncology clinical trials | Haridasan Namboodiri | Cancer remains the second most common cause of dea th in the US with approximately 1 million new cases reported every year. According to the American Cancer Society, Cancer accounts for nearly 1 of every 4 deaths in the US. Cancer is also becoming preva lent in the developing world as it is estimated that o ver 21 million people will have cancer by 2030. Therefore , more and more treatments are entering the market and sponsors are ini tiating new therapies in their clinical trials to treat the disease. Since Cancer is the general name for a group of more than 100 diseases, the initiation of a cancer clinical trial can be different based on the type. That is the first level of complexity in the conduct of a trial. As a next level of complexity , a trial can further investigate whether the study drug is for a treat ment, or for prevention or for screening and whether they can look at different types of cancers with the same study drug | adam dataset, adverse events, clinical trial, adae, cdisc | source | 11 |
| 59 | Compare Without PROC COMPARE | Sri Pavan Vemuri | proc compare, proc step | source | 8 | |
| 60 | Considerations in Creating SDTM Trial Design Datasets | Jerry Salyers, Richard Lewis, Kimberly Minkalis, Fred Wood |
Many sponsors are now submitting clinical trials data to the FDA in the format of the CDISC SDTM. The Trial Design Model (TDM) datasets can be especially challenging because, in most cases, they are being created retrospectively from the protocol, and cannot be created from electronic data. From the most recent Common Data Standards Issues document, it is clear that FDA is placing a greater emphasis on incorporating the trial design datasets into any SDTM based submission. This paper will discuss some of the considerations and challenges in creating the TDM datasets, using case studies of both relatively simple and more complex trials. We will highlight a number of the pitfalls and misconceptions that are commonly seen when sponsors and their vendors attempt to create the TDM datasets for the first time | clinical trial, open label, trial summary, trial design model, cdisc | source | 9 |
| 61 | Considerations in the Submission of Exposure Data in SDTM-Based Datasets | Fred Wood, Jerry Salyers, Richard Lewis, Kristin Kelly |
The submission of data regarding the subjects' exposure to a study treatment is critical in assessing its safety and efficacy. While more and more sponsors are committing resources to submit SDTM-based datasets, our experience in legacy-data conversion has revealed that many studies don't collect sufficient data to get a reliable assessment of actual exposure. Even when such data have been collected, many sponsors are unsure of how to properly represent that data in the SDTMIG Exposure (EX) and Exposure as Collected (EC; new to SDTMIG v3.2) domains. This paper will discuss methods for representing exposure data, as well as some of the challenges sponsors may face in converting data to be consistent with the SDTMIG | exposure, proc freq, concomitant medications, cdisc | source | 6 |
| 62 | Converting Multiple Plain DOC Files to RTF Files in SAS | William Wu, Xiaoxian Dai, Linda Gau |
Creating tables and listings in the Rich Text Format (RTF) has become immensely popular in the pharmaceutical industry. The most common method of creating RTF files in SAS is to use the PROC REPORT procedure with Output Delivery System (ODS). However, it is not easy to create multiple RTF files with uniform formats. An alternative method is to generate RTF files in two steps, which involves the creation of plain DOC files and conversion of DOC files to RTF files. The first step can be easily accomplished with the combination of PROC REPORT and ODS. Currently, there is no easy way to do the second step. In this paper, we introduce a macro, %doc2rtf, which was developed in SAS 9.3 and can be used to convert multiple plain DOC files in the same folder to RTF files with uniform formats. The DOC files are first read and converted to SAS datasets, which is then used to create RTF files based on Rich Text Format Specification Version 1.9.1 by using data _NULL_ step |
dataset, ods rtf, proc report, proc step, macro variable, sas programmer, put statement | source | 13 |
| 63 | Cover the Basics, Tool for structuring data checking with SAS | Ole Zester | Data Cleaning and checking are essential parts of the Stat programmer's tasks. We therefore all develop some simple checks that we use for these tasks. This paper presents a program package for an easier way to structure and over viewing data checks. The program is easy to use and it is very easy to modify with new checks. If you have a common data structure (common between tasks) you can use this to cover some of the basic checks, and spend more time to search for the specials. If your data are changing i.e. not final, this program includes a way of remembering which findings you already have identified, to avoid double-querying. The program also includes a dynamic report which shows both the overview (number of findings) and more detailed information about the individual findings | data cleaning, clinical trial | source | 10 |
| 64 | Create Excel TFLs Using the SAS Add-in | Jeffrey Tsao, Tony Chang |
Creating pivot tables, figures, and listings (pivot TFLs) within Microsoft (MS) EXCEL using SAS Add-in is an easy method to rapidly generate some statistical reports. The creation of pivot TFLs is simple and it can save time and programming resources. The contents of pivot TFLs can be easily refreshed after the source data are updated. In addition, custom SAS code also can be added and run using SAS Add-In of MS Office. This paper will present detailed processes of creating pivot TFLs using SAS Add-in technology |
raw data, excel | source | 6 |
| 65 | Creating a Career GPS to Enhance Your Opportunities: Ten Steps to Improve Your Value by Strengthening Your Planning | Bill Donovan, Shridhar Patel |
Building a successful career in the life sciences field requires that you regularly measure and strengthen your professional value. But personal development is particularly challenging within this sector. The industry thrives on the promise of breakthrough drugs, but the lack of clarity about formulations and the variable cost structure of clinical trials means many seasoned professionals perform in outsourced or contract roles. In this lean, results -focused corporate culture, companies are unwilling or unable to offer career planning resources to the professionals who contribute to pharmaceutical and biotechnology success. Yet the employment boom continues. Certain industry estimates project 30 percent growth through 2016, so hiring remains robust. Within this specialized workforce, a paradigm is shifting. Contract work has become the leading form of employment, the new normal. Now more than ever, you need a detailed plan designed to help drive your career forward | life sciences, clinical endpoint | source | 3 |
| 66 | Creating and Customizing the Kaplan-Meier Survival Plot in PROC LIFETEST in the SAS/STAT 13.1 Release | Warren F. Kuhfeld, Ying C. So |
If you are a medical, pharmaceutical, or life sciences researcher, you have probably analyzed time-to-event data (survival data). The LIFETEST procedure computes Kaplan-Meier estimates of the survivor functions and compares survival curves between groups of patients. Y ou can use the Kaplan-Meier plot to display the number of subjects at risk, confidence limits, equal-precision bands, Hall-Wellner bands, and homogeneity test p-value. Y ou can control the contents of the survival plot by specifying PROCEDURE OPTIONS in PROC LIFETEST. When the PROCEDURE OPTIONS are insufficient, you can modify the graph templates by using SAS macros. PROC LIFETEST in SAS/STAT 13.1 provides many new options for Kaplan-Meier plot modification, and the macros have been completely redone in this release in order to provide more power and flexibility than was available in previous releases. This paper provides examples of these new capabilities |
macro variable, kaplan-meier plot, proc step, macro definition | source | 35 |
| 67 | Creating Define-XML version 2 with the SAS Clinical Standards Toolkit 1.6 | Lex Jansen | In March 2013 the final version of the Define-XML 2.0.0 standard [1], formerly known as CRT-DDS (Case Report Tabulation Data Definition Specification) or "define.xml", as most people called it, was released by the CDISC XML Technologies team. Define-XML 2.0.0 is a major revision of the Define-XML standard for transmission of SDTM, SEND and ADaM metadata. Version 1.0.0 was released for implementation in February 2005 [2]. Define -XML has been a useful mechanism and critical component for providing Case Report Tabulations Data Definitions in an XML format for CDISC based electronic submissions to a regulatory authority such as the U.S. Food and Drug Administration (FDA). This presentation describes new features of Define -XML version 2.0.0, and will then describe how the SAS Clinical Standards Toolkit 1.6 can be used to create define.xml version 2.0 .0 documents. Keywords: CDISC, CRT-DDS, Define-XML, define.xml, metadata, SAS Clinical Standards Toolkit | foreign key, where statement, unique key, controlled terminology, create table, sample, crf, dataset, format statement, imputation, data cleaning, output delivery system, clinical trial, reference data, cdisc | source | 33 |
| 68 | Creating Define.xml v2 Using SAS for FDA Submissions | Qinghua (Kathy) Chen, James Lenihan |
When submitting clinical data to the Food and Drug Administration (FDA), we need to submit the trial results as well as information that help the FDA understand the data. The FDA has required the CDISC Case Report Tabulation Data Definition Specification (Define-XML), which is based on the CDISC Operational Data Model (ODM), for submissions using Study Data Tabulation Model (SDTM). Electronic submission to the FDA is therefore a process of following the guidelines from CDISC and FDA. This paper illustrates how to create an FDA guidance compliant define.xml v2 from metadata using SAS | dataset, clinical data, controlled terminology, cdisc | source | 20 |
| 69 | Creating Multi-Sheet Microsoft Excel Workbooks with SAS: The Basics and Beyond Part 1 | Vincent DelGobbo | This presentation explains how to use Base SAS9 software to create multi-sheet Microsoft EXCEL workbooks. You learn step-by-step techniques for quickly and easily creating attractive multi-sheet EXCEL workbooks that contain your SAS output using the ExcelXP ODS tagset. The techniques can be used regardless of the platform on which SAS software is installed. You can even use them on a mainframe! Creating and delivering your workbooks on-demand and in real time using SAS server technology is discussed. Although the title is similar to previous presentations by this author, this p resentation contains new and revised material not previously presented |
excel, xls, sas output, sas base, format statement, ods xml, proc report, sas log, proc tabulate, output delivery system, datetime, sample, by group processing, dataset | source | 19 |
| 70 | Creating PDF Reports Using Output Delivery System | Shubha Manjunath, Shirish Nalavade |
Output Delivery System (ODS) in V9.2 provides new and enhanced capabilities to programmers for reporting and displaying clinical trials results with numerous options that provide greater control of formatting and layout of the report. The purpose of this paper is to list and demonstrate variety of ODS parameters that help control display of statistical reports while creating PDF reports. Fundamental ODS procedures included in the article but not limited to, are, controlling the structu re of the report (eg. ODS D OCUMENT), sending reports directly to a printer (eg. ODS PDF), inserting text into an ODS output (ODS TEXT =), setting valid values for page orientation (eg. PAGESTYL) and controlling the level of expansion of PDF table of Contents (eg. PDFTOC). These functionalities are illustrated using SAS9.2 version on a Windows operating system |
ods pdf, output delivery system, proc step | source | 5 |
| 71 | D is for Dynamic, putting Dynamic back into CDISC (A simple macro utilizing PROC SQL which auto-formats continuous variables for lab tables) | Steven C. Black | As CDISC implementation increases, the ability and need for simple dynamic code has also risen. Using PROC SQL and the SAS MACRO language coupled with proper use of ADaM guidelines, generating dynamic code has become much easier. This paper illustrates one way of auto generating the decimal format needed for tables where continuous data is arranged by parameters. This code has been especially helpful with laboratory table values where the decimal formats change between each parameter. Understanding and using these same techniques and framework, additional dynamic code can be created allowing you to put the D back into CDISC |
proc sql, proc step, macro variable, do loop, create table, macro loop, standard deviation, macro facility, put statement, macro definition, macro call, macro parameter, sas output, data science, cdisc | source | 9 |
| 72 | Data Standards Development for Therapeutic Areas: A Focus on SDTM-Based Datasets | Fred Wood, Diane Wold, Rhonda Facile, Wayne Kubick |
In recent years, there has been an increasing focus on developing clinical data standards for individual therapeutic areas (TAs). A number of Therapeutic-Area User Guides (TAUGs) have been published via the collaboration of a number of standards-development organizations as well as the FDA. This presentation will provide an overview the TA development structure (CDISC, C-Path, CFAST, TransCelerate Biopharma, Inc.), the standards-development process, and some of the new SDTM (Study Data Tabulation Model)-based domains and concepts. The relationship between domains in the TAUGs and versions of the SDTMIG will also be discussed. Finally, highlights for some of the domains new to the SDTMIG (SDTM Implementation Guide) in v3.2 (e.g., Death Details, Microscopic Findings, Morphology, Procedures, and Skin Response), some of the provisional domains in TAUGs (e.g., Respiratory Measurements, Procedure Agents, and Meals), and the Disease Milestones concept will be presented | clinical trial, data standard, cdisc | source | 10 |
| 73 | Dealing with Missing Data in Clinical Trials | Lucheng Shao | It seems inevitable to encounter missing data in clinical trials no matter how perfect the study was designated and how carefully Clinical Research Associates collected the data. However, having missing values in our original clinical database is not the end of the world for our SAS programmers. The focus of this paper will be showing you how to deal with missing data in clinical trials, especially how to improve the way of representing different types of missing data so that the missing information can be taken advantage of in improving reports. This paper does not cover missing data mechanisms or imputation methods. It is intended for readers who are similar with SAS base but not with different types of missing data | output delivery system, missing value, proc step, character variable, proc print, clinical trial, proc format, date variable | source | 13 |
| 74 | Defensive Programming, Avoiding the Big Mistakes | David W. Franklin | Typically, when you build a small garden shed you should first do some planning, then do construction, and finally look it over and check what you have done and that it is going to do as intended. A similar process is used for writing programs - we should first do some planning, construct the program, and check it over to see that it producing what was asked. This paper takes a brief and lighthearted look at each of these stages, providing a few tips for avoiding some of the many pitfalls and gives a few pieces of SAS code that are useful in development of your program, hopefully avoiding having to say that dreaded phrase, "delete and start again!" | proc step, randomization, adverse events | source | 11 |
| 75 | Defining Non-Inferiority Margins for Skin Adhesion Studies | Marina Komaroff, Sailaja Bhaskar |
The non-inferiority trials might be performed as opposed to, or in addition to the superiority trials. The aim in non- inferiority trials is to demonstrate that the test product is "not worse" than reference listed drug (RLD) or active control by more than the non-inferiority margin. The non-inferiority studies carry some weaknesses such as assay sensitivity, blinding, defining appropriate non-inferiority margins. Yet, the use of active control in non-inferiority trails might be the only choice to demonstrate the efficacy of a new product when the use of placebo arm is not ethical. Another example is transdermal products where it is recommended that the adhesion performance of the test patch should be compared to the adhesion performance of RLD. One of complexities of non -inferiority trials is to define an appropriate non -inferiority margin (E) | sample size, sample, proc power and sample size, confidence interval, standard deviation, phase i, proc freq, data science | source | 12 |
| 76 | DefKit : A Micro Framework for CDISC Define-XML Application Development | Lei Zhang | CDISC Define-XML specification [1] provides an extended ODM model to describe the clinical data and statistical analyses submitted for FDA review. However, because of the inherent complexity, creating define.xml files from clinical studies poses many challenges to SAS programmers. In this paper, we introduce a micro-framework called DefKit to facilitate the development of CDISC/XML applications. DefKit is designed as a rapid development framework, and is built specifically for SAS programmers who want to have a simple way to create CDISC/XML applications, such as define.xml generators. The toolkit that the DefKit framework provides consists of a very small set of macros and user defined functions (UDFs), and employs hash objects for fast data retrieval and XML generation. This paper first introduces the organization and usages of the DefKit framework components, and then provides examples to illustrate how to generate define.xml elements with DefKit | hash table, data step, character variable, where statement, macro variable, clinical trial, sas programmer, proc step, excel, cdisc | source | 23 |
| 77 | Demystify "Ten years of pharma programming experience required" - What hiring managers actually look for | Peng Yang | Pharmaceutical SAS programmer job descriptions often times specify a certain number years of experience as a requirement. But what exactly does it mean to have 5 or 10 years of experience? Does one person's 10-years count the same as another person's 10-years? In this paper, we will discuss the relationship between industry experience length and some key qualifications for a successful pharma SAS programmer. Some of the qualifications are not quantifiable and elusive to explain, thus the number of years is used as one of the simplified criteria in job posting. Discussion around the qualifications can help recruiters conduct more effective screening and it can also enable candidates to write more specific and informative resumes for their job search | clinical trial, clinical research | source | 3 |
| 78 | Deploying a User-Friendly SAS Grid on Microsoft Windows | Houliang Li | Your company's chronically overloaded SAS environment, adversely impacted user community, and the resultant lackluster productivity have finally convinced your upper management that it is time to upgrade to SAS grid to eliminate all the resource problems once and for all. But after the contract is signed and implementation begins, you as the SAS administrator suddenly realize that your company-wide standard mode of SAS operations, i.e., using the traditional SAS Display Manager on a server machine, runs counter to the expectation of SAS grid - your users are now supposed to switch to SAS Enterprise Guide on a PC. This is utterly unacceptable to the user community because almost everything has to change in a big way. If you like to play a hero in your little world, this is your opportunity. There are a number of things you can do to make the transition to SAS grid as smooth and painless as possible, and your users get to keep their favorite SAS Display Manager | sas grid, sas enterprise guide, batch job, work library, grid computing, sas administrator | source | 6 |
| 79 | Design of Experiments (DOE) Using JMP | Charles E. Shipp | JMP has provided some of the best design of experiment software for years. The JMP team continues the tradition of providing state-of-the-art DOE support. In addition to the full range of classical and modern design of experiment approaches, JMP provides a template for Custom Design for specific requirements. The other choices include: Screening Design; Response Surface Design; Choice Design; Accelerated Life Test Design; Nonlinear Design; Space Filling Design; Full Factorial Design; Taguchi Arrays; Mixture Design; and Augmented Design. Further, sample size and power plots are available. We give an introduction to these methods followed by a few examples with factors | quality control, sample size | source | 4 |
| 80 | Developing ADaM Specifications to Embrace Define-XML 2.0.0 Requirements | Lin Yan | The CDISC Define-XML 2.0.0 standard was released in March 2013. The new standard has quite a few new features and requirements. In order to adopt the new standards, sponsors need make changes accordingly in the ADaM specification files, which are usually used as programming guidance and as the basis of the generation of ADaM define-XML as well. This paper will discuss the new features and requirements in the Define-XML 2.0.0 that have direct impact to ADaM specifications. Also, this paper will use examples to illustrate what changes/enhancements in the ADaM specifications should be added to meet the requirements specified in Define-XML 2.0.0 | controlled terminology, sample, where statement, format statement, adam dataset, cdisc controlled terminology, cdisc | source | 10 |
| 81 | Developing Graphical Standards: A Collaborative, Cross-Functional Approach | Mayur Uttarwar, Murali Kanakenahalli |
"A picture is worth a thousand words:" a quote proven by the fact that graphs are increasingly used in reporting clinical trial data. Conventionally, SAS Graph procedures in conjunction with annotation datasets have been used to create graphs, but recentl y SAS Graph Template Language (GTL) is gaining ground. GTL is very powerful in its ability to allow the building of complex and intricate graphs using a structured approach. However, the key factor in leveraging the full potential of GTL and maximizing program efficiency is to establish graphical standards. This paper addresses the need for graphical standards, showcases a collaborative approach with cross -functional partners to identify & standardize common graph attributes, and provides one style templ ate & one graph template that can support multiple graph types | scatter plot, line chart, censoring, clinical trial, macro definition | source | 5 |
| 82 | Discover Define-XML | Mark Wheeldon, Kevin Burges |
Previously, Define.pdf was used as a submission deliverable to enable FDA reviewers to understand the content of submitted proprietary datasets. Define-XML was introduced by CDISC as a machine-readable alternative, and this has replaced Define.pdf as a mandatory part of an eCTD-based FDA submission. Define-XML is still often seen as an afterthought, only produced when datasets are ready to be submitted | proc contents, sdtm domain, clinical trial, where statement, data cleaning, cdisc | source | 12 |
| 83 | Distance Management: how to lead a team of SAS users who sit half a world away | Max Cherny | This focus of the paper will be the author's experience of managing a large group of SAS users (both programmers and statisticians) based in India. The paper will describe advantages and challenges of managing such a group as well as various project management techniques to guide the projects to successful completion | sas base, clinical research | source | 4 |
| 84 | Don't Type, Talk SAS | Vikas Gaddu, Smitha Madhu |
Are you a lazy but smart programmer? Then you will like my paper!! We have seen that SAS programs over the last decade have started becoming more and more standardized. We have standard headers, standard init files, standard macros and standard ways to output reports and each client has their own standards. In turn, we are required to remember lot of standards and their documentation. What if we could talk to SAS and these standard structures would automatically appear in your code? This is now possible with Windows Speech Recognition Macros | macro facility, anova | source | 6 |
| 85 | Effective Use of Metadata in Analysis Reporting | Jeffrey M. Abolafia | Many organizations are effectively using metadata for the creation and validation of clinical and analysis databases. The use of metadata for analysis reporting, however, lags behind that of database production. While many sponsors have submitted define.xml to document ADaM databases, very few of these files have included analysis results metadata. This despite a recent CDISC pilot, which demonstrated that results level metadata adds significant value to a regulatory submission. As the CDISC ADaM model has matured as an analysis dataset standard it, combined with results related metadata, can be utilized to facilitate producing displays and statistical analysis and easily be extended to generate the results portion of define.xml file | adam dataset, data cleaning, clinical trial, data science, cdisc | source | 9 |
| 86 | Efficient SQL for Pharma ... and Other Industries | Christopher R. Olinger | The SQL Procedure has been used for many years by many different types of SAS programmers. This paper delves into how PROC SQL processes internally, and how the user can exploit this information to improve performance with larger data sets. We will go over common tricks such as use of _method, as well as talk about views, updates, and the implications of sorting and IO "hints" that you can specify to PROC SQL to perform better. This talk is intended for persons already familiar with PROC SQL, SAS configuration options, and that have used PROC SQL in a clinical setting |
proc sql, proc step, proc sort, cpu time, order by, where statement, create table, by group processing, sas log, update statement, dataset | source | 15 |
| 87 | Enhancing your Career by Bringing Consultants Into Your Organization | Roger D. Muller, Gregory S. Barnes Nelson |
No matter how outstanding you are as programmer, your value to the organization that employs you is based upon your perceived contributions to the overall goals and success of the organization. This paper addresses the role that consultants (both external and internal) can bring to an organization, thereby enhancing not only your performance, but that of others. Issues are presented for both the client and consultant. Consultants can have a larger view than just that of the task at hand. They can play a vital role in helping establish the direction to be taken on not only current work, but also on future projects. In the process, the client associated with bringing the consultant into the organization will be perceived as a strong team player. It is essential that the consultant and the sponsor be proactive in broadcasting their accomplishments and make higher levels of management aware of progress | data governance, service provider | source | 6 |
| 88 | Estimating Medication Adherence Using a Patient-Mix Adjustment Method | R. Scott Leslie | The Centers for Medicaid and Medicare Services (CMS) and several national health care quality organizations regard medication adherence as a major attribute of quality of care. The preferred method of measuring medication adherence is the Proportion of Days Covered (PDC) by medication(s) over a specified review period. Although PDC can be calculated fairly easily from pharmacy claims using relatively little data elements, patient's medication adherence is most likely confounded by patient demographics and other measurable and immeasurable factors. This paper explores the use of a patient-mix adjustment method to account for patient's characteristics and previous medication history. Included is a description of a macro used to calculate PDC and estimate medication adherence | do loop, insurance claims, data step, binary variable, risk adjustment | source | 9 |
| 89 | Evaluating the benefits of JMP for SAS programmers | Xiaopeng Li, Chun Feng, Nancy Wang |
JMP is a user friendly software for creating figures in clinical research. For SAS programmers, JMP also provides a convenient way to do quality control (QC) of listings, tables, and figures (TFLs). Additionally, using JMP for QC is an alternative way to verify statistical analysis results, a quick way to verify SAS code for statistical analysis tables, and a way to do QC documentation. This paper provides details about what supports and benefits JMP can provide for SAS programmers | data science, sas programmer, clinical research, independent qc, proc means | source | 9 |
| 90 | Expediting Access to Critical Pathology Data | Rebecca Ottesen, Leanne Goldstein, Julie A. Kilburn, Joyce C. Niland |
Abstracting information from pathology notes is often quite cumbersome. Clinical Research Associates and Tumor Registrars typically have to read through all of the diagnosis information and manually enter the data into a database for fields such as tumor size, lymph nodes, and staging. This manual process can lead to data that is subject to interpretation and data entry errors, in addition to the workload burden. In this presentation, we will demonstrate approaches to simplifying data abstraction from pathology reports using various SAS programming techniques. First, we consider the use of semi-coded College of American Pathologists (CAP) synoptic worksheet data based on a check list filled out by pathologists when reviewing a surgical specimen. We also evaluate the approach of performing string searches on the unstructured pathology dictation using functions such as INDEX() and SUBSTR() | data mining, dataset, parsing, proc freq | source | 8 |
| 91 | Express Yourself! Regular Expressions vs SAS Text String Functions | Spencer Childress | SAS and Perl regular expression functions offer a powerful alternative and complement to typical SAS text string functions. By harnessing the power of regular expressions, SAS functions such as PRXMATCH and PRXCHANGE not only overlap functionality with functions such as INDEX and TRANWRD, they also eclipse them. With the addition of the modifier argument to such functions as COMPRESS, SCAN, and FINDC, some of the regular expression syntax already exists for programmers familiar with SAS 9.2 and later versions. We look at different methods that solve the same problem, with detailed explanations of how each method works. Problems range from simple searches to complex search and replaces. Programmers should expect an improved grasp of the regular expression and how it can complement their portfolio of code. The techniques presented herein offer a good overview of basic DATA STEP text string manipulation appropriate for all levels of SAS capability |
sas programmer, data step | source | 10 |
| 92 | Factor Analysis of Scale for Assessment of Negative Symptoms using SAS Software | Ben Adeyi, David Shen |
The objective is to study the psychometric properties of the SANS (Scale for the Assessment of Negative Symptoms) using factor analysis, and investigate the feasibility of shortening the current version of the SANS. SANS data were examined with exploratory factor analysis to identify the principle components of SANS. The results showed that the SANS consisted of three factors, suggested a short SANS with 3 response cluster options of 10 items. Confirmatory factor analysis demonstrated the reliability of the short version of SANS | factor analysis, estimate, proc princomp, confirmatory factor analysis, clinical trial, correlation, sample size, scree plot, proc step, covariance, sample, proc calis | source | 8 |
| 93 | Five Ways to Flip-Flop Your Data | Joshua M. Horstman | Data is often stored in highly normalized ("tall and skinny") structures that are not convenient for analysis. The SAS programmer frequently needs to transform the data to arrange relevant variables together in a single row. Sometimes this is a simple matter of using the TRANSPOSE procedure to flip the values of a single variable into separate variables. However, when there are multiple variables to be transposed to a single row, it might require multiple transpositions to obtain the desired result. This paper describes five different ways to achieve this flip-flop, explains how each method works, and compares the usefulness of each method in various situations. Emphasis is given to achieving a data-driven solution that minimizes hard-coding based on prior knowledge of the possible values each variable can have and that improves maintainability and reusability of the code |
proc transpose, proc step, response variable, by group processing, merge statement, proc sql, sas programmer, keep statement, sample | source | 9 |
| 94 | Forging New SDTM Standards for In-Vitro Diagnostic (IVD) Devices: A Use-Case | Carey G. Smoak, Smitha Krishnamurthy, Mansi Singh, Sy J. Truong |
How does a new data standard get established for medical devices? Data standards for medical devices have made good progress recently with the development of seven new SDTM domains specifically intended for medical device submissions. These seven new domains address the requisite domains to capture the data that is unique to medical devices because medical device data can be distinct and different from pharmaceutical and biotechnology data. These seven medical device domains were intended to capture data that is commonly collected across various types of devices. Currently, in SDTM for drugs, there is an on-going effort to develop therapeutic specific standards (e.g., Alzheimer's, Parkinson's, etc.). Similarly, within medical devices there is a need to develop standards for various types of devices. This paper addresses one such need to design domains specifically for In-Vitro Diagnostic (IVD) devices which are different from other medical devices (e.g., implantable devices) | sdtm domain, sample, sas programming, data standard, laboratory data, cdisc | source | 6 |
| 95 | From "Just Shells" to a Detailed Specification Document for Tables, Listings and Figures | Supriya Dalvi | We are assigned a new study. We go through the protocol, the statistical analysis plan, the mock up shells and start programming. The basic annotations for the mock up shells is been done. The programmer uses this as a specification document for generating the outputs; similarly the validator uses it for QC of the outputs. There are some differences in understanding between the two as the shells are not "clear enough" leading to discussions amongst them , also involving the statistician at several times .At the time of Statistical review, it is observed there are inconsistencies in the layout of the reports, date formats, visit orders, treatment group information, common derivations etc… The result: a lot of rework on correcting these issues, loss of time, confusions and a question mark on the quality of the reports. Could this have been avoided if the mock up shells were given some more attention than what they got? May be Yes…How? Let's try to understand… | statistical programmer, data science | source | 13 |
| 96 | Functioning at a Higher Level: Using SAS Functions to Improve Your Code | Peter W. Eberhardt, Lucheng Shao |
SAS provides many built in functions that will help you write cleaner, faster code. With each new release of SAS there are new functions added; in many cases these new functions are overlooked because we have developed coding habits to try to accomplish the same result as these functions. In this paper we will survey some functions we find useful. In addition we will touch on how you can turn your code habits into functions | missing value, sysdate9, sas function, date variable, datetime variable, character variable, macro function, character functions | source | 12 |
| 97 | Give me EVERYTHING! A macro to combine the CONTENTS procedure output and formats | Lynn Mullins | The PROC CONTENTS output displays SAS data set information such as variable name, type, length, informats, and format names. The values and codes for the formats are not included in this output; therefore, a separate printout of the program that creates the formats or a printout of the format catalog via DATA STEP programming needs to be used in conjunction with the PROC CONTENTS output. This paper will describe a SAS macro that combines PROC CONTENTS output with the format catalog data to create a single metadata dictionary file |
proc contents, proc step, proc format | source | 6 |
| 98 | Good versus Better SDTM - Why "Good Enough" May No Longer Be Good Enough When It Comes to SDTM | Henry B. Winsor | While companies are finally making strong efforts to use and provide SDTM, mostly because of serious encouragement from the FDA, there seems to be some misunderstandings about why this work needs to be done. Although originally strictly intended to replace paper Case Report Tabulations with data that is electronically accessible, SDTM is being used - and abused -- with other purposes in mind. Problems arise when people forget what SDTM is for and tailor their implementations for something other than easing the Reviewer's task. The author provides a gentle reminder of SDTM's real purpose in the FDA submission world and some suggestions of how and why to maximize your company's benefit from having SDTM data sets available for use, preferably long before a CSR or eCTD is complete | clinical data, adverse events, clinical trial, cdisc | source | 6 |
| 99 | Graphical Representation of Patient Profile for Efficacy Analyses in Oncology | William Wu, Xiaoxian Dai, Linda Gau |
With the advancement of cancer care and the need to develop new therapies for cancer, oncology clinical trials have become more and more popular. Currently, most of the efficacy analyses in oncology clinical trials are represented by tables and listings. For patients with multiple visits, it is not convenient to read and understand the information presented in the tables and listings. In this paper, we introduce a SAS macro developed in SAS 9.3 to create patient profile graphs in a multi-page PDF file using the SAS Output Delivery System (ODS) for efficacy analyses. On each page of the PDF file, there are two graphs. In addition, supporting information is added as listings to the graphs using the SAS Annotate Facility. Efficacy data for patients with chronic lymphocytic leukemia (CLL) are used to generate the graphics output using the developed SAS macro. Compared to the tables and listings, the graphs are more intuitive and much easier to understand |
clinical trial, ods pdf, sample | source | 7 |
| 100 | Guidelines for Protecting Your Computer, Network, and Data from Malware Threats | Ryan Paul Lafler, Kirk Paul Lafler |
Malware, sometimes referred to as malicious software, represent software threats engineered to damage computer systems, networks and data without the knowledge of the owner using the system. All users are increasingly becoming more prone to malware attacks and need to have strategies and a set of guidelines to help them get the most out of their antivirus software. This poster highlights a classification of malware threats, the types of computer threats, detection strategies, removal methods, and provides guidelines for the protection of essential assets | source | 9 | |
| 101 | Handling with missing data in clinical trials for time-to-event variables | Giulia Tonini, Simona Scartoni, Angela Capriati |
Missing data is often a major issue in clinical trials, especially when the outcome variables come from repeated assessments. In particular, time-to-event endpoints can be substantially affected by a too conservative treatment of missing data along the observation period. When neglected or not properly treated, missing data may bias the results, reduce power and lead to wrong study conclusions. The advantage of a more sophisticated statistical method versus the traditional clinical method, such as last observation carried forward (LOCF), is still under debate. We compare the two methods in a clinical study testing the efficacy of an anti -arrhythmic agent versus placebo on the time to Atrial Fibrillation (AF) recurrence, where the maintenance of normal heart rhythm or the occurrence of the AF event was to be daily evaluated by trans -telephonic ECG recorded by the patients. A Cox model is applied for the comparison between treatments | missing value, imputation, proc mi, multiple imputation, proc step, proc phreg, treatment effect, data science, regression analysis, logistic regression, clinical trial, logistic distribution, last observation carried forward | source | 9 |
| 102 | Hands-On ADaM ADAE Development | Sandra Minjoe, Kimberly Minkalis |
The Analysis Data Model (ADaM) Data Structure for Adverse Event Analysis1 was released by the Clinical Data Interchange Standards Consortium (CDISC) ADaM team in May, 2012. This document is an appendix to the ADaM Implementation Guide (IG)1, and describes the standard structure of the analysis dataset used for most of our typical adverse event reporting needs. This hands-on training focuses on creating metadata for a typical adverse event (AE) dataset. Attendees will work with sample SDTM and ADaM data, finding information needed to create the results specified in a sample set of table mock-ups. Variable specifications, including coding algorithms, will be written. Some familiarity with SDTM data, AE reporting needs, SAS DATA STEP programming, and Microsoft EXCEL is expected. Attendees will also learn how to apply the data structure for similar analyses other than adverse events |
adverse events, adam dataset, in=, concomitant medications, system organ class, medical history, imputation, study day, cdisc | source | 7 |
| 103 | Having Fun with RACE Derivation in DM Domain | Chunxia Lin, Deli Wang |
Race in SDTM DM domain is an expected variable; generally it is quite easy to derive. However, there are times when raw database is set up with multiple race variables (RACE_X), and a subject may have multiple race values. Some clients require that, if a subject has more than one race values, set RACE as "MULTIPLE", otherwise, set to the single selected race value. The logic looks simple, however SAS programmers have to figure out two important steps before coding: 1. whether the subject has more than one race variables selected; 2. which race variable has nonmissing value. The Multiple IF-THEN/ELSE statements work fine but the coding is a little tedious. This paper introduces four methods to derive RACE using the logical expression and SAS functions. Each of the methods is discussed separately depending on the attributes of the data (character/numeric) | proc sql, proc step, sas function, sum, if-then-else, sas programmer, missing function, cdisc | source | 5 |
| 104 | Healthcare Data Manipulation and Analytics Using SAS | Lumin Shen, Jane Lu |
Increasing application of information technology in the healthcare delivery system helps healthcare industry gain valuable knowledge from data, and use this insight to recommend action or guide decision making, and improve quality of patient care and practice of medicine. There is more data available than ever before. How can it truly benefit patients, payers and healthcare providers? Analytics can help medical researchers exploit healthcare data to discover knowledge lying implicitly in individual patients' health records, physicians identify effective treatments and best practices, patients receive better and more affordable healthcare services, and healthcare insurance companies detect fraud and abuse. This article explores analytics applications in healthcare industry. It illustrates the process of data integration and exploration, and building of predictive models to find previously unknown patterns and trends. It also presents analytics applications in major healthcare areas | proc step, regression analysis, proc sql, proc quantreg, libname statement, proc freq, logistic distribution, correlation, odbc connection, proc means, discriminant analysis, numeric variable, adverse events, missing value, sql server, histogram, data mining, outlier, poisson distribution, data science, data cleaning | source | 11 |
| 105 | How to Keep Multiple Formats in One Variable after Transpose | Mindy Wang | In clinical trials and many other research fields, PROC TRANSPOSE are used very often. When many va riables with their individual formats are transposed into one variable, we lose the formats. We can do a series of if then statements to put the formats back in. However, when the variables involved are too many, the abo ve method can be very tedious. This paper illustrates how to extract formats from dictionary.columns or sashelp.vcolumn , and then use PUT N function to assign the formats at run time and make the task much easier. In addition, it is much easier to apply the same method to other projects wit hout using a lot of if then statements in the SAS program. Efficiency is largely increased with this method |
putn, excel, proc sql | source | 8 |
| 106 | How To Win Friends and Influence People - A Programmer's Perspective in Effective Human Relationships | Priscilla Gathoni | Dealing with people has become a task and an art that every person has to master in the work and home environment. This paper explores 15 different ways that a programmer can use to win friends and influence people. It displays the steps leading to a positive, warm, and enthusiastic balanced work and life environment. The ability to think and to do things in their order of importance is a key ingredient for a successful career growth. Programmers who want to grow beyond just programming should enhance their people skills in order to move up to the management level. However, for this to be a reality a programmer must have good technical skills, possess the ability to arouse enthusiasm among peers, and is able to assume leadership. It is the programmer that embraces non- judgment, non-resistance, and non-attachment as the core mantras that will succeed in the complex and high paced work environment that we are in | clinical trial, macro definition | source | 9 |
| 107 | How Valued is Value Level Metadata? | Shelley Dunn | One of the challenges of implementing SDTM and ADaM is the vertical data structure where some variables are dependent on test code (xxTESTCD) in SDTM or Parameter (PARAMCD) in ADaM. This type of metadata is described as "value level metadata" and at a basic level describes the metadata of one variable based on the value of another variable. For example, how do you describe the result of a Vital Sign (VSORRES) when the Vital Signs test code (VSTESTCD) is WEIGHT? This definition can be different for different values of the test code and is best described based on those values. The underlying question is whether this type of value level metadata is important and what value it provides to stakeholders. Stakeholders include a wide range of people such as study specification creators, SAS programmers, standards developers, and FDA reviewers, each of which might have different needs | database lock, crf, cdisc | source | 12 |
| 108 | I Am Legend | Kriss Harris | Have you ever produced a legend on a plot that was taking up too much space, hence making the actual graph too small? Have you ever removed a legend because it was taking up too much space? Have you ever wanted to just produce a legend? Have you ever wondered that there must be a more efficient way of producing a legend then using the exact same legend on every BY variable of your output? This paper will demonstrate solutions to the above problems using Graph Template Language (GTL) in SAS 9.2, in particularly using the SERIES, VECTOR and SCATTERPLOT statements | line chart, ods listing | source | 13 |
| 109 | I Object: SAS Does Objects with DS2 | Peter W. Eberhardt, Xue Yao |
The DATA STEP has served SAS programmers well over the years, and although it is powerful, it has not fundamentally changed. With DS2, SAS has introduced a significant alternative to the DATA STEP by introducing an object-oriented programming environment. In this paper, we share our experiences with getting started with DS2 and learning to use it to access, manage, and share data in a scalable, threaded, and standards-based way |
missing value, macro function, macro variable, proc step, sas function, dataset, return, sysdate9, sas programmer, proc sql, data step | source | 29 |
| 110 | Indexing: A powerful technique for improving efficiency | Arun Raj Vidhyadharan, Sunil Mohan Jairath |
The primary goal of any programmer is "to get the desired output". Once we have a plan to achieve this primary goal, there should ideally be a secondary goal, which is "to get the desired output, efficiently". Most programmers are successful in achieving the primary goal while at least some don't pay much attention or don't feel the necessity of the secondary goal. This paper focuses on a technique called indexing in SAS that could drastically improve the performance of SAS programs that access small subsets of observations from large SAS data sets. This paper covers creation of simple and composite indexes, determining ideal candidates for index key variables, understanding when to use index and how to generate index usage messages | index, dataset, proc step, by group processing, proc sql, cpu time, where statement, index creation, modify statement, set statement, libname statement | source | 9 |
| 111 | Inserting MS Word Document into RTF Output and Creating Customized Table of Contents Using SAS and VBA Macro | Haining Li, Merit E. Cudkowicz, Hong Yu |
In clinical trials, to effectively monitor study progress and subject safety, the investigators are frequently requested to submit a set of tables and listings at regular basis throughout the study. With the ODS (Output Delivery System) RTF destination, the programmers could build tables and listings that are opened directly in MS Word and other word- processing packages. However, to expedite the review process, with each submission, a Summary Report to highlight any study update during the report cycle is highly recommended. In practice, the key study team members often provide the programmers with a MS Word document with multiple sections of study updates to be inserted into the RTF outputs. Having all information consolidated in one document will keep the integrity of the report and make it easy for reference |
ods rtf, clinical research | source | 6 |
| 112 | Internal Consistency and the Repeat-TFL Paradigm: When, Why and How to Generate Repeat Tables/Figures/Listings from Single Programs | Tracy Sherman, Brian P. Fairfield-Carter |
The concept of 'repeat' tables/figures/listings (TFLs), those being groups of 'similar' output that are understood to require less time and effort to produce than 'unique' TFLs, is probably familiar to most programmers. But even with the interest programmers have in improving efficiency and reducing maintenance overhead, it's surprising how often the relationship between repeat TFLs isn't exploited in code-writing. Perhaps this stems from inadequate planning (i.e. allocating work to a rapidly-assembled programming team without first assessing relatedness among TFLs), possibly combined with a lack of understanding of either the importance of grouping related output, or of the programming techniques that can be applied in producing repeat TFLs, but in any event we often see projects that follow a '1 table/1 program' (1:1) paradigm, and which treat each TFL in isolation | macro loop, %if-%then-%else, macro definition, proc step | source | 10 |
| 113 | Investigating the Irregular: Using Perl Regular Expressions | Peter W. Eberhardt | A true detective needs the help of a small army of assistants to track down and apprehend the bad guys. Likewise, a good SAS programmer will use a small army of functions to find and fix bad data. In this paper we will show how the small army of regular expressions in SAS can help you. The paper will first explain how regular expressions work, then show how they can be used with CDSIC | data cleaning, data step | source | 18 |
| 114 | It's not the Yellow Brick Road but the SAS PC FILES SERVER will take you Down the LIBNAME PATH= to Using the 64-Bit Excel Workbooks | William E. Benjamin Jr. | SAS users who also use EXCEL or produce EXCEL workbooks will eventually find that the rapid pace of hardware and software changes occurring today will soon meet them head on. The need for faster computers and bigger workbooks are accelerating. This issue is not new, 8-Bit computers were replaced with 16-Bit CPU's, and they lost the battle to 32-Bit computers. Today new computer hardware routinely comes with up to eight 64-Bit CPUs in a single 2X2 piece of hardware for an affordable price. The fictional path down the yellow brick road to OZ was fraught with many challenges. SAS Institute has stepped up to the challenge of the way their users mix and match hardware and software. Since SAS Institute could not control the users and their hardware, the institute expanded the way programmers can use the LIBNAME statement to create a PATH= to open the way to create and read new EXCEL formats |
excel, xls, libname statement, proc sql, sas log, proc step, name range list | source | 14 |
| 115 | JMP Visual Analytics | Charles E. Shipp | For beginners, we review the continuing merging of statistics and graphics. Statistical graphics is the forte of JMP software and the JMP team pioneered the way for SAS Visual Analytics. Moving forward into Version 11, JMP has easy navigation, a graph builder, advanced algorithms in 85 platforms, and robust statistics you can trust. For olde-timers, we celebrate JMP success and discuss evolving and emerging developments, which we saw at the JMP Discovery Summit 2013 with the new Design of Experiments additions and other additions to JMP Version 11. New also is the entry of the 12th platform for experimental design, the Definitive Screening Design, adding selected midpoints. Many of the views will be shown in the presentation, and a lively discussion will continue in the hallway! | correlation, quality control | source | 7 |
| 116 | Kaizen | Usha Kumar | In an ever-growing, demanding and changing world, we need to understand that the pursuit for excellence is endless. There needs to be a process of continuous improvement. This being the basis of my paper, I would elaborate on certain principles from the management theory that can be practiced at individual leve l. The process of continuous improvement at individual level when practiced by many in an organization develops a CULTURE, where QUALITY becomes a habit. CULTURE builds a successful and healthy workplace. I present KAIZEN and other principles that can help implement KAIZEN as a self-improving technique | csr, clinical trial | source | 5 |
| 117 | Kaplan-Meier Survival Plotting Macro %NEWSURV | Jeffrey P. Meyers | The research areas of pharmaceuticals and oncology clinical trials greatly depend on time-to-event endpoints such as overall survival and progression-free survival. One of the best graphical displays of these analyses is the Kaplan- Meier curve, which can be simple to generate with the LIFETEST procedure but difficult to customize. Journal articles generally prefer that statistics such as median time-to-event, number of patients, and time-point event-free rate estimates be displayed within the graphic itself, and this was previously difficult to do without an external program such as Microsoft EXCEL. The macro NEWSURV takes advantage of the Graph Template Language (GTL) that was added with the SG graphics engine to create this level of customizability without the need for backend manipulation. Taking this one step further, the macro was improved to be able to generate a lattice of multiple unique Kaplan-Meier curves for side by side comparisons or condensing figures for publications |
class variable, macro parameter, macro call, graph template language, time variable, hazard ratio, proc step, proc phreg, confidence interval, character variable, numeric variable, proc means, where statement, kaplan-meier plot, treatment effect, data transformation, overall survival, progression-free survival, excel, proc sql | source | 19 |
| 118 | Let Chi-Square Pass Decision to Fisher's Programmatically | Linga Reddy Baddam, Sudarshan Reddy Shabadu |
There is often the question of "when" a nd "which" statistical test should be used against any kind of clinical data in wide variety of situations as there ar e many significant cases when insufficient information can lead a statistician to choose an inappropriate analysis. It is common to test th e hypothesis of independence of events across different treatment arms to identify the appropriate statistical test based on certain clinical reporting criterion and the clinical programmer has to develop code to carry out the subsequ ent statistical tests based on the nature of data and assumptions which have been made. In order to optimize e fforts of clinical programmers, automating such code to find the appropriate statistical test is key-job and the featur es of such an automated %fc_pval macro are discussed in further detail in this paper | fisher exact test, exact test, chi-square test, proc freq, sample, clinical data | source | 5 |
| 119 | Let Hash SUMINC Count For You | Joseph W. Hinson | Counting of events is inevitable in clinical programming and is easily accomplished with SAS procedures such as FREQ, MEANS, SUMMARY, TABULATE, SQL or even by simple DATA STEP statements. In certain situations where counting is a bit intricate involving data partitioning and classifying, another convenient and efficient way is by hash programming. Within the DATA STEP, hash objects make data directly available to summary variables without the need to first save the data into a dataset. A little-known hash utility, SUMINC, was introduced with SAS version 9.2. SUMINC is an argument tag for the hash object declaration statement in which it designates a numeric variable for counting. Together with other new SAS 9.2 hash methods REF() and SUM(), counting of items becomes feasible in a key-based manner thus allowing any pattern of counting to be easily accomplished and directly available for summary reporting, as demonstrated in this paper for clinical trial protocol deviation analysis |
hash table, protocol deviations, proc sql, proc freq, clinical trial | source | 7 |
| 120 | Let SAS Do That For You | Emmy V Pahmer | Do you ever repeat certain tasks and think there should be a better or easier way to do them? Choosing and copying files are tasks that we often perform manually but which can easily be done by SAS using particular selection criteria. We'll look at how to get a list of files in a directory, some code to select the desired file, creating a warning message if more than one file fits the criteria or if no files fit the criteria, and copying the file(s). This presentation is suitable for all users, including beginners | macro variable, proc print, proc step | source | 4 |
| 121 | Let SAS Improve Your CDISC Data Quality | Wayne (Weizhen) Zhong | How often is "but this data passed OpenCDISC" used as a defense for poor quality data? Adoption of data standards benefits reviewers and analysts by keeping data structures consistent. Ensuring data integrity however remains a manual labor with edit checks or eyeballing. This paper presents a data quality control application for CDISC data: using the metadata of CDISC datasets to trigger SAS code modules, running relevant checks for each dataset and presenting issues for review. This tool can be run with the availability of any CDISC data, not waiting for late statistical analysis to report strange results and later investigations to identify data issues, making this application an important component of a good CDISC data creation process | outlier, call execute, type ii error, type i error, interquartile range, data cleaning, proc step, verbatim term, macro definition, macro call, data audit, proc sql, adverse events, cdisc | source | 12 |
| 122 | Let the CAT Catch a STYLE | Yanhong Liu, Justin Bates |
Being flexible and highlighting important details in your output is critical. The use of ODS ESCAPECHAR allows the SAS programmer to insert inline formatting functions into variable values through the DATA STEP, and it makes for a quick and easy way to highlight specific data values or modify the style of the table cells in your output. What is an easier and more efficient way to concatenate those inline formatting functions to the variable values? This paper shows how the CAT functions can simplify this task |
character functions, numeric variable, proc step | source | 11 |
| 123 | Let the CAT Out of the Bag: String Concatenation in SAS 9 | Joshua M. Horstman | Are you still using TRIM, LEFT, and vertical bar operators to concatenate strings? It's time to modernize and streamline that clumsy code by using the string concatenation functions introduced in SAS 9. This paper is an overview of the CAT, CATS, CATT, and CATX functions introduced in SAS 9.0, and the new CATQ function added in version 9.2. In addition to making your code more compact and readable, this family of functions also offers some new tricks for accomplishing previously cumbersome tasks | character functions, sas 9, catq, ifc, sas programmer | source | 6 |
| 124 | Linking Healthcare Claims and Electronic Health Records (EHR) for Patient Management - Diabetes Case Study | Paul A. LaBrec | Treo Solutions-now part of 3M Health Information System s-conducted a pilot project to assess the feasibility of linking healthcare administrative claims data to an electronic health record (EHR) data extract to enhance patient case management activities. We linked one year of healthcare claims data (2012) to the equivalent year of medical record data abstracted from the EHR system of a large Midwest commercial insurer. The claims database identified 328,897 adult patients receiving services during 2012. Over 35,000 of these patients (10%) had a diabetes diagnosis. The clinical data set included 272,193 records on 61,532 patients in 2012 and included over 50 data elements. Measures identified in the EHR database included physical measures (the most common records), health history, health behaviors, radiologic and endoscopic tests, select prescription data and laboratory values | insurance claims, proc sql, clinical data, clinical trial, proc step, proc freq, clinical database, interval variable | source | 17 |
| 125 | Ma, How Long Do I Cook The Turkey For? | David W. Franklin | In November it will be Thanksgiving and the cry will go out from the kitchen in some households "Ma, How Long Do I Cook The Turkey For?" This paper aims to give a lighthearted introduction to ODS RTF output using information of cooking times for that traditional of meats' at Thanksgiving, the turkey. Along the way there will be some turkey facts added in for little bit of light relief |
proc step, proc report | source | 9 |
| 126 | Macro Makes Final Documentation Quick and Easy | Indrani Sarkar, Jean Crain |
Purpose of this macro is to generate a document containing information on all the sas programs used to create derived datasets, summary, listings, and figures during a clinical trial project. This word document is used as a part of final package delivered to the client after completion of each project. Primary objective for this file is to assemble all the key information in one document so that it would be easier to replicate all the work in future without any difficulties and also it will help someone to get familiar with a project in a very short time. The macro, explained in this paper, will be able to list the sas program names; the analysis population(s); the endpoints; name(s) of required input datasets (including non-sas files); any additional SAS macros called by the program; the output file name(s); and any additional notes clarifying information. It would also be able to group tables, listings and figures based on their endpoints | in=, excel, macro definition, %if-%then-%else | source | 4 |
| 127 | Macro Programming via Parameter Look-Up Tables | Joseph W. Hinson | SAS Macros provide a unique means of creating one-size-fits-all programs and many large institutions rely on secure non-editable macros for generating standardized clinical reports. In such situations, programmers are shielded from the standard macros and are instead simply made to manipulate an external source of parameters in order to produce customized reports. This approach can further be extended by organizing report macros into domain-neutral classes based only on the structural layout of the reports, and another set based on analysis types, such that a call to a parameter look-up table would provide the appropriate combination of structural and analysis class macros pertinent to a particular report. With such an approach, just a dozen macro classes can rely on a large set of parameters in a look-up table to generate hundreds of different customized report across domains and therapeutic areas | macro variable, macro call, hash table, macro definition, excel | source | 9 |
| 128 | Macro to check Audit compliance and standards of SAS programs | Seeja Shetty | As a lead statistical programmer in clinical trial study you are responsible to submit an accurate representation of the collected data in the form of analysis datasets, summary tables, listing and figures. In addition, you need to ensure the SAS programs which created the above mentioned reports are compliant to Good Programming Practices. Even considering a small study it is tedious and time consuming to go through all the programs individually. This paper demonstrates a SAS macro to ensure basic checks for the GPP compliance which might divulge inconsistencies during study Audits | proc sort, dataset | source | 11 |
| 129 | MACUMBA - The log belongs to the program | Michael Weiss | MACUMBA is an in-house-developed application for SAS programming. It combines interactive development features of PC-SAS, the possibility of a client-server environment and unique state-of-the-art features. This presentation shows a feature of the MACUMBA application that aligns the generated log file to the SAS program, it belongs to. In this way all relevant log lines (ERROR's, WARNING's and others) are directly displayed at the source code line, they occurred. This alignment provides an easy way to find the source of a problem and ensures that no important log line is overlooked anymore | sas log, options statement, error message, merge statement, macro definition, data cleaning, by group processing | source | 8 |
| 130 | Managing bulk SAS job submissions with post execution analysis and notification | Bruce Kayton | Running all the programs in a study analysis with all their dependencies can be a time consuming or inefficient if done individually or sequentially. This paper outlines a methodology to use driving data to manage a job submission and monitoring process using defined dependencies. This enables programs to run efficiently in quick succession or often simultaneously to best utilize available resources. Upon the completion of all programs a submission summary is generated with run times and log analyses highlighting any warning or error issues. The submitter is notified via email about job completion with a hyperlink to the log analysis in spreadsheet format. Detailed line items contain links to submitted program logs along with hyperlinks to identified errors or warnings if applicable. Benefits: * Hands off submission, gives users the ability to focus on other tasks whilst programs run unattended in the background | sample, dataset | source | 5 |
| 131 | Managing the Organization of SAS Format and Macro Code Libraries in Complex Environments Including PC SAS, SAS Enterprise Guide, and UNIX SAS | Roger D. Muller Ph.D | The capabilities of SAS have been extended by the use of macros and custom formats. SAS macro code libraries and custom format libraries can be stored in various locations, some of which may or may not always be easily and efficiently accessed from other operating environments. Code can be in various states of development ranging from global organization-wide approved libraries to very elementary "just-getting-started" code. Formalized yet flexible file structures for storing code are needed. SAS user environments range from standalone systems such as PC SAS or SAS on a server/mainframe to much more complex installations using multiple platforms. Strictest attention must be paid to (1) file location for macros and formats and (2) management of the lack of cross-platform portability of formats. Macros are relatively easy to run from their native locations | user-defined format, format statement, macro definition, proc format, proc step, sas enterprise guide | source | 9 |
| 132 | Methodology for Non-Randomized Clinical Trials: Propensity Score Analysis | Dan Conroy | Randomized clinical trials serve as the gold standard for all research trials conducted within the pharmaceutical industry. When trials are not properly randomized, there is a potential for bias in all subsequent statistical analyses. When proper randomizations are not in place for a trial, methods exist that can help researchers draw valid conclusions. This paper summarizes and demonstrates some potential methods that can be used in this scenario. In particular, propensity score methodologies are presented and discussed with illustrative examples and SAS code. The examples and issues discussed herein were selected with the intent that researchers may find them informative, relevant, and applicable in a variety of scenarios, so that they may mimic and apply these methods in their own statistical analyses. The content is directed at users of SAS software with an intermediate understanding of standard statistical concepts and methodologies | propensity score, p-value, primary endpoint, randomization, logistic distribution, logistic regression, data science, nominal variable, clinical trial, sample size, regression analysis, sample, proc logistic, proc step | source | 5 |
| 133 | Modernizing Your Data Strategy: Understanding SAS Solutions for Data Integration, Data Quality, Data Governance, and Master Data Management | Gregory S. Barnes Nelson, Lisa Dodson |
For over three decades, SAS has provided capabilities for beating your data into submission. In June of 2000, SAS acquired a company called DataFlux to add data quality capabilities to its portfolio. Recently, SAS folded Data Flux into the mother ship and with SAS 9.4, the SAS Enterprise Data Integration (and baby brother Data Integration) solutions were upgraded into a series of new bundles that still include the former DataFlux products, but those products have grown. These new bundles include data management, data governance, data quality and master data management and come in advanced and standard packaging. This paper will explore these offerings and help you understand what this means to both new and existing customers of the Data Integration and DataFlux products. We will break down the marketing jargon and give you real world scenarios of what customers are using today (pre-SAS 9.4) and walk you through what that might look like in the SAS 9.4 world | data governance, master data management | source | 18 |
| 134 | Monitoring Quality, Time and Costs of Clinical Trial Programming Projects using SAS | Jagan Mohan Achi | Effective management of the Quality, Time and Costs (QTC) of programming activities entails a collective collaboration between statisticians and programming teams. In order to manage a portfolio of studies, there is always a necessity of having a close monitoring of the progress by the management. This ensures that the projects are delivered with a great control over QTC. To manage the projects, data is collected for tracking (programming trackers), operation (resource projections), finance (baseline costs and continuing costs) and quality (issues trackers). Project dashboards can be built with SAS GRAPH using the operational data with risk metrics built around the project progress. This paper will describe how SAS can help in monitoring project progress in a simple and yet, elegant way in order to keep your projects on track and have a better understanding of the implications of QTC on a real time basis | data cleaning, clinical trial | source | 4 |
| 135 | Moving to SAS Drug Development 4 | Magnus Mengelbier | Life Science organisations have a long investment into business processes, standards and conventions that make it difficult to simply turn to a new generation of analysis environments. SAS Drug Development 4 integrates many key features found in current analysis environments that are spread across several applications and systems, which require to be monitored and managed accordingly. The paper considers a set of SAS programs and how the SAS Drug Development repository, workspace and workflow features support a common innovative business process with all of the associated tools and utilities. The result is a short list of points to consider and some tricks for moving a business process from PC SAS or SAS server environments to the new release of SAS Drug Development | clinical research, macro variable, sas programming, macro put, audit trail, macro quoting function, life sciences | source | 17 |
| 136 | Napoleon Plot for PharmaSUG | Kriss Harris | Do you want to produce a very useful plot assessing treatment safety? Okay, do you want to produce a plot that for each subject shows the number of treatment cycles, the number of days on treatment, the doses that were received, whether the subject has discontinued treatment, and the cohort the subject is in? This paper will demonstrate how to do the above in SAS 9.4. Figure 1 above was created in GTL using the DISCRETEATTRMAP, DISCRETEATTRVAR, LAYOUT OVERLAY, BARCHARTPARM, SCATTERPLOT and DISCRETELEGEND statements. Figure 1 is created in four steps. Step 1 creates the stacked bar charts and the dose legend. Step 2 creates the square markers on the stacked bar chart that | bar chart, graph template language | source | 9 |
| 137 | Need for Speed in Large Datasets - The Trio of SAS INDICES, PROC SQL and WHERE CLAUSE is the Answer | Kunal Agnihotri | Programming on/with large datasets can often become a time consuming ordeal. One way to handle this type of situation is by using the powerful SAS INDEXES in conjunction with the WHERE clause in the PROC SQL step. This paper highlights how effective index es can be created using SQL (more flexible when compared to indexes created using DATA STEP index option or the DATASETS procedure) and further subset data using the WHERE clause which drastically reduces dataset processing and run time. This combination o f techniques gives better results when accessing big datasets than using the said techniques singularly. This paper also throws light on the dual functionality of the SQL created indexes, namely, the ability to create indexes on both new and existing SAS d ata sets |
proc sql, index, proc step, where statement, index creation, laboratory data, proc sort | source | 7 |
| 138 | Need to Review or Deliver Outputs on a Rolling Basis? Just Apply the Filter! | Tom Santopoli | Wouldn't it be nice if all of the outputs in a deliverable passed QC at exactly the same time and could be submitted for final review all at once, while leaving adequate time for the review to be completed prior to a deadline? Unfortunately, outputs often pass QC at different times and must be submitted for final review on a rolling basis in order to meet deadlines. The task of selecting 50 specific outputs to copy from a folder containing 500 outputs can be very tedious and cumbersome for a lead programmer. There are papers that explain how to copy files from one folder to another, but this paper addresses the issue of selectively copying specific files based on criteria set in a project tracking document. A simple macro called %MFILTER is presented to help make life a little easier for lead programmers as deadlines approach | macro variable, call execute, where statement, character functions | source | 6 |
| 139 | ODS EPUB: SAS Output at Hand | Erica Goodrich, Daniel Sturgeon |
A new addition to SAS 9.4 is the Output Delivery System (ODS) Electronic-Publications (EPUB) destination. ODS EPUB can be used to create SAS output files for various e-readers on both smart phones (e.g. Samsung Galaxy, Apple iPhone) and tablets (e.g. Apple iPad, and Amazon Kindle). In this paper we will be discussing how to create SAS output that can be taken with you on these devices and look at a few different procedures and customization options available to create e-publication files |
proc step, proc report | source | 7 |
| 140 | OpenCDISC Validator Implementation: A Complex Multiple Stakeholder Process | Terek J. Peterson, Gareth Adams |
The embracing of data standards by FDA following the vision of CDISC of reduced review time of drug applications opened the door for the creation of several tools to ensure conformance to standards. Tools like SAS PROC CDISC, WebSDM , and SAS Clinical Standards Toolkit help ed industry ensure compliance to the CDISC standards defined as SDTM, ADaM and define.xml. With the introduction of a free conformance engine OpenCDISC Validator, the possibilities of less confusion and more synergies across Sponsors, CROs and FDA was possible. However, the authors would argue the use of this tool has not achieved that goal and has created complex processes between stakeholders that include clinical, data management, programming, sponsor, and FDA; each group having different understanding of the conformance reports. Confounding any implementation are multiple versions OpenCDISC, SDTM, ADaM, and sometime contradicting FDA documentation |
controlled terminology, type i error, data governance, sdtm domain, data cleaning, proc step, cdisc controlled terminology, cdisc | source | 9 |
| 141 | Our Survival Confidence Intervals are not the Same! | David W. Franklin | "Our Survival Confidence Intervals are not the same!" This was a message I received from a client who was doing some checking of my statistics. After some research it was found that our results were "correct" insofar as the programming was correct but the internal calculations by the software was different. This paper looks into the calculation of the KaplanMeier estimate and compares the different methods of how the quartiles are calculated and the formulas for the confidence intervals they are not only different among different software but also among different versions of SAS. Along the way we shall see some of the options that affect the calculations and see how the defaults have changed in recent releases of SAS. There will also be a macro that calculates some options that SAS does not do in older versions | confidence interval, proc calis, life table, sample | source | 6 |
| 142 | Pharma Company Questions and Answers | Joseph J. Hantsch | We've all heard that pharmaceutical companies have two factions, a science directorate that doesn't care about sales and a sales directorate that doesn't understand the science, but there is a third group, the Slartibartfast team. But who are they? Are new hire statisticians any better equipped to deal clinical trials than new hire statistical programmers? Why is the CRA function the only one to avoid when considering dating within your company? What is the difference between project teams and product teams? How did CROs come about? Does anyone ever really adopt an orphan drug? What is so different about the medical writers? What is the difference between PK and PD? Why are the largest pharmaceutical companies in the world mostly US companies? Will MedDRA ever run out of numbers and revert to COSTAR? These and other mysteries of your average pharmaceutical company answered today | clinical trial, statistical programmer | source | 3 |
| 143 | Pick Me, Pick Me | Deloris Jones, Richard Harbin, Monique Gainey |
Currently we are experiencing an upswing in the market for hiring, particularly when it comes to programmers. Programming is one area where supply is lower than demand. The industry is not experiencing a recession in this field and while we are running into a fair amount of jobs that are being outsourced offshore the demand for qualified domestic candidates is higher than I have seen in the past five years | sas programming, clinical research | source | 4 |
| 144 | Practically Perfect Presentations | Cynthia L. Zender | PROC REPORT is a powerful reporting procedure, whose output can be "practically perfect" when you add ODS STYLE= overrides to your PROC REPORT code. This hands-on workshop will feature several PROC REPORT programs that produce default output for ODS HTML, RTF and PDF destinations. Workshop attendees will learn how to modify the defaults to change elements of PROC REPORT output, such as HEADER cells, DATA cells, SUMMARY cells and LINE output using ODS STYLE= overrides. In addition, attendees will learn how to apply conditional formatting at the column or cell level and at the row level using PROC FORMAT techniques and CALL DEFINE techniques. Other topics include: table attributes that control interior table lines and table borders, use of logos in output and producing "Page x of y" page numbering. The rest of this document is divided into two parts: the slides used in the Hands-On Workshop presentation and the attendee worksheet |
proc report, proc step | source | 40 |
| 145 | PRELOADFMT comes to your rescue, it brings missing categories to life in summary reports | Niraj J. Pandya, Ramalaxmareddy Kandimalla |
In clinical trails data analysis and reporting, one always comes across producing categorical tables used for analysis. Provided with lots of different kind of data types such as labs, adverse events, physical examination, concomitant therapies etc and multiple categories for several categorical variables, it becomes difficult sometimes to impute 0 values for categories which are missing altogether for a particular variable. SAS provides multiple options to handle such cases and produce output with all the categories even if some don't exist in the data. This paper concentrates on different work around methods and will discuss details of implementing each technique | proc step, proc report, proc means | source | 6 |
| 146 | Preserving Line Breaks When Exporting to Excel | Nelson Lee | Do you have imported data with line breaks and want to export the data to EXCEL? What if you need to preserve the line breaks in the data export? This paper shares a quick tip on how to export SAS data with line breaks to EXCEL through PROC TEMPLATE and TAGSET attributes. This paper was written for audiences with beginner skills; t he code was written using SAS Version 9.2 on Windows operating system |
excel, proc template | source | 5 |
| 147 | Principles of Writing Readable SQL | Kenneth W. Borowiak | PROC SQL is a commonly used data manipulation utility by SAS users. Despite its widespread use and logical components, there is no accepted standard fo r writing PROC SQL stat ements. The benefits of well-written code include ease of comprehension and code maintenance for both the original author and those who inherit it. This paper puts forth some principles of writing readable SQL in an objective manner. Each principle is followed by a suggested coding style. The ultimate goal is to elucidate the attributes of well-written PROC SQL code that users will implement to maximize comprehension by all |
proc sql, proc step, create table, macro variable, select, proc sort | source | 9 |
| 148 | Process and Tools for Assessing Compliance with Standard Operating Procedures | Ginger Redner, Eunice Ndungu |
In our efforts to develop drugs and vaccines that improve and save lives, we must maintain the integrity of patient data. This is accomplished by ensuring compliance with SOPs (Standard Operating Procedures) for developing and validating programs used to generate output for the Clinical Study Report (CSR) and submission deliverables. We have developed a suite of macros to help study teams ensure their deliverables are compliant with our SOPs. The main compliance macro identifies and reports specific areas of non-compliance. Another assesses the use of previously developed and fully validated standard macros. Using these macros greatly reduces the risk of error in reporting, decreases the number of SOP steps required by the project programmers to generate the deliverables, and increases efficiency by saving programming time. This paper discusses the macros and the process followed to ensure consistency and mitigate deviations | data cleaning, dataset, sample, independent qc, excel | source | 10 |
| 149 | Programming With CLASS: Keeping Your Options Open | Arthur L. Carpenter | Many SAS procedures utilize classification variables when they are processing the data. These variables control how the PROCEDURE FORMS groupings, summarizations, and analysis elements. For statistics procedures they are often used in the formation of the statistical model that is being analyzed. Classification variables may be explicitly specified with a CLASS statement, or they may be specified implicitly from their usage in the procedure. Because classification variables have such a heavy influence on the outcome of so many procedures, it is essential that the analyst have a good understanding of how classification variables are applied. Certainly there are a number of options (system and procedural) that affect how classification variables behave. While you may be aware of some of these options, a great many are new, and some of these new options and techniques are especially powerful. You really need to be open to learning how to program with CLASS |
proc step, missing value, proc freq, proc report, proc means, proc tabulate | source | 15 |
| 150 | QC made easy using macros | Prashanthi Selvakumar | To err is human. But this cannot be an excuse for our mistakes. We have to make sure there are no errors in the reports that we submit. To minimize errors in programming, we have the QC (Quality Check) team. In most cases, QC requires producing reports from the scratch, which is time consuming. In this paper we will be discussing a macro used for creating reports similar to the production programmer and that compares the result with QC programmer. This can help you save time on coding as well check the mistakes that human eyes do not capture | macro variable, character variable, proc sql, in=, quality control, proc step, clinical trial, crf, missing value, numeric variable | source | 7 |
| 151 | Quickly Organize Statistical Output for Review | Bradford J. Danner | Statisticians and programmers in the pharmaceutical industry are often required to include model based tables to satisfy the requirements of study protocols. Working for a client who does not explicitly require or expect the output created from SAS procedures as part of a submission has understandably created difficulty when reviewing such tables for accuracy. The programming team tends to focus on the end product with less thought as to checking the SAS procedural output. However, statisticians reviewing and approving the table will often require the statistical output to determine if the procedure was applied correctly. If prompted to produce the statistical output, a flood of information is typically consigned to a large text file, often with little or no organization which then impedes review | txt, ods pdf, repeated measures, least squares mean, confidence interval, proc mixed, clinical trial, sas output, proc step, data cleaning, regression analysis | source | 4 |
| 152 | Quotes within Quotes: When Single (') and Double (") Quotes are not Enough | Arthur L. Carpenter | Although it does not happen every day, it is not unusual to need to place a quoted string within another quoted string. Fort unately SAS recognizes both single and double quote marks and either can be used to within the other. This gives us the ability t o have two deep quoting. There are situations, however where two kinds of quotes are not enough. Sometimes we need a third layer o r more commonly we need to use a macro variable within the layers of quotes. Macro variables can be especially problematic as they will generally not resolve when they are inside single quotes. However this is SAS, and that implies that there are sev eral things going on at once and that there are several ways to solve these types of quoting problems. The primary goal of this paper is to assist the programmer with solutions to the quotes within quotes problem with special emphasis on the presence of macro variables | macro variable, filename statement, macro facility, &variable, macro quoting function, macro put, macro function | source | 6 |
| 153 | Recruiting for Retention | Kathy Greer, John Reilly |
Recruiting in the hopes of identifying and retaining highly qualified staff becomes more difficult each year. Since DataCeutics' is a Full Service Provider, our staff is placed in many highly visible positions throughout our clients. Following a process that eliminates applicants that cannot function independently and produce high level deliverables is critical. We follow a proven process to hire employees. The process includes determination of communication skills, following directions, abstract thinking, and understanding of clinical statistical programming by a verbal discussion and programming, and lastly a background check. The applicant speaks with at least three staff who determines the possibility of a fit within our company. This paper will go into detail on each step followed during the hiring process | dataset, clinical programming | source | 5 |
| 154 | Reducing Variable Lengths for Submission Dataset Size Reduction | Sandra VanPelt Nguyen | The FDA has cited dataset size as one of the issues they commonly encounter for submitted clinical trial datasets and has found the allotted column variable lengths to have a high correlation to overall dataset size. Based on this analysis, the reviewing divisions have requested sponsors to reduce variable lengths to the minimum lengths needed to accommodate the values found within each variable. Since it may be difficult to identify or predict up front the longest potential value for every variable, not to mention that sponsors will want to avoid risk of truncation, this paper presents a macro which identifies the minimal lengths needed based on the actual data values which are present in a dataset and reassigns variable lengths accordingly as a post-processing step prior to submitting datasets to a regulatory agency | length statement, character variable, proc compare, clinical trial, proc step, correlation | source | 6 |
| 155 | Referencing Medical Device Data in Standard SDTM domains | Timothy L Bullock, Ramkumar Krishnamurthy |
The seven new SDTM device domains capture the data describing patient exposure as well as all the details defining and identifying each device used in a medical device study. In order to provide continuity of device data across the entire SDTM model, some device-related data may also have to reside outside of the device domains. Examples of this are the AE domain which can contain information on device-related AEs and the PR domain which may need to accommodate a large amount of detailed information on device-related procedures such as implantation. We will discuss the integration of device data in the overall SDTM model and provide examples of methods for including device-related information in Findings domains outside of the device SDTM using the Findings About construct | adverse events, sdtm domain, sdtmig, cdisc | source | 7 |
| 156 | Reporting Healthcare Data: Understanding Rates and Adjustments | Gregory S. Barnes Nelson | In healthcare, we often express our analytics results as being "adjusted". For example, you may have read a study in which the authors reported the data as "age-adjusted" or "risk-adjusted." The concept of adjustment is widely used in program evaluation, comparing quality indicators across providers and systems, forecasting incidence rates and in cost-effectiveness research. In order to make reasonable comparisons across time, place or population, need to account for small sample sizes and case-mix variation - in other words - we need to level the playing field and account for differences in health status and accounts for uniqueness in a given population. If you are new to healthcare it may not be obvious what that really means to adjust the data in order to make comparisons. In this paper, we will explore the methods by which we control for potentially confounding variables in our data | health insurance, sample size | source | 22 |
| 157 | Risk-Based Approach to Identifying and Selecting Clinical Sites for Sponsor's Preparation for FDA/EMA Inspection | Xiangchen (Bob) Cui | In December 2012, the Center for Drug Evaluation and Research (CDER) issued a draft guidance relating to electronic submissions. Guidance for Industry: Providing Submissions in Electronic Format- Summary Level Clinical Site Data for CDER's Inspection Planning [1] [2] is one in a series of guidance documents intended to assist sponsors making certain regulatory submissions to FDA in electronic format. FDA's Office of Scientific Investigation (OSI) requests the sponsor to submit a clinical dataset that describes and summarizes the characteristics and outcomes of clinical investigation at the level of the individual study site within all NDAs, BLAs, or supplements that contain clinical data submitted to CDER. The OSI has developed and is piloting a risk-based inspection site selection tool to facilitate use of a risk-based approach for the timely identification of clinical investigator sites for on-site inspection by the CDER during the review of marketing applications | insurance risk score, adverse events, binary variable, primary endpoint, serious adverse event, treatment arm, effect size, change from baseline, clinical trial, treatment effect, likelihood function, proc rank | source | 21 |
| 158 | Risk-Based Monitoring of Clinical Trials Using JMP Clinical | Richard C. Zink, Kelci J. Miclaus |
Guidelines from the International Conference on Harmonisation suggest that clinical trial data should be actively monitored to ensure data quality. Traditional interpretation of this guidance has often led to 100% source data verification (SDV) of respective case report forms through onsite monitoring. Such monitoring activities can also identify deficiencies in site training and uncover fraudulent behavior. However, such extensive onsite review is time consuming, expensive, and as is true for any manual effort, limited in scope and prone to error. In contrast, risk- based monitoring makes use of central computerized review of clinical trial data and site metrics to determine if sites should receive more extensive quality review through on-site monitoring visits. We will demonstrate a risk-based monitoring solution within JMP Clinical to assess clinical trial data quality. Further, we'll describe a suite of tools used for identifying potentially fraudulent data at clinical sites | clinical trial, data cleaning, clinical data, outlier, adverse events, box plot, dataset, threshold, hierarchical clustering, vital signs, volcano plot, sample | source | 15 |
| 159 | Round Trip Ticket - Using the Define.xml file to Send and Receive your Study Specifications | Julie A. Maddox | Why can't you always get want you want? All you need to do is ask for it! Now that CDISC data standards have matured, why not provide your project leads and external partners with the exact study specifications you require all wrapped up in a single CRT-DDS define.xml file. Code lists, domains, variable, computational algorithms, and value- level metadata information are all captured in the CRT -DDS define.xml file. SAS Clinical Standards Toolkit 1.5 provides a variety of macros to extract this study information from the define file and produce domain templates, format catalogs and metadata tables ready to be populated. SAS Drug Development provides a secure, web- based interface to a SAS programming environment with access to the SAS Clinical Standards Toolkit as well as the full power of the SAS analytics procedures and reporting features | sample, clinical research, dataset, cdisc | source | 10 |
| 160 | Route to SDTM Implementation in In-Vitro Diagnostic Industry: Simple or Twisted | Carey G. Smoak, Sofia Shamas, Chowdagam Chaitanya, Don Lim, Girish Rajeev |
SDTM implementation for In-Vitro Diagnostic (IVD) data found a guiding light when CDISC came up with seven new domains specific to the medical device industry. Although these domains are not tailor -designed for diagnostic data, they serve as a good starting point for us to define SDTM+, which is an extension of the SDTM standards to accommodate the large variety of IVD data. The similarity across studies following SDTM domain structures presents opportunities for code standardization and reusability. What this paper hopes to achieve is to take the reader on our journey and explain briefly the company-specific standards created, the new domains and how our data was adjusted across SDTM+ domains. The main focus will be on mapping of IVD data with company specific use-case examples | sample, clinical trial, sdtm domain, excel, cdisc | source | 10 |
| 161 | Same Data, Separate MEANS - 'SORT' of Magic or Logic? | Naina Pandurangi, Seeja Shetty |
Sample Mean is the most fundamental element of any statistical analysis. It is also considered to be one of the simplest descriptive statistics with a straightforward formula i.e. sum of individual sample values divided by the number of values. Quite reasonably, one would expect to get a unique mean value for a given set of results irrespective of the order of the individual data points | sample, decimal, sas log, proc step, proc means | source | 8 |
| 162 | SAS as a Tool to Manage Growing SDTM+ Repository for Medical Device Studies | Julia Yang | When we have a substantial number of medical device studies in many different therapeutic areas, it is desirable to have a common data repository to facilitate clinical data management, analysis and reports. Modified Study Data Tabulation Model plus (SDTM+) becomes the infrastructure for our clinical data. SDTM+, with some adaptations, followed the SDTM and the SDTM for Medical Devices (SDTM-MD) by Clinical Data Interchange Standards Consortium (CDISC). There are many challenges associated with mapping multiple studies in many different therapeutic areas into one set of SDTM+ domains. These challenges include: 1) ensuring consistency across all studies; 2) incorporating new medical devices added periodically, quite possibly indefinitely; 3) making the SDTM+ database both scalable and stable; and 4) making sure the database is "self-explanatory" and source-traceable so new users do not need to refer to multiple documents. This paper summarizes what we learned so far | proc compare, raw data, excel, proc step, data cleaning, data governance, macro definition, date variable, sample, clinical data, macro call, data transformation, label statement, management reporting, regulatory submission, cdisc | source | 12 |
| 163 | SAS Can Automatically Provide GTL Templates for Graphics in Three Ways | David Shen, Ben Adeyi |
User-defined GTL templates are needed for the complicated statistical graphics which can not be obtained directly from the SG procedures. However, GTL is a relatively new language to many SAS users and it encompasses a large amount of syntax, statements and options. Actually there are three ways SAS can automatically provide the GTL templates. This presentation will show you how we may leverage this SAS feature to obtain the desired GTL templates, and then tailor these templates to create the customized statistical graphics, without writing GTL codes from scratch | proc sgplot, histogram, proc step | source | 8 |
| 164 | SCAN and FIND "CALL SCAN" | Usha Kumar | Let's explore the unexplored. Most of us are frequent users of SCAN and FIND/INDEX function. We use these when it comes to parsing a string. If we were to figure out the nth word from a character string, we would do so by using SCAN to solve this. If we are to figur e out the starting position of the nth word extracted, we would try and use INDEX/FIND for this purpose. What if we come up with a situation where we are to find out the position of the nth word that is repeated multiple times in a string? It get s more complicated. We have definitely come across this situation and solved it too. But let's find out if it is as easy as solving using the CALL SCAN routine available in SAS v9.1 and above | do loop, index | source | 4 |
| 165 | SDTM, ADaM and define.xml with OpenCDISC | Angela S. Ringelberg, Tracy Sherman |
As programmers, many of us have spent hours reviewing SDTM/ADaM standards and implementation guides to generate "compliant" CDISC SAS data sets. However, there is an easier way to ensure compliance with CDISC standards, including SDTM, ADaM, Define.xml, and others. OpenCDISC is an open source community which is focusing on creating frameworks and tools for the implementation and advancement of CDISC Standards. OpenCDISC has created a CDISC Validator which will eliminate the need for individuals to develop their own custom processes in order to ensure that their CDISC models are compliant with CDISC standards. By taking common validation rules, OpenCDISC has developed an open- source tool which is freely available and of commercial-quality to ensure data compliance with CDISC models such as SDTM, ADaM and Define.xml. The validation rules for each standard have been pooled into a CDISC Validation Rules Repository, providing users with a central listing | data cleaning, cdisc controlled terminology, error message, excel, data validation rules, cdisc | source | 21 |
| 166 | Self-fulfilling Macros Generating Macro Calls and Enabling Automation from a Specification | Y. Christina Song | In most cases, macros facilitate repetitive SAS programming iterations. In clinical data cleaning tasks, like edit check programming, each query item has different query logic. However, the overall query report generation process is somewhat repetitive; it all includes the process of reading, subsetting, formatting, and printing data. Even with all of the macros, programmers still have to read specifications carefully and create macro calls accordingly. The overall process is time-consuming and labor intensive. To improve programming efficiency, a procedure is introduced to let SAS macros generate macro calls from the specification sheet and to do all of the SAS programing. This program takes advantage of the data-driven and dynamic features of SAS macros and dynamically reads specifications, tweaks the data, generates all macro calls, codes the texts between the macros, formats the data, and outputs the data into desired reports | macro call, macro definition, data step, data validation rules, proc sql | source | 6 |
| 167 | Show Your SAS Off: Personal Branding and Your Online Portfolio | Barbara Ross | "Visibility creates opportunities." The word "online portfolio", for most people, bring s to mind collections of stunning photographs and graphic design; though utilization of this tool should not stop there. Any and all creative professionals can and should have an online portfolio. The ferocity a t which we present and attend these user groups attests to the fact that portfolios would flourish within our line of work. Are white papers not but showcases of our creative programming solutions? Ho w many of us keep copies of our best coding snidbits tucked away in a file on the computer? Wou ld it not serve us best to showcase these to our peers? After all visibility creates opportunities. Opportunities that include new job leads, collaborations, mentorship, and self-learning. Also it's simple. In today's day and age, sites such as Weebly and Wordpress can have you published within an hour- all you need is content and a little inspiration | proc step, pii | source | 9 |
| 168 | So You're Still Not Using PROC REPORT. Why Not? | Ray Pass, Daphne E. Ewing |
Everyone who can spell SAS knows how to use PROC PRINT. Its primary use may be as a development tool to help in debugging a long multi-step program, or as a simple report generator when all that is really needed is a quick look at the data, or even a basic low-level finished report. However, if a report generation/information delivery tool with powerful formatting, summarizing and analysis features is called for, then PROC REPORT is the solution. PROC REPORT can provide the standard PROC PRINT functionality, but in addition, can easily perform many of the tasks that you would otherwise have to use the SORT, MEANS, FREQ and TABULATE procedures to accomplish. PROC REPORT is part of the Base SAS product, can run in both an interactive screen-painting mode or a batch mode, and should be the basic tool of choice when there is a need to produce powerful and productive reports from SAS data sets |
proc report, proc step, class variable, character variable, proc print, proc means, proc tabulate | source | 14 |
| 169 | Standardization of Confidence Intervals in PFS Tables - a Macro Approach | John Saida Shaik, Boxun Zhang |
Any oncology trial requires time-to-event (TTE) analysis to determine whether an event of interest (EOI) occurred and when it occurred. An EOI can be progression of disease, stable disease, complete remission or death. Usually overall survival (OS) and/or progression-free survival (PFS) tables are requested by statisticians to perform TTE analyses. In this paper, we propose a macro that uses the P roc LIFETEST procedure to automate generation of PFS tables and standardize calculation of confidence intervals (CI), in addition to a plethora of other parameters. Usage of PROC LIFETEST to generate PFS tables results in consistency. This macro makes calculation of CI much more straight - forward and a standardized process |
overall survival, sample, confidence interval, survival analysis, out=, progression-free survival, proc step | source | 4 |
| 170 | Strategies and Techniques for Debugging SAS Program Errors and Warnings | Kirk Paul Lafler | As a SAS user, you've probably experienced first-hand more than your share of program code bugs, and realize that debugging SAS program errors and warnings can, at times, be a daunting task. This paper and presentation explores the world of SAS errors and warnings, provides important information about syntax errors, input and output data sources, system-related default specifications, and logic scenarios specified in program code. Attendees will learn how to apply effective techniques to understand, fix, and resolve errors and warnings, allowing program code to work as intended | sas log, options statement, data cleaning, hash table, proc step, mprint | source | 13 |
| 171 | Strategies and Techniques for Getting the Most Out of Your Antivirus Software for SAS Users | Ryan Paul Lafler, Kirk Paul Lafler |
Malware, sometimes referred to as malicious software, represent software threats engineered to damage computer systems without the knowledge of the owner using the system. SAS users are incr easingly becoming more prone to malware attacks and need to have strategies and a set of guidelines to help them get the most out of their antivirus software. This presentation highlights the many different types of computer threats, classification approaches, detection strategies, and removal methods. Attendees learn what malware is; the types of malware including viruses, Trojans, rootkits, zombies, worms, spyware, adware, scareware, spam email, and denial of service (DOS) attacks; password protection and management strategies; software to detect and protect computer systems; techniques for the removal of malicious software; and strategies and techniques for protecting your computer and data assets | source | 8 | |
| 172 | Streamline the Dual Antiplatelet Therapy Record Processing in SAS by Using Concept of Queue and Run-Length Encoding | Kai Koo | Dual antiplatelet therapy (DAPT) is a common practice to pr otect patients from stent thrombosis after stent implantation. In order to analyze its efficiency, medication records of two antiplatelet drugs have to be compiled together. To reduce the coding complexity, the concept of q ueue is used in SAS DATA STEP s |
sample, proc sort, proc step, macro definition | source | 6 |
| 173 | Survey of Population Risk Management Applications Using SAS | Jack N. Shoemaker | The business of health insurance has always been to manage medical costs so that they don't exceed premium revenue. The PPACA legislation which is now in full force amplifies this basic business driver by imposing MLR thresholds and establishing other risk-bearing entities like ACOs and BPCI conveners. Monitoring and knowing about these patient populations will mean the difference between success and financial ruin. SAS software provides several mechanisms for monitoring risk management including OLAP cubes, third-party solutions, and Visual Analytics. This paper surveys these SAS solutions in the context of the population risk management problems now part of the healthcare landscape | proc step, macro variable | source | 7 |
| 174 | Survival 101 - Just Learning to Survive | Leanne Goldstein, Rebecca Ottesen |
Analysis of time to event data is common in biostatistics and epidemiology but can be extended to a variety of settings such as engineering, economics and even sociology. While the statistical methodology behind time to event analysis can be quite complex and difficult to understand, the basic survival analysis is fairly easy to conduct and interpret. This workshop is designed to provide an introduction to time to event analyses, survival analysis and assumptions, appropriate graphics, building multivariable models, and dealing with time dependent covariates. The emphasis will be on applied survival analysis for beginners in the health sciences setting | proc step, kaplan-meier plot, hazard ratio, proc phreg, survival analysis, proportional hazards assumption, binary variable, rank test, log-rank test, time-dependent covariate, nominal variable, interval variable, stepwise selection, maximum likelihood estimation, confidence interval, proc calis, likelihood function, regression analysis | source | 19 |
| 175 | Survival Analysis Approaches and New Developments using SAS | Jane Lu, David Shen |
A common feature of survival data is the presence of censoring and non-normality. It is inappropriate to analyze survival data by the conventional statistical methods such as linear regression or logistic regression, because of the characteristics of the survival data. When censoring, survival time can't be considered as a continuous variable. Linear regression, in which to compare mean time-to-event between groups, cannot deal with the influence from censored data correctly. Logistic method compares proportion of events between groups using odds ratio, but the differences in the timing of event occurrence are not considered. With unequal survival times, analyzing the probability of survival as a dichotomous variable by Chi-square test would fail to account for this non-comparability between subjects. This paper provides an overview of survival analysis and describes its principle and applications | survival analysis, regression analysis, hazard function, proc step, rank test, hazard ratio, log-rank test, likelihood function, bayesian statistics, survival function, proc phreg, null hypothesis, proportional hazards assumption, censoring, predictor variable, proc quantreg, time-dependent covariate, wilcoxon test, proc reg, proc calis, sample, interval variable, time variable, univariate analysis, dataset, logistic distribution, exponential distribution, posterior probability, correlation, longitudinal data, proc quantlife, probability distribution, clinical trial, proc lifereg, response variable | source | 13 |
| 176 | Swimmer Plot: Tell a Graphical Story of Your Time to Response Data Using PROC SGPLOT | Stacey D. Phillips | ODS Statistical Graphics (SG) procedures are making complex and sophisticated graphics easier to create with every new release of SAS. Through the use of color, line-types, symbols and annotations we can tell a complicated graphical story of our data in one glance. This paper will demonstrate how to create a swimmer plot using PROC SGPLOT that shows multiple pieces of tumor response information for individual subjects in an oncology study. Specifically, the swimmer plot will show total time to tumor response, whether the response was complete or partial, when the response started/ended, censoring information and the current disease stage of the subject. The paper will demonstrate the step-by-step process of creating a swimmer plot from basic PROC SGPLOT statements through more complex annotations using SAS version 9.3. There will also be some discussion on generating similar plots using SAS version 9.2 as well as Graph Template Language (GTL) |
swimmer plot, proc sgplot, time to response, proc step, sg annotation, graph template language, scatter plot, complete response, response variable, retain | source | 12 |
| 177 | Switching from PC SAS to SAS Enterprise Guide | Zhengxin (Cindy) Yang | As more and more organizations adapt to the SAS Enterprise Guide, switching smoothly from PC SAS to SAS Enterprise Guide and reducing the learning curve becomes remarkably important. The tips from work experiences can help maintaining productivity efficiency and revealing the powerful capabilities of SAS Enterprise Guide during this transition. This paper presents tips from firsthand experiences of using SAS Enterprise Guide. Setting up a working environment by choosing preferred options in the tool manual is a great start for programming. Using work space layout, the 'send to' option and other devices to utilize MS applications as additional tools can improve work efficiency. Grouping programs as projects will facilitate to work with multiple programs and even multiple projects at the same time | sas enterprise guide, sas programmer, excel, pharmaceutical industry, statistical programmer | source | 13 |
| 178 | Table Lookup Techniques: From the Basics to the Innovative | Arthur L. Carpenter | One of the more commonly needed operations within SAS programming is to determine the value of one variable based on the value of another. A series of techniques and tools have evolved over the years to make the matching of these values go faster, smoother, and easier. A majority of these techniques requir e operations such as sorting, searching, and comparing. As it turns out, these types of techniques are some of the more computationally intensive, and consequently an understanding of the operations involved and a careful selection of the specific technique can often save the user a substantial amount of computing resources. Many of the more advanced techniques can require substantially fewer resources. It is incumbent on the user to have a broad understanding of the issues involved and a more detailed understanding of the solutions available | set statement, hash table, by group processing, merge statement, lookup, proc step, proc sql, data merging, proc format, key=, select, if-then-else, length statement, proc sort, index, dataset, key, conditional do loop | source | 11 |
| 179 | Techniques for managing (large!) batches of statistical output | Brian P. Fairfield-Carter, Tracy Sherman |
When delivering batches of statistical output to a client, some fairly basic conditions need to be met: output must be current (generated without error from current analysis data), validation status must be current, and the collection of output must comprise what the client is expecting to receive (no missing files or extra files). While these conditions are fairly easy to enforce with small batches of output, they can be surprisingly difficult to meet with larger batches: consider for instance the practicality of checking that each of 350 entries in a programming plan has a corresponding output file (or conversely that each file has a corresponding entry). Techniques for managing a small delivery tend to be inadequate for large deliveries, and as the size and complexity of the delivery increases, the need for automation in meeting/confirming these conditions also increases | ods rtf, macro variable, excel | source | 20 |
| 180 | Techniques of Preparing Datasets for Visualizing Clinical Adverse Events | Amos Shu, Qinghua (Kathy) Chen |
With the introduction of SAS Graph Template Language and SAS/GRAPH SG Procedures, there have been papers [1-4] that have provided very useful codes to easily visualize clinical adverse events (AE). However, it is still not easy to create the suitable datasets that are used to generate the right graphs. This paper discusses techniques of preparing datasets that will be used to generate different types of figures for clinical adverse event |
adverse events, hazard function, scatter plot, graph template language, study day, proc template, kaplan-meier plot | source | 8 |
| 181 | That SASsy Lab Data | Amie Bissonett | Working with laboratory data can be a daunting task. Data can come from central labs, local labs, or both on the same study. Receiving lab data from different labs can result in values within a lab test to have differing units and normal ranges, which need to be reconciled prior to analyzing and displaying results so that values are accurate and consistent. CDISC standards bring additional issues to the table that need to be considered while programming the SDTM and ADaM data sets. This paper displays some data issues to look for and how to handle them, as well as how to handle programming issues for SDTM, ADaM, and CTCAE grading | laboratory data, macro variable, proc sql, proc step, ctcae grade, raw data, outlier, adverse events, proc freq, cdisc | source | 6 |
| 182 | The Association of Morbid Obesity with Mortality and Coronary Revascularization among Patients with Acute Myocardial Infarction | Ashwini S Erande, Shaista Malik |
The aim of this study was to investigate the impact of morbid obesity (body Mass index >= 40 kg/m2) on in -hospital mortality and coronary revascularization outcomes in patients presenting with acute myo cardial infarctions (AMI).The Nationwide Inpatient Sample of the Healthcare Cost and Utilization Project was used, and 413,673 Patients hospitalized with AMIs in 2009 were reviewed. Morbidly obese patients constituted 3.7% of all patients with AMIs. All the analyses were performed in SAS 9.3. ARRAY Statements were used to create the morbid obesity variable based on the ICD9 codes from 2 4 "Diagnosis" data elements. The SAS procedures PROC SURVEYFREQ and PROC SURVEYLOGISTIC were used to perform bivariate and multivariate analyses on this sample survey database |
proc step, proc surveyfreq, proc surveylogistic, sample, odds ratio, nominal variable, multivariate analysis, p-value, predictor variable, regression analysis, response variable, do loop, proc freq, null hypothesis, likelihood function, array, bivariate analysis, binary variable | source | 11 |
| 183 | The New Tradition: SAS Clinical Data Integration | Vincent J. Amoruccio, Janet E. Stuelpner |
Base SAS programming has been around for a very long time. And over that time, there have been many changes. New and enhanced procedures, new features, new functions and even operating systems have been added. Over time, there have been many windows and w izards that help to more easily generate code that can be used in programs. Through it all, programmers always come back to their SAS roots, the basic programs with which they started. But, as we move into the future, is this the best use of time, to sit and manually code everything? Or can we take advantage of the new tools and solutions that generate code and use metadata to describe data, validate output and document exactly what the programmer has done. This paper will show you how we can change the c urrent process using the graphical user interface of SAS Clinical Data Integration to integrate data from disparate data sources and transform that data into industry standards in a methodical, repeatable, more automated fashion | sas base, proc step, sample, clinical data, clinical trial, sas programming, data integration, sdtm domain, proc sql, dataset, pharmaceutical industry, excel, adam dataset, macro variable, data cleaning, macro definition, cdisc | source | 18 |
| 184 | The path less trodden - PROC FREQ for ODDS RATIO | Manjusha Gondil, Linga Reddy Baddam |
In our clinical industry we conduct various types of simple/complex statistical analysis for data interpretation and Odds Ratio is one such extremely useful and simple to understand technique. Odds Ratio is used for making the critical decision about which treatment is benefiting the trial subjects in a clinical trial. In statistics, the odds of an event occurring is the probability of the event divided by the probability of an even t not occurring. Historically we calculate odds ratio using complex stats procedure like PROC LOGISTICS, PROC GENMOD etc. , but this paper gives us an idea about easier alternative of how to find odds ratio using simpler stats procedures like |
odds ratio, proc step, proc freq, confidence interval, proc logistic, logistic distribution, proc genmod | source | 4 |
| 185 | The SAS LOCALE Option: Win an international passport for your SAS code | Xiaojin Qin | Want to win an international passport for a round-the-world journey? Start with your SAS code! SAS internationalization is the step that generalizes your project to be language independent. This allows you to write code once, and then have it run in different cultural environments with the appropriate cultural interpretation; for example, write your code so it uses formats that are familiar to you in China, yet when your French clients run the code it will use formats familiar to them. LOCALE, one of the internationalization features of SAS, can help your code be a world traveler. This paper will show the use of LOCALE in our SAS sessions as a major part of making the round-the-world journey a reality. You will see how a minor change can make a major difference | proc step, options statement, proc sort | source | 8 |
| 186 | The Three I's of SAS Log Messages, IMPORTANT, INTERESTING, and IRRELEVANT | William E. Benjamin Jr. | I like to think that SAS error messages come in three flavors, IMPORTANT, INTERESTING, and IRRELEVANT. SAS calls its messages NOTES, WARNINGS, and ERRORS. I intend to show you that not all NOTES are IRRELEVANT nor are all ERRORS IMPORTANT. This paper will walk through many different scenarios and explain in detail the meaning and impact of messages presented in the SAS log. I will show you how to locate, classify, analyze, and resolve many different SAS message types. And for those brave enough I will go on to teach you how to both generate and suppress messages sent to the SAS log. This paper presents an overview of messages that can often be found in a SAS Log window or output file. The intent of this presentation is to familiarize you with common messages, the meaning of the messages, and how to determine the best way to react to the messages. Notice I said "react", not necessarily correct. Code examples and log output will be presented to aid in the explanations | cpu time, sas log, error message, libname statement, dataset, options statement, data step, error, proc step, proc printto, sas function, macro variable | source | 20 |
| 187 | Times Can Be Tough: Taming DATE, TIME and DATETIME Variables | Sajeet Pavate | Some programmers may not fully understand how the values for Date, Time and DATETIME variables are stored and manipulated within SAS especially in relation with each other. Several previous papers have provided an introduction to how date, time and DATETIME values work in SAS as well as the different functions and formats that apply to these variables. The aim of this paper is to show common issues that may occur while working with these variables. These issues, for example, occur when missing time component is not considered or when incorrect assumptions are made that can result in invalid or inaccurate calculations. The paper points to some of these issues with examples from real life scenarios and includes the corrected code to fix such issues. It attempts to educate readers on how these variables are used within SAS and makes them aware and mindful of common pitfalls when working with Date, Time and DATETIME variables |
sample, datetime variable, missing value, date variable, time variable, sas log, note, imputation | source | 6 |
| 188 | Tips for Creating SAS-Based Applications for Oracle Clinical | Kunal Agnihotri, Kenneth W. Borowiak |
Oracle Clinical (OC) is database management system used to support clinical trials processes. There is an enormous amount of data and metadata stored in OC beyond the data points collected on a case report form, which can be used as the basis for developin g applications to support a variety of activities. This paper offers some tips for creating SAS macros and standard programs against OC. Topics include using PROC SQL Pass -Through facility, resolving macro variables, handling of dates, and regular expression support. Some useful queries against OC are used to demonstrate each topic |
proc sql, macro variable, sql pass-through, proc step, clinical trial, libname engine, data cleaning, macro quoting function | source | 6 |
| 189 | Tips for Finding Your Bugs Before QC Does | Beatriz Garcia | Statistical Programmers often have to work as both programmers and in validation or verification of programs during the course of a project. Sometimes after we deliver the program for validation, many requests are received in order to change the results or update the code. Why does that happen? Maybe because we have not checked the results as carefully as we should. In this paper, if you work in UNIX environment, I want to show you some tips for reviewing your results before delivering to QC, so you can prevent many of those requests, avoid re-work and save time | proc step, data cleaning, proc contents, proc freq | source | 6 |
| 190 | Tips to Manipulate the Partial Dates | Deli Wang, Chunxia Lin |
A partial date is simply any date where the date is incomplete, but not wholly missing. More commonly in clinical trials, the day and/or month are missing. In these cases, SAS programmers may be asked to impute a reasonable date or time per client's requirement or statistical purpose. This paper introduces two different imputation logics with the missing day set to the last day of the month. Both methods take the leap years into consideration, and generate same results. However, one method imputes the day depending on the leap year and month, while another not considering any | datepart, imputation, sas programmer, clinical trial | source | 4 |
| 191 | TLF Validation Etiquette:What to Say, When to Say, How to Say, Why to Say | Karen Walker | Peer review is the gold standard by where quality is achieved. It has been used to publish scientific journals for centuries. On the internet we see the effects of peer review every day. The peer review process has been mimicked in reality television shows that judge singers, d ancers, and even for selecting a spouse. In this paper are the rules by where quality peer review can be done with success and bring forth further insights for SAS programs. Quality is achieved by using a checklist, cooperation, and support. Inherent within this process is the contrast of disparate ideas. That's the beauty of it. Flowing from those disparate ideas; contrast and compared, is proof that one idea is the best suited. Persons involved in this process must agree that the overall quest to discover the best is a collaboration effort. They have to be open to equally capable expertise among one and other, and truly share ideas. Those involved remain free of insult, "bullyisum" and "come up isum" | data cleaning, proc step, adverse events, proc compare, adam dataset, proc sql, proc freq, cdisc | source | 10 |
| 192 | Understanding and Applying the Logic of the DOW-Loop | Arthur X. Li | The DOW-loop is not official terminology that one can find in SAS documentation, but it was well-known and widely-used among experienced SAS programmers. The DOW-loop was developed over a decade ago by a few SAS gurus, including Don Henderson, Paul Dorfman, and Ian Whitlock. A common construction of the DOW-loop consists of a DO-UNTIL loop with a SET and a BY statement within the loop. This construction isolates actions that are performed before and after the loop from the action within the loop which results in eliminating the need for retaining or resetting the newly-created variables to missing in the DATA STEP. In this talk, in addition to understanding the DOW-loop construction, we will review how to apply the DOW-loop to various applications. B |
missing value, do loop, set statement, conditional do loop, retain, group by, if-then-else | source | 12 |
| 193 | Up Your Game with Graph Template Language Layouts | Sanjay N. Matange | You have built the simple bar chart and mastered the art of layering multiple plot statements to create complex graphs like the survival plot using the SGPLOT procedure. You know all about how to use plot statements creatively to get what you need and how to customize the axes to achieve the look and feel you want. Now it's time to up your game and step into the realm of the "Graphics Wizard." Behold the magical powers of Graph Template Language layouts! Here you will learn the esoteric art of creating complex multi-cell graphs using LAYOUT LATTICE. This is the incantation that gives you the power to build complex, multi-cell graphs like the forest plot, stock plots with multiple indicators like MACD and Stochastic, Adverse Events by Relative Risk graphs, and more. If you ever wondered how the Diagnostics panel in the REG procedure was built, this paper is for you. Be warned, this is not the realm for the faint of heart! |
kaplan-meier plot, proc sgplot, scatter plot, class variable, forest plot, adverse events, histogram, bar chart, graph template language, box plot, relative risk | source | 20 |
| 194 | Update: Development of White Papers and Standard Scripts for Analysis and Programming | Nancy Brucken, Michael Carniello, Mary Nilsson, Hanming Tu |
A PhUSE Computational Science Symposium (CSS) Working Group is creating white papers outlining safety, demographics, disposition and medications analysis and reporting for clinical trials and regulatory submissions. An online platform for sharing code has also been created, making these standards easy to implement. This paper provides an update as of April 2014 on the progress made in these efforts | phase ii, clinical trial | source | 3 |
| 195 | Using SAS to Calculate and Compare Adjusted Relative Risks, Odds Ratios, and Hazard Ratios | Besa Smith, Tyler C. Smith |
In the past decade, health outcomes research has gained in popularity as increasing focus has been given to improving patient outcomes. Whether upon refining screening strategies for earlier detection of disease, reducing readmission or nosocomial infection rates, improving patient satisfaction, or evaluating new patient therapies and treatments, the underlying focus is to improve prevention, control, and/or treatment. The analysis of the occurrence of health outcome events is dependent upon differing risk sets among those with and without the event of interest and is often modeled using one of three approaches. Using regression methods, we often see relative risk estimates, odds ratios, or hazards ratios presented after adjusting for a list of covariates that may be distorting our view. This paper will use SAS to compare the process and results of a log-binomial regression, logistic regression, and Cox regression in the context of several covariates and including a temporal element | proc step, regression analysis, odds ratio, relative risk, logistic distribution, hazard function, likelihood function, response variable, confidence interval, hazard ratio, logistic regression, proc genmod, proc logistic, predictor variable, binomial distribution, null hypothesis, estimate, degrees of freedom, proportional hazards assumption, proc reg, proc phreg, follow-up period, left censoring, right censoring, survival function, proc freq, poisson distribution, probability distribution, maximum likelihood estimation | source | 23 |
| 196 | Using the Power of SAS SQL | Jessica Wang | SAS is a flexible language in that the same task can be accomplished in numerous ways. SAS SQL is a powerful tool for data manipulation and query. SAS SQL can make your programs more efficient, simpler and more readable. Topics in the paper will cover: merging multiple tables by different columns and different rules; SQL in-line view; SQL set operation; using dictionary tables; creating empty tables with pre-defined dataset structure; inserting rows into a dataset; assigning a list of macro variables. Some tricks and tips from the author's personal experience as a SAS user will also be shared: e.g. using COMPRESS to save storage size; using SQL options _METHOD to understand your SQL code better; using NOPRINT to compress unnecessary display in output window. This paper is intended for intermediate to advanced SAS SQL users who already know the basics of SAS/SQL, and want to better exploit the power that SQL offers |
proc sql, macro variable, proc step, create table, automatic macro variable, macro put, sas output, cpu time, dictionary tables, randomization, data merging | source | 14 |
| 197 | Using the SAS System as a bioinformatics tool: A macro that translates BLASTn results to populate a DNA sequence database table | Kevin R. Viel | Using the Basic Local Alignment Search Tool (BLAST) to align DNA sequences to a known reference sequence is a common task in genomics research. The results of the BLASTn (nucleotide) alignment can be translated into a database table of a relational database of a sequencing project. Appropriately annotating the reference sequences increases the utility of the resulting table. The National Center for Biotechnology Information (NCBI) of National Institutes of Health (NIH) provides the standalone blast+ software package, which enables a SAS programmer to easily submit batches of query sequences. The goals of this paper are to describe a SAS macro that uses the results of BLASTn alignments and Phred data to populate a table and to discuss some issues encountered in a sequencing project that generated data on over 60 million nucleotides | macro parameter, dataset, data step, macro variable, macro definition, proc sql | source | 20 |
| 198 | Validating Analysis Data Set without Double Programming - An Alternative Way to Validate the Analysis Data Set | Linfeng Xu, Christina Scienski |
This paper will demonstrate an alternative way to validate the analysis data set without double programming. The common practice for the most critical level validation of an analysis data set in pharmaceutical industry is double programming, that is, the source programmer generates an analysis data set (i.e. production data set) and another programmer (Reviewer) uses same specifications to create a QC data set. Reviewer then conducts PROC COMPARE to see whether or not there is any discrepancy between the two data sets. This paper will introduce the ALTVAL macro as an alternative to double programming in validating an analysis data set. The ALTVAL macro consists of two parts: 1) compare common variables between raw and analysis data set and use PROC COMPARE to check for discrepancies |
proc step, data cleaning, independent qc, proc freq, proc compare, raw data, date variable, macro call, macro parameter | source | 15 |
| 199 | Want to Conquer the Fear of Annotation? Start Using the NOTE Statement | Madhuri Aswale | The capabilities of #BYVAL in plotting graphs are exceptional for graph ical display and can be made even more efficient and effective whe n used with the NOTE statement, Unlike TITLE and FOOTNOTE, NOTE is not frequently used in SAS code for creating and modifying graphs. The use of both NOTE and #BYVAL cohesively allows the programmer to write better code and to embellish graphs with essential information. The purpose of t his paper is to explore the effective use of th e NOTE statement to add text to maps, plots, charts, and text slides, resulting in better control of content, appearance, and placement of the text, including color, size, font, and alignment, in addition to allowing for underline and box drawing around text and straight lines on the output | log-rank test, by group processing | source | 5 |
| 200 | Was Dorothy Right: Is There No Place Like Home? | Kjersten Offenbecker | Many companies within the pharmaceutical industry have adopted the practice of allowing their SAS programming staff to work from home either part-time or full-time. To many programmers this trend offers several benefits including reduced travel time, less disruption in family life, improved work -life balance and more flexible hours. For management and the company as a whole the benefits include cost savings, increased productivity, improved employee motivation, employee retention and improved employee satisfaction. But there are challenges to working from home for both the employee and the company including loss of focus, poor working environment as well as loss of connection and/or collaboration with other team members. This paper will explore the pros and cons of working from home from the perspective of someone who works from home full -time and successfully manages employees who work both as telecommuters and participate in more traditional working situations | clinical research, pharmaceutical industry | source | 6 |
| 201 | What do you mean 0.3 doesn-t equal 0.3? Numeric Representation and Precision in SAS and Why it Matters | Paul Stutzman | The manner in which numeric values are stored in data sets or memory can cause SAS programs to produce seemingly surprising results if that manner is not well understood. Numeric representation and precision describes how these values are stored. This paper shows how numeric representation and precision can affect program output and produce unintended results. It shows how numbers are actually represented, it identifies the magnitude of the difference between how values are represented and their absolute values, and it provides solutions to the problems that numeric representation and precision can introduce | proc step, proc print, numeric functions, numeric variable, decimal, proc compare, where statement, proc report | source | 6 |
| 202 | What is the Definition of Global On-Demand Reporting within the Pharmaceutical Industry? | Eric Kammer | It is not uncommon in the pharmaceutical industry to have standardized reporting for data management cleaning activities or clinical review. However, certain steps have to be taken into consideration when programming standardized reports, so they run properly for all studies. One particular troublesome area is when the global reports are run on-demand by non-programmers. As new data becomes available, original test cases that were used could be different, and the programs could fail. This paper will identify techniques to assist programmers on what to do when developing code, so programs can run successfully when unexpected surprises with data occur running SAS reports in an on-demand environment and give the customers information to assist in understanding the results | error message, pharmaceutical industry | source | 8 |
| 203 | What's Hot, What's Not - Skills for SAS Professionals | Kirk Paul Lafler, Charles E. Shipp |
As a new generation of SAS user emerges, current and prior generations of users have an extensive array of procedures, programming tools, approaches and techniques to choose from. This presentation identifies and explores the areas that are hot and not-so-hot in the world of the professional SAS user. Topics include Enterprise Guide, PROC SQL, PROC REPORT, PROC FORMAT, Macro Language, ODS, DATA STEP programming techniques such as arrays and hashing, business intelligence, sasCommunity.org, JMP, SAS/GRAPH, SAS/STAT, and SAS/AF |
sas 9, sas base, proc step | source | 6 |
| 204 | WHERE, Oh, WHERE Art Thou? A Cautionary Tale for Using WHERE Statements and WHERE= Options | Britney D. Gilbert | Using WHERE statements in your SAS programming can make processing data more efficient. However, the programmer needs to have a full understanding and be aware of how SAS processes multiple WHERE statements or combinations of WHERE statements and WHERE= dataset options in DATA steps and PROCEDURES. This paper explores examples of the combinations of WHERE statements and WHERE= dataset options in both DATA steps and PROCEDURES and the resulting logs and output | where statement, full analysis set, analysis set, proc sort, sample, if-then-else, proc step | source | 4 |
| 205 | XML in a SAS and Pharma World | Mike Molter | The introduction of standards to the clinical data life cycle has brought about significant changes to the job of a SAS programmer. Traditionally, SAS programmers who built data sets and statistical output for regulatory submission purposes had little need for technical knowledge beyond SAS programming and maybe some Microsoft or Adobe basics. In today's world, collected data can be made available in an XML format produced by EDC systems (i.e. ODM.xml). Submissions are expected to be accompanied by metadata expressed through an XML extension of ODM (i.e. Define.xml). There's even talk of replacing the traditional version 5 transport files with another XML extension of ODM (i.e. SDS-XML) for submission of domain data. The increased use of XML for transferring data and metadata has its advantages, but also imposes new requirements of a programmer's skill set. This paper serves as an introduction to some of these new skills | libname statement, proc step, sas programmer, where statement, controlled terminology, proc print, clinical data, libname engine, dataset, excel, proc copy, adverse events, cdisc | source | 19 |
This site serves as a convenient hosting location and does not work as a publisher. All copyrights belong to their respective owners.
The information on this site is provided for general reference purposes only. Whilst every effort is made to ensure that the site is up to date and accurate, no warrant, nor any responsibility or liability for, the accuracy or completeness of the content or for any loss which may arise from reliance on information contained in this site is provided. Links to other sites are provided for your convenience but no responsibility or liability for the content of those sites or of any external site which links to this site is accepted. References to any specific commercial product, process, service, or corporation are also for information only, and do not constitute endorsement, recommendation or favoring.
SAS is a registered trademark of SAS Institute Inc. SAS, Statistical Analysis System, and all other SAS Institute Inc. product or service names are registered trademarks or trademarks of SAS Institute Inc. in the USA and other countries. ® indicates USA registration.