HOME QUICK SEARCH AUTHORS KEYWORDS HELP BUGS

PharmaSUG 1998 Papers - Index

48 papers. Source: PharmaSUG (Pharmaceutical Software Users Group) conference proceedings.

Back to Conf
go 1999
go 1997
# Title
×		 Authors
×		 Abstract
×		 Keywords
×		 Extras Pages
1 A Business Case for Using SAS/PH Templates as a Code Generator for Technical Report Table Writing Ben E. Bocchicchio,
C. A. Fortner-Burton,
W. W. Woods		 The writing of SAS programs to support a Technical Report (TR) is a time and resource consuming necessity. The SAS code's output listings are the corner stone of the TR. Whether the output is converted into a polished table or used by the medical writing staff as an aid in the generating the TR, SAS code needs to be created to synthesize the data data cleaning, box plot 5
2 A Data Audit Report for Any Occasion Drew K. Edwards Quality Assurance (QA) audits are commonly performed that compare the completed case report form (CRF) pages to a printout of the SAS database. The programming required to provide these audit reports can be very time-consuming and tedious. This poster discusses a SAS program that can be used to easily and quickly generate audit reports and field counts for QA audits and other similar purposes. The program requires that only a LIBNAME statement and TITLE statements be updated and the patient population be specified. This SAS program compiles a list of all page numbers as they occur in each dataset and then prints the entire database in page order for the specified patients. This allows the QA auditor to quickly compare the CRF page to the printed page. In addition, the program provides a summary report of field counts using the following two counting algorithms: all fields and all non-missing fields, both for each individual dataset and for the overall total macro variable, proc step, macro call, adverse events 7
3 A Laboratory Approach to JMP Annie L. Dudley Often getting the data from the machine that analyzed the sample to the analysis stage is a cumbersome and frustrating process. JMP offers possible solutions to several parts of the process. This paper presents a step-by-step approach to the fundamental uses of JMP software in the laboratory; to include setting up importing from an instrument, parsing the input stream, viewing incoming data in control charts, data validation, merging datasets, and exploratory data analysis. JMP Background JMP was first released in 1989 on the Mac only. In April of 1995, JMP was released for Windows 3.1, Windows 95, and WindowsNT. Rather than a data management tool, or a tool for statisticians, JMP is designed as a tool for researchers and engineers, who occasionally need a statistical tool. I. Importing Data JMP version 3 can import data not only from text, but also directly from an attached instrument or device dataset, sample, data cleaning 7
4 A Macro to Produce Pre-Formatted Electronic Documents Marina V. Kungurtseva,
Cheng-Tao Chang		 When a summary report using SAS PROC TABULATE, PROC REPORT, DATA _NULL_ or any other techniques has been generated, additional conversions for different customized final documents are generally required. This presentation discusses a SAS Macro which provides a simple approach to save and to convert an output into a word processing table format that is ready for use in the final clinical report. The electronic output is easy to edit or modify, if needed, within any word processing software program. Our focus will be on Microsoft Word since it has been adopted as the standard software by FDA. proc step, delimited file, proc report 11
5 A Sample of SAS/AF Automated System for Reports Generation Irene Zhao macro definition, macro facility 3
6 A SAS/Frames Application to Estimate Sample Size and Power for Clinical Trials Brian Mitchell SAS/AF Frame entries provide all of the flexibility necessary to make a user-friendly GUI-based variation of the traditional programs used to estimate sample size or power. This particular program uses an extremely comprehensive and accurate program named UnifyPow, which was written by Dr. Ralph O'Brien of the Cleveland Clinic (O'Brien, 1997). UnifyPow is used for the calculations and the tabular summary of the output. This application provides an on-screen graph of sample size against power for a user-specified range of values. Most of the functionality available in UnifyPow is incorporated into the graphical interface. sample, sample size, correlation, likelihood function, power analysis 4
7 A Technique for Importing External Data into a Relational Database Using PROC SQL, the Pass-Through Facility and the Macro Language Paul Doucette Data conversions are not fun, no doubt about that. But if you're lucky, you can usually learn a thing or two from them. This effort was no different. It was not a lot of fun but a lot was learned from it, including a few pretty neat PROC SQL and macro techniques. Credit must be given to SAS Tech Support for providing the basis from which this code was developed. The goal of this conversion was to create an automated process (the "bridge") that extracted recently entered or updated safety (adverse event) data stored in a clinical data management system (Oracle tables) residing on a VAX and migrated it to an adverse event tracking system built on a SQL/DS database residing on an IBM. Once the data was extracted from the Oracle database and exported to the IBM, SAS was used to perform the data conversion and insert the data into the adverse event (SQL/DS) database. This was accomplished through the use of PROC SQL statements contained in macros proc sql, proc step, macro variable, put statement, macro loop, do loop, %if-%then-%else, macro definition, call symput, &variable, relational database, character variable, adverse events, macro facility 7
8 Advanced Macro Topics: Utilities and Examples Arthur L. Carpenter Numerous utilities have been created using the SAS Macro Language and many of the newer utilities take advantage of recent changes and enhancements to the SAS System. The examples of macro utilities presented in this paper include the use of: /G43 SASHELP views /G43 DATA STEP and SCL functions using macro facility, macro variable, autocall macro, macro definition, macro function, proc step, macro loop, %if-%then-%else 6
9 Advanced Techniques for Creating Format with Variables Values Erika Y. Liu It is often necessary to have formats in order to generate tables or to print off datasets in certain nice layout. Programmers usually use PROC FORMAT with lots of value statements to do it, which is tedious and time consuming, and also typing in the name of each variable manually is prone to error. There is a more efficient way to create formats without having to write VALUE statements by altering the variable values. This paper first explore a way of specifying options in PROC FORMAT to use variable's values to create its format, and then demonstrates how to generate generic codes to make formats automatically by using MACRO. An example of Adverse Events is presented to demonstrate how to use this simple and helpful tip proc format, adverse events, proc step 3
10 An Easy-to-Use SAS Macro for Use with Microsoft Windows That Converts Existing Text Tables to Microsoft Word Tables Gary Cunningham This paper presents an easy-to-use SAS macro for use with Microsoft Windows that converts existing text tables to Microsoft Word tables. This macro applies the concepts of Dynamic Data Exchange (DDE), Dynamic Link Libraries (DLLs), and Word's Convert-Text-to-Table feature to automate the process of creating visually-appealing, word-processed tables from standard text files of computer output. Automating this process saves a significant amount of time over a manual process and eliminates typographical errors. A particularly appealing feature of this macro is that it works independently from the program used to create the text table, being primarily driven by the text file itself. Furthermore, the text file needs only to meet minimal requirements with respect to the way in which it is formatted txt, macro definition, filename statement, delimited file, sas function 5
11 Building Clinical Information Spaces on the World Wide Web Paul C. Wehr In clinical research, a clinical investigation is made up of a research protocol, data, analyses, and a research report. Each component depends on, or refers to, information contained in the other sections, and within itself. The goal of Clinical Research-to demonstrate that a drug or medical device merits approval-is really nothing more than an information space. This paper will show that using SAS Software, and the capabilities of the Web, one can create a convenient system for navigating this space, and even lay the foundation for a fast, inexpensive, and effective computer-assisted new drug application (CANDA) clinical research, crf, proc step, proc tabulate 4
12 Comparing Clinical Trials Data Using Population Trees Lisa McNamara Hlina Population trees generated using the SAS/GRAPH GCHART Procedure are a great way to interpret data from two different populations. In this paper, population trees are used to compare the psychological symptoms obtained from clinical trials data for two different treatment groups over three 28 day cycles. This paper will also discuss the use of how color and/or shading, as well as, annotated labels help to communicate information quickly and easily. The target audience is for both beginner and intermediate audiences and can be adapted to any platform proc step, proc gchart, clinical trial, clinical data, proc freq 7
13 Deciphering the _TYPE_ Variable in MEANS and SUMMARY Output Data Sets Arthur L. Carpenter The variable _FREQ_ has been included by PROC Output data sets generated using the procedures MEANS. It counts the number of available MEANS and SUMMARY automatically contain the observations and because of missing values, may not variable _TYPE_. This variable can prove to be very be the same as the number of observations used to valuable when creating or working with subsets of the generate the statistics class variable, proc step, proc means 3
14 Design and Deployment of a Web Application Using SAS/IntrNet Thomas H. Burger,
Richard W. Tucker,
John M. LaBore		 Industry research and development increasingly relies on global operations. IT divisions now more than ever are challenged with developing an infrastructure capable of providing business solutions at this scale. SAS/INTRNET software offers the ability to couple powerful analysis and reporting tools with global information delivery using the Internet. Speed-to-market initiatives demand rapid implementation of this capability. We describe a methodology for the design and deployment of a web application providing end-users the capability of generating text and graphical reports macro definition, macro facility, data wrangling, proc step, proc sql 7
15 Designing Edit Check Subsystem in SAS/IntrNet James Sun,
Monmouth Junction		 Edit check is one of critical steps in clinical trial data processing. It has a major impact on the overall quality of clinical studies. In the past, some SAS based edit check systems only u tilize SAS for limited computing service in a central or local environments. With newly introduced SAS/INTRNET, developers are able to extend the reach of application, and deploy comprehensive systems on an intranet setting. This paper illustrates a working prototype of edit check subsystem, which is able to manage edit check queries, track their resolution and monitor the overall progress. The prototype is essentially a multi-level SAS/INTRNET applic ation. Some technique issues are addressed in dealing with such an approach. Furthermore, the author will discuss the likely impact when such a system is built upon a standardized / modularized CRF design data validation rules, clinical trial, data wrangling, clinical data 5
16 Developing Cross-Platform IntraNet Applications on UNIX M. Kumar Sagar This paper illustrates two intranet applications developed using Netscape 3 browser on the client-end and an Apache http server running on a SunOS 5.5 server, at a major pharmaceutical company. The first application is executed from the browser interface, after the user fills in the required input fields. It invokes a PERL cgi-bin script that processes the inputs and in turn invokes an EXPECT script(s). This EXPECT script opens FTP and RLOGIN connections to the remote VAX and ALPHA (AXP) nodes. SAS programs are then executed on the remote VAX/AXP nodes and results are brought back to the UNIX, processed by the PERL cgi-bin script, and presented to the user in the HTML format. A Second application exploits the strengths of the SAS System by employing SAS/CONNECT to make a remote connection to the VAX/AXP nodes and transfer the SAS datasets to the UNIX node. This is again done from within the Netscape 3 browser on the client-end where the user fills in the required input fields dataset, view, error message, macro definition, create view, proc sql 9
17 Development of Global Reporting Systems for the Hoechst Marion Roussel Inc. Dorothy Hu Huang,
I. Outline		 proc step, data cleaning, raw data, macro definition, proc report, dataset, adverse events, clinical trial, macro variable, proc freq, %if-%then-%else 7
18 Fun With Formats. A Few Neat Uses Of Formats And Format Catalogs Lisa McNamara Hlina proc format, proc step 2
19 Getting a Grip on SAS Output Tables with Hyperlink Connie X. Li,
Monmouth Junction		 sas output, proc step, put statement, proc printto 4
20 Graphically Enhancing the Visual Presentation and Analysis of Univariate Data Using SAS Software James R. O'Hearn The problem of analyzing univariate data is investigated. In this paper an enhanced graphical approach based on a template of numerical summary statistics and graphical plots using SAS/GRAPH , SAS/QC , and SAS/STAT is presented. It is shown that this template provides a more powerful tool for assessing statistical assumptions, for suggesting corrective actions when assumptions are not met, and for elucidating patterns and relationships than the UNIVARIATE procedure. It is anticipated that this template will be of some use for the data analyst in gaining greater insight into the structure of univariate data. An example using fictitious exercise test data will be given to illustrate this methodology histogram, proc means, box plot, txt, proc step, proc greplay, proc printto 5
21 Happiness is Using Arrays to Make Your Job Easier Greg M. Woolridge Arrays and array processing are very powerful tools available in the SAS/G1A system which can be used to make programming easier. However; many people don't use them because they are thought to be too confusing or difficult to learn and use. This paper will present a brief tutorial on defining arrays and their properties. We will also demonstrate some real-life examples of how they can be used to make writing programs easier do loop, array, macro variable, if-then-else, dataset 5
22 Identifying and Reporting of Medically Serious Adverse Events: An Interactive Approach Anna Kunina,
Palo Alto		 When writing study reports for regulatory submission for a new drug application, detailed patient narratives are required for patients who develop a medically serious adverse events (MSAEs) during the clinical trial. Traditionally, the identification and compilation of MSAEs has been done manually as the adverse event thesaurus we use (COSTART) does not readily lend itself to this process which requires medical judgment. This paper describes an interactive and systematic approach which identifies, compiles and reports MSAEs. Two interactive (or computer assisted) systems were developed for the process: one for the identification and classification of malignancies; another for processing MSAEs. This interactive approach allows users (mostly medical staff on the drug development team) to review all necessary information prior to deciding whether or not an event meets MSAE criteria. Results are then compiled via interactive systems for reporting adverse events, serious adverse event, regulatory submission 3
23 Integrating SAS and Adobe Acrobat into Electronic FDA Submissions Shylendra Kumar Over the last two years the FDA Center for Drug Evaluation and Research (CDER) has released a series of guidelines for submission of regulatory documents in electronic format. On March 20, 1997, the Agency published the Electronic Records; Electronic Signatures regulation [21 CFR Part 11], which provides for the voluntary submission of parts or all of an application in electronic format without an accompanying paper copy. In September 1997 CDER released the dataset, clinical data, clinical data management, data governance, sas output, data science 5
24 Interpretation of statistical analysis for repeated measures Armand Rostami The purpose of this presentation is to develop a procedure that will aid in the interpretation of statistical analysis for repeated measures. The repeated measures would be measurements over time. A graph for each combination of categories of group variables would be given. All that is required would be the user will provide the data and the variables to be used as group variables. For example, the sex and the dosage of a drug being studied. The user provides the data set, and the two grouping variable names. The outcome would be individual plots for combination of sexes by each dosage, e.g. 0, 1, 2 and 3 units. Each plot shows response over time. In this example there would be eight plots on the page proc step, proc gplot, proc greplay, repeated measures, macro variable, class variable, macro definition, %if-%then-%else 3
25 Introduction to Arrays Bob Virgile This paper explains the basics of defining and using an array. The information and examples will be useful to the programmer who is either unfamiliar with or confused by arrays. The basics are simple enough that most programmers can begin to successfully use arrays immediately after reading this paper. array, dataset, character variable, sample 6
26 Managing SAS/PH-Clinical in a Multiple Instance Environment Steven Light,
Paul M. Gilbert		 Companies using SAS/PH-Clinical to support mu ltiple clinical development projects often implement separate instances of PH-Clinical. Maintaining consistency among instances can be a complex system management task. This paper discusses a multiple instance model for deploying and managing PH-Clinical in which a separate PH-Clinical instance is created for each project. Consistency and compatibility of project instances is maintained by building each instance from a single 'standards' instance. Global standards for the PH- Clinical dictionary, PH-Clinical study definition, PH- Clinical variable group and PH-Clinical templates are maintained in the standards instance. Modifications to these 'standard' PH-Clinical objects are made only in the standards instance and distributed to project instances. Design considerations, implementation issues and configuration management will be discussed clinical trial, data standard, clinical data, clinical data management, dataset, data governance, sample 3
27 PharmaTechnology Process: Data Autoload Kay Obenshain Prior to Release 2.10 of SAS/PH-Clinical Software, the process of defining clinical data for use within SAS/PH-Clinical has been interactive and, at times, complex. The Autoload facility greatly simplifies the process. In many instances, information about clinical data (metadata) is maintained by a clinical database management system. The natural question is, "Can I use my existing metadata to automatically load my clinical data into SAS/PH-Clinical?" The SAS/PH-Clinical Autoload facility is designed to provide this functionality 4
28 Printing a Random Sample of a Large Data Sets Hany Aboutaleb If you have a large data set and you wish to print 5 %, 10 %, or more of your data, this article can help you. It describes and illustrate how to print a percent of your data with PROC PRINT. The macro will pick the percent of your data that you specify and then help you to print it. The percent that is printed is a random sample. The database you are working with can be an entire library or just one file sample, proc print, proc step, macro variable 4
29 PROC SQL Dictionary Tables - A Great Source of Information about Data Sets Wendih S. Yao PROC SQL provides the capability to retrieve information about all libraries and external files that are allocated in a session. This information will be returned as what appears to be rows in tables and can be accessed from other procedures by creating views of the tables listed in this paper. It can be accessed by PROC SQL with views of the tables or with the table names themselves proc sql, dictionary tables, proc step, macro variable, order by, adverse events, serious adverse event 4
30 Programmers Can Check Data Too Diana L. Williams Many times throughout the course of data cleaning it would be helpful to take a quick look at numeric values and dates as data become available. The identification of outliers is commonplace in statistical analysis, but often times programmers are underutilized during the early stages of a study. They can be of tremendous help to quality control auditors, data management personnel and statisticians by providing some quickly generated, easy to read, consolidated listings of current data values. This poster will present two SAS programs which can be easily modified for use with any SAS database. The UNIVARS program utilizes the PROC CONTENTS procedure and two macros to automatically produce univariate statistics for every numeric variable in a SAS database. The HILODATE program uses similar means to produce a consolidated listing of high and low date values for every SAS date variable in a database proc step, date variable, proc contents, proc univariate, macro variable, proc sort, macro definition, sample, data step, macro loop 4
31 Reducing the Time to Market Through Importation of VMS/SAS into PC WordPerfect Donald Six macro variable, %if-%then-%else, macro definition 5
32 Retiring Legacy Database Systems with SAS Brenda Bishop,
Hoechst Marion Roussel		 Mergers and acquisitions are common in the industry and each company can have a different system and platform for data management. Hoechst Marion Roussel had three active legacy systems from three previous companies (Marion Labs, Merrell Dow, and Marion Merrell Dow). Each system was on a different platform. In 1997 HMR launched a global data management system on a UNIX platform. Working with four systems was too much for any programmer to manage. This presentation will go through the steps used to archive data from the three systems into SAS datasets dataset, flat file 4
33 SAS Techniques for Developing an Intranet Drug Safety Review System Dennis X. Tang,
Mickey Cheng		 Intranet systems allow users to quickly access information and conduct in-depth drill-down analyses. At the International Clinical Safety Department (ICSD) of AMGEN, SAS and Perl languages are used to develop a Safety Online Adverse Event Review system. This system gives a summary of adverse events first, and then permits users to drill-down for details of the adverse events such as original report, company comments, severity and relationship to company drugs, etc. This paper will discuss SAS techniques used to develop Web pages, links, and reports adverse events, proc report, sample, oracle, preferred term, statistical programmer, proc step 10
34 Serving Up Clinical Information Globally to your Web Browser from MVS Don Johns clinical trial, macro parameter, macro facility, proc freq 5
35 Some Aspects of Statistical Modeling to Develop a System for Pharmaceutical Industry Indicators Forecasting Alexander Visnevsky,
Covance Periappoval		 pharmaceutical industry, regression analysis 6
36 Supporting the "Program-Analyze-Write-Review "Process with a Development Environment for Base SAS and the Macro Language Barry R. Cohen Pharmaceutical companies do much Base SAS and Macro Language programming in the process of analyzing their clinical trials data. This is one part in their larger process of collecting, managing, analyzing, and presenting this data. Many companies now provide considerable system support for the early part of this process (data collection and management) and for the later part (document publishing and presentation of sas base, macro facility, sas output, sas programmer, clinical trial, pharmaceutical industry, data science 6
37 The Causes, Impact and Detection of Duplicate Observations Alice M. Cheng Invalid duplicate observations can produce incorrect statistics and cause data management problems. It is critical to identify repeated observations through data validation process. This paper will discuss the possible causes, impact and methods to detect these redundant observations. Keywords: Duplicate Observations, Observations with Duplicate Key-Variable Values, Identifiers, Key Variables, Structural Query Language (SQL). A. Introduction Duplicate observations are observations with identical values for all variables. In clinical trials, as well as, in other disciplines, the chance of having relevant duplicate observations is almost null. Often times, unique identifiers (or key variables) are used to specify an observation. The choice of variables as identifiers depends on the design of the study and of the data management system create table, proc step, proc sql, by group processing, group by, proc freq, clinical trial, unique key, full join, data cleaning, order by, sample, macro loop, macro definition 11
38 The Clinical Data Warehouse Peter Villiers One of the greatest challenges facing the pharmaceutical industry today is the migration of data from a raw, data-entry oriented format into a consistent, analysis friendly format. This includes the pressure to perform the migration on a regular (sometimes daily) basis and provide verification that no errors are introduced during the migration process. Data warehousing has the potential to solve a great many of the data management issues that arise as a consequence of this pressure. The SAS /GD2 PharmaTechnology Center at SAS Institute is developing tools for building Clinical Data Warehouses. These tools are integrated with SAS/WAREHOUSE Administrator/GD4 software to provide a complete data migration solution data migration, pharmaceutical industry 5
39 The Magic of PROC SQL John Hotaling The SQL procedure provided by SAS places a great deal of power into a programmer's hands. It can be used to examine existing data or to join data together in a manner which is sometimes preferable to merging. proc sql, full join 3
40 The Right Approach to Learning PROC TABULATE Bob Virgile PROC TABULATE produces tables as illustrated by the samples in Figures 1 and 2. These tables incorporate some special features, features which no other SAS procedure can produce. The first feature is that the rows (or columns) may be composed of a number of variables. The variables may be concatenated (as with STATE and CUSTOMER in Figure 1) or nested (as with COMPANY and JOB in Figure 2). The other unique feature of PROC TABULATE tables is that the numbers in the table are not necessarily frequency counts. The numbers can represent statistics (means, sums, etc.) based on the values of numeric variables. proc tabulate, proc step, proc means, format statement, sample, proc freq 8
41 There's No Such Thing as Normal Clinical Trials Data, or Is There? Daphne E. Ewing Clinical Trials data comes in all shapes and sizes depending upon the therapeutic area, indication and phase of the trial. Quite a bit of the data arriving on Case Report Forms (CRFs) is fairly standard (e.g. Demography, Adverse Event, Medications, Laboratory, etc.), and hence can be stored in fairly standard data structures. Designing clinical data structures for data entry is important, but it should be done with some understanding of the analysis that will be performed. Once an appropriate clinical data structure is arrived at for data entry, it is important to then determine how to best use the data in the analysis environment. This paper will discuss data normalization and what it means along with the effects it has on SAS programs used to list and summarize clinical trials data. Side by side examples of programs and output from standard data structures versus normalized data structures will provide proof of the importance of normalization proc step, sample, proc report, by group processing, proc means, normalization 14
42 Transposing a Relational Database: The Q-System for Pharmaceutical Safety Summarization, Graphics and Analysis Mary Cowmeadow Transposing relational data to one record per subject can solve all those "many to one" problems that make analyzing and summarizing this type of data so difficult. The Q System transposes pharmaceutical safety data, i.e. adverse event (AE) data, from a relational database structure to a "data mart" type of structure with one record per patient. Since AE data are generally summarized and analyzed at the patient level, the data should be structured in this same way. Data can then be entered directly into appropriate statistical or graphical procedures with meaningful results. Transposing a relational database is a straightforward process. The major challenge is sorting, organizing, renaming and re-labeling the hundreds, sometimes thousands, of AEs collected during a clinical trial. But once this was done, writing programs for standard excel, proc step, relational database, proc transpose, adverse events, macro variable, structured data, proc freq, macro definition 8
43 Use of Pilot Trials as Screening Procedure in Generic Drug Product Development: Statistical Power and Influential Factors Yibin Wang power analysis, sample size, sample, confidence interval, normal distribution 5
44 Using Dynamic Data Exchange Within SAS Software to Directly Access Data From Microsoft Windows Applications Ellen L. Asam,
Donna Usavage		 In order to support the statistical analysis of clinical data, we utilized the DDE facility in SAS to retrieve clinical study data from a Microsoft Access database. Although the DDE facility is documented, it took quite a bit of experimentation to successfully execute. Our programming environment included Windows for Workgroups 3.11, SAS 6.10, and MS Access 2.0. Our Microsoft Access database was available to many users on a local area network and DDE provided us with the most current data. In our paper, we use our programs to provide examples to review the DDE syntax using the FILENAME statement and explain how the DDE triplet maps to our MS Access database. Our example reads in entire Access tables, but we describe how to set limits. This paper also touches on accessing MSExcel data from within SAS as well as writing data to Microsoft applications from within SAS proc sql, dataset, excel 4
45 Using Proc Report in Displaying Clinical Laboratory Results Ann Root Many features of PROC REPORT provide you with the simple tools for generating complex report listings for clinical laboratory results. This procedure is flexible enough to present results across columns or consolidate many observations into one record. This paper presents the steps for presenting lab data in a variety of ways utilizing PROC REPORT. 1. Lab Data Listings 2. Means and Standard Deviations of Labs 3. Changes of Means and Standard Deviation of Labs from Baseline proc step, proc report, standard deviation, numeric variable 3
46 Using SAS Arrays to Estimate Regression Parameters Tesfaye Liranso,
Hoechst Marion Roussel		 Many experiments from clinical trials call for the methods of simple linear regression analysis. The SAS system provides many procedures that perform this analysis, and it is typical to choose a procedure to fit a specific situation. A SAS program using SAS arrays, and meeting general situations is developed to estimate the parameters of a simple regression. Output from this method is compared with outputs obtained from some of the most commonly used procedures such as GLM, REG and MIXED regression analysis, simple linear regression, proc reg, proc genmod, proc step, macro loop, proc report 5
47 Validation of SAS Macro Systems Philip M. Pochon The validation of systems for regulated environments requires rigorous testing. System validation is generally achieved through structural testing ('white box') and functional testing ('black box'). SAS macros permit construction of analysis and reporting systems using highly testable modular components. We describe a systematic method of validating macros which permits structural testing and (multilevel) functional testing while preserving regression testability data cleaning, macro definition, macro variable, macro conditional, regression analysis, coverage units 5
48 Web-Based Data Collection and Report Generation Aradhana Gokul Janga,
Kaiser Permanente		 The World Wide Web provides the ability to exchange information between sources at different locations. This could be a very efficient and cost- effective way of obtaining valuable data in a research environment and for disseminating useful information. Although powerful commercial software like SAS Intrnet are available for such uses, the availability of free/low cost public domain software like Perl and some web servers and Javascript enabled web browsers, allows a highly cost effective implementation. This presentation focusses on developing a low-cost system for collecting data and generating reports by combining basic SAS tools with such software. Thus, research programs and organizations with limited resources can still collect data that will be up-to-date, error-free, logically correct and meaningful. The Need There exist a lot of ways to enter data for purposes of research, analyses and reports dataset, proc sql 5

Back to Conf go 1999 go 1997

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.