PharmaSUG 2000 Papers - Index

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

#	Title ×	Authors ×	Abstract ×	Keywords ×	Pages
1	%RPT_UTIL: A SAS Macro for Enhancing Reports in Clinical Trials	Wei Cheng	When preparing tables and listings for clinical trial studies, we need to show the company name, protocol name, table titles, notes, program name, create time, etc. on each page. We also need to put each page number and the total number of pages on each page. By simply calling the SAS macro RPT_UTIL once, we accomplish all these tasks. It has the following features: All headers or footers of all the reports can be placed in one program; Footnotes have the same width as the width of the report; The macro can call external or internal reports; The blank space on the last page can be eliminated; * The macro can run under other operating systems with a few modifications	clinical trial, macro call	6
2	A Macro System for Standardizing and Grading Laboratory Data	Bruce Coate, William Hoskins	In nearly all clinical trials involving humans it is necessary to collect and evaluate lab data. Frequently this evaluation consists of assigning a grade to each result, and then summarizing changes over time for each test. The purpose of this paper is to present an overview of how lab data is standardized and graded using SAS macros. The procedure outlined here starts at the point where the lab data has been entered into a database (Oracle Clinical in this case) and validated, and ends with the creation of a standardized, graded SAS dataset	proc step, %if-%then-%else, macro definition	7
3	A Macro Tool to Check If Values of a Variable Match Its Format	Yuguang Zhao	Formatting is a standard practice for decoding coded variables in SAS. Sometimes, it is necessary to check if the entered values of a coded variable match its format. Unfortunately, it is very tedious to check if the entered values of a variable match its format. This macro will scan all SAS data sets in the specified directory, sort out the formatted variables and compare the entered values with their corresponding formats. If the entered values do not match the values listed in the format, the macro will print out the variable, the entered value and the format name	do loop, macro variable, proc step, proc freq	4
4	A Nonparametric Approach for the Statistical Analysis of Time to First Event in Censored Paired Data	Roderick Lashley, Dennis W. King, Pam Marks	Analyzing time to first event data is a common problem in drug development. For a randomized block design or crossover design yielding time to first event data on multiple treatments, standard nonparametric tests, such as the Log-Rank or Gehan Test prove to be inadequate since they do not take into account within subject correlation. This paper will examine a procedure commonly referred to as the Prentice- Wilcoxon Test that can be used to test for differences between the time to first event profile of two treatments tested in a randomized block design. We will use an example from the pharmaceutical industry to illustrate the implementation of this procedure with the SAS System	wilcoxon test, clinical trial, data science	3
5	A SAS Macro For Creating a Standard Directory Structure	Andrea Dynder	This paper discusses an interactive SAS macro that creates a standard directory structure for use with SAS programming related projects. The macro provides a generic directory structure framework for any project, and allows users to provide their own project-specific directory names where appropriate within the framework. It then issues the required operating system level commands to actually create the desired directories on the disk subsystem. The benefits of utilizing such a macro, parts of the SAS code for the macro, and a possible directory structure framework with application towards the pharmaceutical industry are discussed. The use of the %WINDOW statement of the SAS Macro language to achieve the user interface is also discussed. SAS processing platforms targeted are Win/NT and UNIX	macro parameter, sample, macro variable, macro definition	5
6	A SAS Tool for the Presentation and Statistical Analysis of Data from Bioavailability and Bioequivalence Studies	Melvin S. Munsaka, Carl R. Haske	The statistical analysis of bioavailability and bioequivalence data derived from blood or serum concentration measurements requires presentation of individual subject data as well as	data science, pk parameter, adpp, sample size, fixed effects, proc means, anova, sample, outlier	8
7	A Standard Reporting System for Phase 1 Clinical Trials A SAS Based Application "Clin Pharm World"	Fang Dong, Lorraine Dunn, Brian Rosson, Richard F. Synowiec	The Parke-Davis Clinical Pharmacology standard reporting system, called Clin Pharm World (CP World), is a SAS based multi-platform application that runs on a Windows NT workstation and a Unix host. It makes extensive use of Base SAS, `SAS/CONNECT` and SAS Dynamic Data Exchange (DDE) technology. It also utilizes Visual Basic (VB) macros that run under Microsoft `EXCEL`. The Unix portion of the application uses SAS SQL PASSTHROUGH to extract data from an Oracle database, and performs the intensive data manipulation. The Windows NT portion of the application serves as the interface between the user and the Unix host. Additionally, Windows NT performs a data output 'step' using SAS DDE technology. The VB portion of the application is invoked with SAS DDE and allows great flexibility and customization for table formatting. The final output is stored in `EXCEL` and accessed, via the Parke- Davis intranet by our clients (i.e., clinical scientists, physicians and medical writers)	excel, adverse events, clinical trial, sas base, proc sql	4
8	A String Search Program Which Displays the Whole Line for Each Line Containing the Target String	Hugh Geary	Have you ever needed to know which of all of your programs use a certain variable, call a certain macro or, more generally, contain a certain character string? Would it be useful to know which of these programs are old or were modified recently? And would you want to have this information for all of the files in a folder and its subfolders? If you use VMS on a VAX you have such a utility, but apparently it has to be reinvented for PC SAS users. Such a utility is described here here for any users of BASE SAS on a PC.. The target line and some lines before and after can be displayed as well to help see the context in which it is used. The name of each file found and the date of last modification is also given. The results can be saved in a file or displayed on the screen. An application can be extracting current program documentation from information stored within each of your programs into a documentation file at the end of a project	dataset, filename statement	3
9	A Submission Development Environment to Support SAS Programming and Related Activities During Clinical Data Analysis	Barry R. Cohen	Pharmaceutical companies conduct many activities during the statistical analysis of their clinical data. This is one part in their larger process of collecting, managing, analyzing, and presenting all this clinical data (safety and efficacy). Many companies now provide considerable system support for the early part of this larger process, (i.e., the data collection and management), and for the later part when the New Drug Application (NDA) document is published and presented to a regulatory agency in electronic form. But much less has been done to support the work involved in the statistical analysis of the data using SAS Software, particularly Base SAS and the Macro Language. I discuss automated, integrated support for the statistical data analysis in this paper. I call this support a Submission Development Environment. An automated, integrated environment for this work is surely a challenge, but it offers much potential payoff if it can be achieved	data science, macro facility, clinical data, dataset, macro parameter, sas base, sas output, sas programmer, statistical programmer, sas programming, proc sql	6
10	An Alternative to the Odds Ratio: A Method for Comparing Adjusted Treatment Group Effects on a Dichotomous Outcome	P. Chris Holland	The odds ratio is a commonly used statistic for measuring the association between two groups on a dichotomous outcome. In clinical trials, it can be used as a measure of association between two treatment groups on a clinical response rate. However, it is sometimes desired to compare directly the estimated difference in response rates between two treatment groups. While the `SAS/STAT` software does offer features for such comparisons, it does not allow for adjustments made to the treatment effect based on other explanatory variables. I present a method for testing success rate differences between two treatment groups while adjusting for other factors and a SAS macro that performs the necessary steps for carrying out the procedure. The macro produces an output data set that contains estimated adjusted success rates, the difference between them, confidence intervals around the difference, and an associated p- value	confidence interval, logistic regression, regression analysis, logistic distribution, odds ratio, interaction effect, class variable, estimate, proc genmod, nominal variable, macro definition, proc freq, clinical trial, treatment effect, response variable	5
11	An Integrated Review Tool: Using the SAS SQL Library for C to Access SAS Data	Andrea L. Contino	This paper is going to discuss one of the lesser-known tools SAS makes available to application developers to facilitate the access of SAS datasets, the SAS SQL library for C. Integrated Review is a client server application for the review of clinical data stored within an Oracle database management systems. We wanted to broaden the tool to access SAS datasets since the majority of our customers' store "derived" analysis data in SAS . Since the server portion of Integrated Review is a C or C++ application that runs on the Windows and Unix platforms, the SAS SQL library for C was the perfect solution. We needed a fast and flexible tool to access the SAS data without needing the full power of the SAS software. The SAS SQL library for C works in conjunction with the `SAS/SHARE` * Net server whereby SQL queries and statements are passed through the Share server	proc sql, clinical trial	1
12	Automating the Quantification of Healthcare Resource Utilization With Base SAS Software	Nancy Bourgeois, Bobbie Coleman	Healthcare researchers often use prevalence, incidence, and rates of patient visits to physicians, hospitalizations and nursing home stays in the general population to better understand the healthcare resource utilization of diseases. These data contribute to the decision-making process regarding which diseases to treat or prevent to improve public health and to minimize healthcare costs. By making this information on healthcare resource utilization from three commonly used US healthcare surveys readily available, these data can be used by epidemiologists within the company without waiting for a programmer to write a program to provide this information. Computing Environments: NT 4.0 SAS Products: PC SAS 6.12 Other software products: Microsoft Word 97	proc step, dataset, proc sql, create table, data step, macro variable, macro definition	14
13	Calculating a Nonparametric Estimate and Confidence Interval Using SAS Software	Chris Decker	In clinical trials nonparametric analysis methods are sometimes used to assess the differences between treatment groups. Most people use either the `NPAR1WAY` procedure or the `FREQ` procedure to perform nonparametric analysis. However, no procedures currently exist within SAS software to produce a nonparametric estimate of the difference between treatment groups or a confidence interval to assess the magnitude of that difference. This paper describes the process for calculating the nonparametric estimate of the difference and the confidence interval to assess the magnitude of that difference with the use of the `SQL` procedure statement and a few DATA steps	confidence interval, proc sql, proc step, sample, clinical trial, response variable, treatment effect	3
14	Check Digits: Avoiding Errors in Clinical Trials	Malachy J. Foley	In clinical trials, faulty key information leads to duplicate and missing data, which in turn, leads to weakened and biased results. For this reason, it is vital that patient ID' s and other key information always be correct. Check digits are a powerful tool to insure correct data. They can eliminate up to 99% of all transcription and keying errors. They even catch errors missed by double keying. This paper is a tutorial that explains the what, why, when and how of check digits. It includes SAS code to calculate and implement check digits	clinical trial, numeric variable, data wrangling	5
15	Clinical Data Management: Building a Dynamic Application	Arthur L. Carpenter	You have written a series of interesting and often complex SAS programs that perform a variety of data entry operations, data checks, exception reporting, statistical analyses, and summary reporting. Since the next study is somewhat similar to the last one, you are planning to build another set of programs based on (cannibalized from) the ones that you just used. We have been there before, but STOP. Wouldn't you rather build the programs once? The solution lies in building and using data dictionaries that act as control files. These control files are in turn used to create a series of SAS macro variables that are available as arrays to each of the various programs. All project, data set, and variable specific information is stored in the macro variables and hence never in the programs themselves	macro variable, macro loop, do loop, variable list, call symput, macro definition	7
16	Clinical Data Warehouse Functionality	Peter Villiers	Data Warehousing is a buzz-phrase that has taken the information systems world by storm. It seems that in every industry publication, there are articles explaining how this relates to financial and marketing data, yet there is very little information about how the concept of data warehousing applies to the research and development side of the biomedical industry. This paper aims to review some information presented at PharmaSUG 1998 in the paper "The Clinical Data Warehouse"; detail how this information has been acted upon; outline the lessons learned and finally specify areas of new functionality that have been identified to further aid in the clinical research process. This paper is aimed at anyone interested in obtaining a general introduction to clinical data warehousing functionality. The paper will describe concepts and ideas but will not go into details of implementation	clinical data, raw data, clinical research	5
17	Collapsing Adverse Experiences Records	Shi-Tao Yeh	One of the most challenging ta sks for SAS programmers in the clinical studies is to collapse the adverse experiences (AE) records. The AE records are identified as either collapsible or non-collapsible. The collapsible AE records can be categorized into two types. The first type is a set of multiple records with the same AE onset date. If the AE record has a missing end date, this indicates the event is continuing. The second type shows the records with a time consecutive sequence. This paper provides two SAS macros for AE records collapsing, one for each type of collapsible AE records. The SAS product used in this paper is SAS BASE , with no limitation of operation systems	macro definition, data step, clinical trial	5
18	COMPDIFF: A Macro for Comparing Data Sets	Matthew Clarke	`PROC COMPARE` is used to compare the values held by variables in two SAS data sets or variables within SAS data sets. The syntax can utilize up to thirteen options to control the printed output, ten options to control the listing of variables and observations, and six options to specify content of an output data set. When the user determines all the options needed for their comparison, the standard output can often be confusing and lengthy. COMPDIFF is an attempt to create a user friendly tool for the comparison of SAS data sets. Instead of the standard output from `PROC COMPARE`, COMPDIFF enhances the reporting of the comparison and reduces the amount of output needed to display the comparison. It requires less code to carryout unique comparisons because sorting is done within the macro. COMPDIFF is an efficient and easy to use tool for comparing SAS data sets	proc compare, proc step, proc print	2
19	Compliance Readiness for the New Millennium How does your SAS Environment Measure Up?	Steven Light	This paper summarizes how current FDA and ICH regulations and guidance documents affect SAS programming and biostatistics groups reporting clinical data. Its main focus is to illustrate how a organization can assess their current position relative to established standards. Issues to be reviewed include Standard Operating Procedures, Systems and Process Validation, Change Management, Business Process and Systems Documentation, Security, Personnel Qualifications and Training and Archival Protection of Records	data cleaning, recovery planning, sas programming, clinical trial	6
20	Constructing a Data Warehouse for Pharmacokinetic Data	Stanley P. Koprowski Jr., Jeffrey S. Barrett, Dwight J. Fowler	The construction of a warehouse using data from DuPont Pharmaceutical's Clinical Pharmacokinetics Group with the `SAS/WAREHOUSE` Administrator product is described herein. Data sources incorporated into the pharmacokinetic warehouse existed in multiple formats (Oracle, `EXCEL`, SAS data sets, etc) and were represented by numerous individual files, rather then few large files. In most cases, the data density enjoys low granularity. The pharmacokinetic data warehouse draws data from many sources represented by multiple departments and spans long drug development cycles with varying degrees of detail. Additionally, data originated from both internal legacy systems or was obtained from an external contract research organization (CRO). Remote systems have been easily identified within the warehouse and views rather than distinct copies have been incorporated as data sources	pk parameter, data cleaning, clinical research	9
21	Creating Documents that create themselves with SAS and XML TM	Michael C. Palmer	The creation of finely structured documents such as statistical tables in an electronic submission can be automated with electronic documents that contain instructions for database software and publishing software, but no content. Documents with instructions for their own creation, but no content, have been termed "documents that create themselves." The document that creates itself is built in XML of database query instructions and style and composition instructions. When content becomes available, an integrated system of SAS programs exploiting features new in versions 7 and 8 works with XML-enabled publishing software to render the document that creates itself into a complete document in PDF or other formats. The system interprets the instructions to retrieve content from a database, compose and style the content, and publish it. When content is updated, the document is re-run. By segregating content, the reuse of style and composition templates is facilitated	proc tabulate, pharmaceutical industry	4
22	Creating Multiple SAS Data Sets from an ASCII File	Archie Medrano	Data records read into SAS can come from various types of sources. The three basic types of sources are: external files, data lines in the job stream, and existing SAS data sets. This paper discusses the method of reading raw data from an external (ASCII) file into one temporary data set and how this data set is split into multiple data sets (with different sets of variables) using the information in one or more of its variables	if-then-else, input statement, raw data, macro variable, macro definition, %if-%then-%else	6
23	Creating PDF Files Using Data _NULL_	Paul K. Slagle	Creating portable document format (PDF) files has become a preferred method of transporting reports electronically. Under V8 SAS, a facility is available for directly creating these file without the need for third party software	txt, macro definition	2
24	Creating Powerful Laboratory Listings	Bob J. Hull	The summarization of laboratory data can be very exhausting. Different laboratory units, and new test names appearing each time the data is updated can cause quite a headache trying to keep the output from your programs correct. I offer suggestions that can enable your laboratory listing program to recognize these problems in updated data and appropriately display all of the data. Allowing your program to count all of the unique test/unit combinations will enable you to use macros and `PROC REPORT` to accurately display all of the data. Then when it is requested to have 6 columns to a page rather than five, you do not have to change all of your macro calls. Instead just identify the number of columns desired and your program will build its own macro calls. This article is intended to give ideas on how to create a very robust laboratory listing. It outlines specific items that will be needed to accomplish that task. To implement the ideas it is assumed that you have a good knowledge of	proc report, proc step, laboratory data, macro variable, macro call, proc format	3
25	Data Mining and Statistics in a Pharmaceutical Environment	Franky De Cooman	Until now, most of the statistics are used in the R&D department. It is also observed that DM techniques are seldom used in a Pharmaceutical environment. This paper will show that these techniques can be easily and successfully used outside of their normal habitat	adverse events, clinical trial, proc hpsplit, proc freq	3
26	Data Modeling in Clinical Data Analysis Projects	Gajanan Bhat		normalization, key, clinical database, clinical data, raw data	3
27	Delivering Clinical Study Data Using SAS/IntrNet TM	Damian Ciccariello, Phil Giangiulio, Gregory T. Weber	Newly adopted FDA guidelines require clinical study data be delivered as SAS data files in all electronic submissions. The speed and depth at which Clinical Scientists need to assimilate this data is ever increasing. SmithKline Beecham, utilizing `SAS/INTRNET` technology, has developed a Patient Data Browser to address this need. This presentation will describe the Patient Data Browser and how `SAS/INTRNET` was employed. Topics will include the following: Patient Data Browser Overview Building an easily maintained and versioned Web application Application Security Overcoming SAS 6.12 and `SAS/INTRNET` 1.2 Limitations * Version 8 Enhancements	macro variable, clinical data	4
28	Developing Clinical Data Management Systems using Version 8 of SAS/AF	Steven A. Wilson	The `SAS/AF` product in Version 8 of the SAS System is a robust realization of an object oriented development environment. This product will allow developers to easily create sophisticated in-house applications. MAJARO InfoSystems is the developer of a SAS-based clinical information system called ClinAccess that was originally developed using Version 6. As such, we are acutely affected by the version change of the SAS System. We have been working for some time now on upgrading our ClinAccess product to Version 8 of the SAS System. This paper will attempt to detail the process of applications development in SAS Version 8 as gleaned from our upgrade experience	clinical data, dataset, audit trail, constraint, sas log, catalog entry, proc step, clinical trial	10
29	Efficient SAS Quality Checks: Unique Error Identification And Enhanced Data Management Analysis	Jim Grudzinski	The pressures of protocol timelines require an efficient process of quality checks and data error identification. Previously, at Covance, quality checks were run on a cumulative and/or on a set time period range. The data managers would have to review reams of hard copy reports and manually check the issued Data Clarification Forms (DCF's) for previously identified errors. Identify new quality check errors and generate the necessary DCF. The quality checks that could not be corrected would still appear on the hard copy reports, creating a redundancy of review time effort. This was a time consuming and inefficient process. This paper will offer one way of providing for an efficient SAS quality check process. Leading to unique error identification and analysis. This process will integrate SAS and Oracle in a Unix environment. The SAS programming code detailed in the paper is intentionally simplistic for demonstration purposes	proc step, dataset, proc append, key, proc sql, data governance, view	6
30	Expedite Processing Central Laboratory Data with Working Practices, Standards and SAS	Margaret Hung, Henry Shades, Michael Acra	The handling of central laboratory (lab) data is one of the most time- consuming data management tasks. To facilitate the processing of lab data, international data management standards and working practices were established and implemented across Glaxo Wellcome (GW) therapeutic groups and with the various central core laboratories doing business with GW. In addition, a series of SAS programs were developed to machine check lab data. All of these endeavors have helped to streamline the process, reduce time in cleaning up lab data, and enhance communication between GW and our major central core lab vendors. Operating systems: Windows NT 4.0 , VAX Software: SAS 6.08, SAS 6.12, VAX commands	laboratory data, sample, dataset	4
31	From Data to Study Report in One Step: A SAS Macro for the 2,2,2 Crossover Design	Amy Morris, Thomas E. Bradstreet	The two-treatment, two-period, two-treatment-sequence (2,2,2) crossover design is used frequently in drug development programs. Historically when evaluating these trials, each statistician produces his/her own statistical analyses, tables, listings, and graphics by modifying either his/her own software code or code which is on loan from other persons. This process is iterative and can produce redundant efforts both within and among individuals, errors in software revisions, delays in validation, and inconsistencies in the presentation of study results. Recognizing the opportunity to improve this process, we developed a SAS macro to statistically analyze and efficiently display the results from a 2,2,2 crossover trial. The macro produces report ready	anova, treatment period, in=, data science, outlier, macro definition	5
32	GLOBAL INTEGRATED DATABASE (GIDB): Not Just a SET Statement	Marla A. Childers	Last minute changes to the definition of algorithms and reports are inevitable. Creating and using a Global Integrated Database (GIDB) for reporting can reduce programming time and the number of last minute changes across any given project that contains more than one protocol. This paper will reveal the advantages and disadvantages associated with the creation of a GIDB and provide insight to defining and building a GIDB	crf, proc step, proc format, set statement	4
33	How MERGE Really Works	Bob Virgile		set statement, dataset, length statement, merge statement	12
34	How to Conduct 100% Validation of Derived Variables, Tables and Listings	Mary Jane Young	Typical programming done by biostatistics departments' include generation of tables, listings and variables derived from case report form (CRF) data. All of these require some level of validation. Simple table validation may consist of hand checking the data. However, with long listings and multiple page tables, manual checks are time consuming and run the risk of human error. For this reason, a new process is being developed for validation at PPD. In this paper, we will present the methodology that we are implementing to automate the complete validation of listings, tables, and derived variables	data cleaning, proc step	4
35	How To Improve The Process Of Generating Audit Listings	Wendih S. Yao	Clinical Data Management has taken an increasingly important role in the data quality aspects of clinical trials. It has focused primarily on the case report form. When a case report form is received by CDM it may be reasonable to suggest that 95-98% of the data is correct. However, will these data be entered correctly is questionable. A simple data listing can be used to measure the quality of the data entry process. How to shorten the time from writing the code to output listings being produced is the	macro variable, proc sql, dictionary tables, proc step	3
36	I Don't Look Good in Orange or Stripes. Subtitled, "Hard Coding Clinical Data is not Permissible"	Susan M. Fehrer	Clinical programmers are often asked by data managers, statisticians, project directors, or their supervisors to hard code or change clinical trials data to match the Case Report Form or other data collection medium rather than to open the database and make the appropriate change(s). However, there are federal regulatory regulations that set forth policy and enforcement of such	audit trail, data cleaning	3
37	Integrating Metatdata in Pharmaceutical R&D Warehouses	Philip M. Pochon	Warehouses amass discovery and clinical results as the basis for Decision Support Systems (DSS). While collected and computed values are major components of warehouses, metadata defining	anova, main effect, macro variable, quality assurance, macro definition	5
38	Integrating SAS in Corporate IT	John M. LaBore	Applied users widely recognize the value of information delivery using SAS software. Integrating SAS into the business increases and streamlines productivity. However, limited awareness may exist in corporate IT of the role these tools play in knowledge formation for business solutions. The undervaluation of SAS stems from historical use by researchers, rather than IT developers enamoured by new technology. This can be remedied by raising corporate IT's awareness of cutting- edge SAS tools and the value of their adoption for timely solutions to a growing range of tasks. We discuss issues associated with raising corporate IT's awareness of the power of SAS software	clinical research, insurance	6
39	Integrating SAS Software with Microsoft Visual Basic for Applications to Mass-Produce Customized PowerPoint Graphs	Aileen L. Yam	With the advent of Visual Basic for Applications (VBA) and Object Linking and Embedding (OLE), macros can be written to bring wonders to programming. This paper gives simple sample code to exemplify the integration of SAS software and Microsoft Office software to automate the production of customized graphs. During the presentation, a more fully developed application complete with dialog boxes for generating a variety of graphs via option and command buttons will be demonstrated	excel, do loop, conditional do loop	6
40	Integrity Constraints and Audit Trails Working Together	Gary S. Franklin	New features in Version 7 and Version 8 of the SAS System support centralized control of updating. The integrity constraints feature defines rules to be enforced during updates, and the audit trail feature logs every update activity, with enough information to determine which updates failed, if any. When updates fail, data from the audit trail can be used to reconstruct the original updates so they can be successfully reapplied. Using these new features together can substantially reduce the amount of coding required to perform the repair operations	audit trail, dataset, constraint, key, foreign key, proc step, error message, proc sql, proc datasets, data integrity, proc contents	6
41	Managing Independent Consultants - An Oxymoron?	Neil H. Howard, Michelle Gayari	The elements of the validation process, the features and tools of SAS software, and the structure of the Systems Development Life Cycle (SDLC) are indeed compatible. This paper will address: the definitions of verification, validation, testing, and debugging, as well as the structure of the SDLC. It will illustrate how the SAS system can be used to help satisfy the requirements of your SDLC and accomplish the tasks of verification and validation. Since as much as 80% of a programmer's time is invested in testing and validation, it's important to focus on tools that facilitate correction of syntax, data, and logic errors in SAS programs. The presentation focuses on wide variety of SAS features, tips, techniques, tricks, and system tools that can become part of your routine testing methodology	proc step, data cleaning, missing value, sas log, proc print, put statement, proc contents, proc freq, cpu time	10
42	Matched Sampling Using SAS Software	Edgar L. Mounib, Thiru Satchi	A case-control study is an observational study in which subjects are classified according to the presence ('cases') or absence ('controls') of the outcome of interest. These controls can then be matched with cases according to a characteristic(s), to ensure the two groups are comparable for further analysis. However, this matching process can be difficult, time consuming, and costly. Hence, we developed a SAS program to automate the selection of controls, taking into account age, gender, and other user-defined criteria. This program can be adjusted to account for varying case-control ratios, thus affecting the power of the study. It is intended for SAS programmers with a basic understanding of macro programming. Keywords: case-control study, matching, macro, CALL	proc step, proc sort, sample, proc freq, macro variable, macro definition	6
43	Meta-Analysis with Linear and Nonlinear Multilevel Models Using PROC MIXED and PROC NLMIXED	Eugene Komaroff, Russell D. Wolfinger	Meta-analysis is both a theory and a toolbox of statistical techniques for combining summary statistics from similar studies. However, with the notable exception of the FDA New Drug Application, typical studies are not similar. Rather than replicate, they try to extend the generalizability of earlier findings. Consequently, between-studies heterogeneity continues to plague the theory and practice of meta-analysis. This paper uses a study level covariate in a multilevel model for meta-analysis to statistically shrink the between-studies heterogeneity and to estimate an overall treatment effect and confidence interval. The model appears in diverse scientific literature under a variety of names, e.g., mixed, hierarchical, empirical Bayes, and variance components. In SAS , the model is available in `PROC MIXED` for continuous outcome measures and `PROC NLMIXED` for binomial outcome measures	proc mixed, proc step, binomial distribution, estimate, treatment effect, fixed effects, covariance	4
44	Mixed Models Analysis Using JMP Software 4.0	George A. Milliken	The analysis of most designed experiments and observational studies require mixed models. Version 4.0 of JMP Software has greatly expanded its capabilities for analyzing mixed models by including restricted maximum likelihood (REML) methods. This paper will demonstrate the process of analyzing several mixed models using the 4.0 version of JMP. Models examined include randomized complete block designs, incomplete block designs, split plot designs, strip plot designs, and designs with random covariates, where examples are drawn from engineering, medicine and agriculture. Version 4.0 of JMP can fit many of the standard mixed models and the analysis provides estimation of the variance components, estimates of the fixed effect parameters, tests of hypothesis about the fixed effects parameters, appropriate estimated standard errors, confidence intervals about variance components using REML, and least squares means and comparisons	proc mixed, proc calis, restricted maximum likelihood, anova, proc step, least squares mean, likelihood function, fixed effects, main effect	6
45	Optimizing Data Extraction from Oracle Tables	Caroline C. Bahler	The `SAS/ACCESS` product for Oracle offers a fast and easy interface for reading Oracle tables - access views or SQL Pass-Thru facility. However, if your extraction requirements include joining Oracle tables or extracting date ranges then you need to know Oracle's "flavor" of SQL. In addition, efficient use of `SAS/ACCESS` methods may require some knowledge of how the Oracle database was designed and what Oracle operational options are in effect. The objective of this paper is to discuss some of the potential pitfalls and efficiencies when working with `SAS/ACCESS` to extract information from Oracle. This paper assumes the reader is familiar with the `SAS/ACCESS` product and specifically targets `SAS/ACCESS` and Oracle operational and SQL options that can be used to optimize data retrieval. Extracting Data from Oracle ACCESS Views An Access view creates a "road map" to the location of a table and permits data extraction to occur. Access views are created using `PROC ACCESS`	proc sql, create table, proc step, macro variable, variable, dataset, where statement	9
46	PAGECNT: A simple macro to add page numbers to reports	Greg Silva	Most SAS programmers are familiar with the limits of page numbers in SAS when generating reports. The only problem is that most people requesting the reports do not care about any limitations. For this reason a macro has been developed to generate page number in the form: Page x of yy. The macro also allows for customizing the text, as well as allowing the programmer to justify or center the page numbers		3
47	Pharmaceutical Application of SAS Enterprise Miner	Thomas H. Burger	Competitive advantage requires rapid formation of sound inferences for product decisions. As information repositories, warehouses store teradata for decision support. Strategic use of this data requires techniques proven for information delivery. Mining reveals relationships for knowledge formation through methodological data selection, exploration and modeling. A structured process ensures conformance to business assumptions for reliable interpretation. To illustrate, we discuss data mining in pharmaceutical research	hypothesis testing, market basket analysis	4
48	POINT: A useful way to get around your data	Greg Silva	There are times in most SAS programmers' lives when they wish they could move freely around their data, unobstructed by the linear nature of datasets. They feel forced to lag() behind other programmers, never looking forward to their next observation. To these poor unfortunates I present POINT. When used correctly, it provides the flexibility to move through datasets: looking ahead, starting over, jumping into the middle of it	adverse events, set statement	4
49	Producing Special Characters in SAS Output in RTF	Cindy Q. Song	At Merck and other companies, presenting SAS reports in word processor format has become a standard practice. While much effort has been devoted to techniques for automatically converting SAS outputs into word format, little attention has been paid to a method for inserting special characters into reports through SAS. In this paper, I will describe how to produce special characters in SAS output in Rich Text Format for use in any word processor capable of importing RTF	sas output, macro variable	2
50	Random Simulation Methods for Computing Power and Sample Size for Tukey's Trend Test	Benjamin Duncan	Tukey's Trend Test is a simple step-down test for identifying the "No Statistical Significance of Trend" (NOSTASOT) dose [Tukey, Ciminera, and Heyse (1985)]. Obtaining exact power of the experiment and sample size requirements is not always feasible or possible when dealing with this type or other related procedures for handling multiple comparisons. Computer simulations provide a viable alternative to estimate the necessary sample size or power. Methods for obtaining approximate estimates of power and sample size for Tukey's Trend Test are examined. Specifically, the power and sample size to identify the "No Statistical Significance of Trend" (NOSTASOT) dose is approximated using random simulation techniques. A SAS program is developed to carry out these simulations and estimate sample size and power. The techniques presented here are applicable to a variety of step-down tests used to help account for multiplicity	sample size, sample, standard deviation, macro loop, macro definition, correlation, %if-%then-%else	6
51	Reading Multiple and Row Oriented External Files	Fan Xu	In many situations SAS programmers need to deal with special kinds of external files. In this presentation, I discuss two special cases. In one situation, the raw data are stored in many different files under several sub- directories. Without a list of file names, how could these files be read and combined into a SAS data set? In the other case, variables in an external file are stored in rows instead of columns. Is there a way to read external files with row oriented variables in SAS? Techniques are presented to solve these problems. For multiple external files, the SYSTEM function is used to compile a list of file names and FILEVAR option of the INFILE statement is used to read all files. For files with variables in rows, multiple INFILE statements with FIRSTOBS and OBS options are used in a MACRO setting. Key Words Multiple external files, Variables in rows, SYSTEM function, FILEVAR option, FIRSTOBS option, OBS option,	infile statement, dataset	4
52	Reducing Statisticians' Programming Load: Automated Statistical Analysis with SAS and XML TM	Michael C. Palmer	Statisticians often spend more time programming and supervising the programming for tables than they spend on the statistical analyses reported in the tables. Features new in versions 7 and 8 of SAS coupled with XML make it possible to reduce this programming load by automating analysis steps. In the automated system, a statistician prepares table shells and database maps with publishing software that saves both as XML files. SAS programs interpret the XML, retrieve data, and combine the interpreted XML and retrieved data to build XML files. Publishing software renders the XML files to PDF or other formats. The result is that clinical data pass from an analysis data set into a report-quality document without a statistician or programmer writing or setting up table programs or macros. As table content is revised, the system can revise the report- quality tables. Table shells are reusable within a report and across reports	data science, proc tabulate	5
53	Removing Duplicates: PROC SQL Can Help You "See"	Vicki Siemers	Duplication of information within data sets is a common occurrence. Data files may contain duplicate account numbers, telephone numbers, names, etc. A standard/accepted solution for removing duplicates is the NODUPKEY option of `PROC SORT`. Unfortunately, this procedure is often used blindly. The first duplicate observation is kept in the data set while all subsequent occurrences are deleted. But what if the third occurrence should have been kept and the first and second occurrences deleted? `PROC SQL`, a component of Base SAS, can help SAS users investigate duplicates so that a more informed choice can be made when deleting observations. This paper is intended for users with an intermediate SAS programming skill set	proc sql, proc step, proc sort, dataset	2
54	Running Reports Using the PROC Mixed Procedure	Marina V. Kungurtseva	When `PROC MIXED` is used for statistical analyses, the user has to run the procedure multiple times to see which model works best. This SAS Procedure gives many possibilities to working on the mixed model by changing the model itself and also the estimation methods for the covariance parameters as well as the type of covariance structure and other parameters. It takes quite some time to look through all the possibilities and choose the desired one. Additionally the results need to be saved and customized tables need to be generated for final reports. This presentation demonstrates three Macros that will resolve these tasks very quickly and productively. 1) The first Macro runs any model of the user's choice with many different parameters at once and gives a short printout with the description of each run. 2) For the second Macro the user has to specify the final choice of the model. It will generate a SAS data set that can then be used for the table	macro quoting function, dataset, proc mixed, covariance, covariance structure, proc step	8
55	SAS Application for Pharmacokinetic Evaluation and Analysis of the Effect of Treatment with a New Antidepressant Drug in a Population with Major Depression	Lev Sverdlov, John F. Noble, Gabriela Nicolau		clinical data, efficacy summary	8
56	SAS for Analyzing Side-effects of Drugs	Christine Vander Vorst	Monitoring marketed medicines in order to ensure their safe use is the main objective of the pharmacovigilance department of Janssen Pharmaceutica. It presents the added value of an improved safety assurance for patients using its drugs and for the doctors prescribing them. The reporting of Adverse Drug Experiences (ADE) is an important issue for this department and that's where the SAS system helps them a lot. A `SAS/AF` application called SAFIR (SAs For Interactive Reporting) has been developed to offer the users a flexible tool to access, analyse and report their data. With a few mouse clicks they can produce graphs and reports on screen and/or on paper, which facilitates the realisation of their daily tasks. The application provides several different reports and/or graphs that can be generated interactively based on the selections entered by the users. The results can be printed, sent to `EXCEL` or WORD or analysed more in detail using drill down and multidimensional techniques	proc freq, adverse events, data cleaning	3
57	SAS for Statistics; <XML for Output>	Michael C. Palmer	Analysts attracted to SAS for its statistical capabilities no longer have to settle for its clumsy publishing capabilities. Instead, they can take advantage of the Output Delivery System (`ODS`) in version 7.0 or 8.0, SAS's data warehouse and data processing capabilities, and a new open-source, non-proprietary software technology, and literally never use a DATA `_NULL_`, `PROC REPORT`, or `PROC TABULATE` again. An analyst working with publishing software and exploiting its layout and styling flexibility creates a terse sample table. The sample, via SAS programs, directs the retrieval of data from a warehouse and the creation of publishable markup. The publishing software renders the markup publication ready without re-typing, cutting-and-pasting, or format conversion of SAS output. The new, platform-independent software technology is eXtensible Markup Language (XML)	sample, proc tabulate	4
58	SAS version 8 ODS for Drug Safety Reporting (Without Use of HTML)	Rene E. Laurencot	With version 8 of the SAS System, you can use the Output Delivery System (`ODS`) to generate drug safety tables in postscript format. This paper will explore how well suited `ODS` is to enhance or replace existing drug safety reporting methods by examining some examples using `ODS`. We will examine adverse summary tables created with `ODS` and demography summary and listings which utilize `ODS`. We will explore differences in syntax between `ODS` use in `PROC TABULATE` and `ODS` in `PROC REPORT`. We will walk through some examples with `ODS` as an introduction to demonstrate some methods for changing font style, typeface, font size, and other style options	proc tabulate, adverse events, proc report, ods pdf, proc step, txt, proc printto, sashelp, macro loop	6
59	Subject Profiles: (Almost) as easy as 1, 2, 3	Greg Silva	Subject profiles, CRF tabs, patient profiles: whatever you call them, they can be a daunting programming task. This paper will attempt to show that by utilizing a few simple techniques, the programmer can construct complex profiles. By defining the type of data to be presented and using a few constructs, the developer can produce profiles that are not data dependent, and can be used across protocols	set statement, adverse events, concomitant medications	4
60	Symbol Table Generator	James R. Johnson	Have you ever written a lengthy program, printed it, and tried to find where in the program that a particular variable or two were used? Do you remember sitting there with your printout, highlighter, and program editor, repeatedly using the editor's find feature, then trying to locate the reference in the printed copy so you can highlight it? Or, maybe instead of tediously looking for all the references, you simply used the editor's change feature and changed all occurrences of a variable to another spelling. Then when you ran the program you found that you had changed things that you did not expect like TITLE statements, data set names, or keywords. This paper will present a short program that reads a user- provided SAS program and generates a line numbered listing of the program and a symbol table, indicating each variable and keyword in the program and every line number on which it is referenced	symbol table, variable, dataset, proc step, proc sql, title statement, macro facility, macro definition	6
61	SynCoder: A SAS/AF Application for Implementing MedDRA Coding in Clinical Trials	Deborah A. Testa, Russell Holmes	This paper presents SynCoder, a Version 7/8 `SAS/AF` application that implements the new MedDRA international medical terminology for coding adverse events in clinical trials. The presentation will be accompanied by a brief demonstration of three of the application's modules: batch coding using a synonyms data set and a data mart of MedDRA hierarchical terms, an efficient search engine for browsing the hierarchies, and on-line coding of terms requiring human decision making. The application demonstrates the superiority of new features (both in the user interface and in the component technology) in `SAS/AF` software in Version 7 and 8 over earlier versions	data mart, clinical research	2
62	Table Generation Using the PROC REPORT Feature	Edward R. Smith	The `PROC REPORT` procedure is a powerful report generation tool that allows the user to combine many of the capabilities of the SAS system in a single step. The focus of this paper is to introduce the batch version of `PROC REPORT` as a tool for table generation. This paper provides the reader with much of the basic `PROC REPORT` essentials and an introduction to some of the more advanced techniques. It is not meant to be a full	proc step, proc report	6
63	Taking Control and Keeping It: Creating and Using Conditionally Executable SAS Code	Justina M. Flavin	Have you ever wanted to selectively execute chunks of program code? Do you want to leave debugging statements in your program for future debugging sessions while preventing their execution without commenting them manually? Would you like your program to automatically start at a specified time or perhaps delay the start for some period of time? Do you want to have error conditions in one step determine which, if any, of the remaining parts of the program are to be executed? These concepts and others will be discussed in the context of controlling how and when all or a portion of a program runs using conditionally executable SAS code	macro variable, data step, interim analysis, macro facility, proc step, comment, %if-%then-%else, macro function, macro definition	4
64	The Challenges of Looking Across Transaction Data	Sergey Sianissian	The key to running different database marketing programs successfully lies in the manipulation and detailed analysis (mostly using SAS) of the transaction data. Usually those data sets have many records per customer, and the information (date of visits, purchase amount, store of visit, items bought, etc.) disperse among observations.	transaction data, data step, proc sort	3
65	The disadvantages of graphing "LOCF" data and a way of incorporating Discontinuation information graphically using PROC GREPLAY	Sangeeta Bhattacharya	Quite often, in clinical trials to avoid losing valuable information and to preserve the sample size, the last observation recorded for a patient is carried forward for the rest of the observation points("LOCF"). In certain analgesic studies, for example, where the primary efficacy variable is pain, the value at discontinuation can be excessively high and carrying this value forward might mean making the drug look worse than it actually is. Although the decision of being overly conservative or not lies in the analysis plan, when presenting the data graphically, a better approach would be to present a bar graph (with measurement points, intervals of hour on the x-axis and mean pain scores on the y-axis) while superimposing a line graph of the mean pain scores("LOCF") over time. The graph would also show the number of patients discontinuing at each hour interval	proc step, proc greplay, missing value, last observation carried forward	4
66	The Lost Art of Annotate	Richard O. Smith, Arthur L. Carpenter	The ANNOTATE facility is a useful tool that adds to the capabilities of `SAS/GRAPH` and related procedures. We will briefly examine some of the common uses and expound on some of the more advanced uses of annotate	histogram, proc freq	5
67	Trialex System, Information Management via the Web	Sy J. Truong	Clinical information management is a challenging and complex task in an environment of changing regulatory requirements. Rather than adding extra layers of abstraction to bewilder users, this paper will demonstrate the Trialex System which simplifies the process of managing a clinical trial. The Trialex System represents the next generation of information delivery since it goes beyond the client/server model and is deployed completely within the thin client model. This system was developed entirely in `SAS/INTRNET` to deliver an intuitive Web interface for accessibility and ease of use. This paper will also address some of the unique challenges faced when developing within this thin client architecture	data cleaning, audit trail	8
68	Understanding Organizational Resistance - Surrounding Technology Change	Patricia B. Halley	Most technology-adoption projects fail within the first year of their implementation. Millions of dollars are spent acquiring or developing technologies, yet they are never fully institutionalized within an organization. As a solutions provider, PharmaHealth Technologies/Ge4, a business unit of SAS Institute Inc. is very concerned about this problem and practices Technology Change Management (TCM) techniques to minimize the risks associated with implementing technology. TCM is the process of identifying, selecting, and evaluating new technologies and incorporating effective technologies into the organization. One of the major obstacles for successfully implementing technology is the implementers' inability to identify and manage resistance to the changes that the new technology will almost inevitably bring. The purpose of this paper is first to understand that resistance is a natural, human response to change and that resistance will happen		4
69	Using a SAS/IntrNet Data Browsing Application to Generate SAS Code for Stand-alone Reports	Paul M. Gilbert	At DataCeutics, Inc., we have developed a `SAS/INTRNET`-based tool for browsing SAS data and generating listings, summary tables and figures that assist in reviewing clinical trial data. This tool's primary user base is the non-technical clinical scientist. However, we saw an opportunity for the tool's use to be extended to technical users such as statisticians and clinical programmers. To do this we needed the ability to generate the underlying SAS code that created the output and then save the code to a file where the statisticians and clinical programmers could further modify it and execute it in a batch environment. For this to work, we developed a self-contained code generation 'button' that could be easily added to the dynamic `SAS/INTRNET`-generated HTML report generation pages. This paper describes the application, how the code generation functionality was designed and how the code generation button was implemented	macro variable, dataset, macro definition	4
70	Using ODBC and Visual Basic to Connect to SAS from Microsoft Office	Carl R. Haske	In the Windows environment, moving data into word processing and other applications is a basic technique using ODBC. The technique can be made even more powerful using some straightforward Visual Basic scripting. Useful time saving applications can be built quickly and with an introductory knowledge of Visual Basic. This is useful for workflow processes that are highly iterative in a team environment, such as clinical report development. For example, a team consists of document processors and an array of programmers, statisticians, and medical writers. The team members producing the information for the document processors are working with SAS data. Rather than have document processors repeatedly transcribe data into a document through several drafts or database versions, an ODBC publishing system can be established to automate the movement of data from SAS to the target MS Word document	dataset, odbc	5
71	Using SAS DDE and Microsoft Excel to graph Output	Douglas Clark	SAS Dynamic Data Exchange (DDE) can be a valuable tool to graph SAS output in a more user friendly setting. A user can create a graph in `EXCEL` and, by using SAS DDE, can update it as data comes in or new reports are needed. This is useful when a statistician wants to see how their drug is doing against placebo at a given time or to see how well their drug is doing against competitors using observational data. This paper will show how to update these graphs without leaving the SAS system. Computing Environments: NT 4.0 SAS Products: PC SAS 6.12 Other software products: Microsoft `EXCEL` 97	excel, proc step	3
72	Using SAS for the Statistical Analysis of a Bivariate Primary Endpoint in a Clinical Trial of Chronic Fatigue Syndrome (CFS)	Naum M. Khutoryansky, David R. Strayer, William A. Carter	The evaluation of a treatment effect on multiple primary endpoints may be required for some clinical trials (e.g., AIDS, CFS, etc.). This paper is concerned with a statistical analysis of a randomized, double-blinded, placebo-controlled clinical trial of the efficacy and safety of Poly I: Poly C12U (Ampligen) in patients with severely debilitating CFS. The decision rule employed is based on two primary endpoints (the Karnofsky Performance Score and the Exercise Treadmill Test duration) and specifies that the overall significance level is not to exceed 0.05. In addition, two α-levels (α1 and α2) are prescribed requiring that any one of the endpoints be significant at α1-level while the other one at α2-level. The proper values of the α-levels are chosen based on the correlation coefficient value obtained from a previous trial. The statistical analysis is performed in the SAS software framework	data science, clinical trial, primary endpoint, correlation, significance level	3
73	Using SAS Functions in Data Steps	Yue Ye	SAS base software has plenty of built-in functions. Proper use of these functions can save a lot of programming time and effort. In this paper, we will illustrate how to use some of new functions in version 6.12 and later. These new functions include data set functions, variable functions, external file functions, library and catalog functions, and some other special functions. We will concentrate on using these functions in data steps. Quite often, we need to get the information from SAS data sets, libraries or external files in data steps. The conventional way of getting the information is that we first run several SAS procedures, then merge the results with the SAS data set. Using SAS functions directly in `DATA STEP` provides a simple solution in many situations	data step, label statement, dataset, character variable, numeric variable, catalog, catalog entry, libname statement, macro variable, macro function, sas base	5
74	Using SAS Macro to Create Data Driven Format Statement for Clinical Data Flagging	Pilita Canete, Melanie A. Paules, Shi-Tao Yeh	The idea of data flagging is simple enough. It is a process of categorizing the data into ranges based on the study defined significant values. One can use a variety of SAS methods like IF/THEN or SELECT/WHEN to do this grouping. However, these methods entail writing new code everytime values are changed. This paper presents a method of accomplishing data flagging by simply specifying the range(s) of interest into a macro. 'Range of interest' is defined here as limits that are deemed significant for the study population. The limits can be user-defined or can be derived from the data itself. For purposes of this paper, this concept is taken within the clinical scenario. That is the focus is on clinical data flagging based on percentiles. The paper shows a method of flagging the data based on the 5th and 95th percentile whereby values below 5th percentile is flagged as Low, above, 95th as High, and witihin 5th and 95th percentiles as Normal	proc step, proc rank, format statement, proc format, clinical data, macro definition, vital signs, proc sort	5
75	Using SAS Macro to List the Frequencies and Statistics in a Summary Table	Kinwah Fung, Toronto Sunnybrook	A preliminary summary list is crucial in exploring the contents of a data set before conducting any data analysis. This paper presents a SAS Macro generating a list which prints 1) all the variable names of the data set; 2) the categories (formatted or unformatted) of each variable; 3) the frequencies of each category; and 4) the statistics from the `UNIVARIATE` procedure for numeric variables. In clinical trials, the data sets usually compose of observations from several interest groups. The list from this SAS Macro will print the information by the group variable specified by the user. In addition, a total column for the entire group is listed. Not only cutting down the number of printout pages, this SAS Macro also helps the user verifying the validity of the data set	macro definition, numeric variable, proc sql, proc step, macro variable, proc freq, class variable, put statement, proc univariate, macro loop, nominal variable, interval variable, %if-%then-%else	6
76	Using the Annotate Facility for Enhancing Output	Marcia Branham, Timothy Maxwell	Table presentation is an important consideration when programming results for clinical trials. Attention and readability are greatly increased when using annotate to program tables. The flexibility for output is virtually endless. A graphical display of serious adverse event outcomes can be shown using all outcomes. Additionally, a piece of pie can be exploded to emphasize the most severe outcome. Furthermore, a table to the side of the pie could show the characteristics of these patients. The graphical presentation of this data is much more readily understood and comprehended. The annotate facility can accommodate a multitude of useful tools, both simple and very ornate, to enhance graphical display. Simple concepts will be discussed to get you started with the annotate facility	serious adverse event, adverse events, create table, group by, proc sql, proc step	7
77	Using the Host Variable INTO: in PROC SQL	Thiru Satchi	"INTO:" host-variable in `PROC SQL` is a powerful tool. It simplifies programming code while minimizing the risk of typographical errors. SQL INTO: creates one or more macro variables, based on the results of a SELECT statement. This macro variable(s) reflects a list of values that can then be used to manipulate data in both DATA and `PROC` steps. The usefulness of SQL INTO: will be demonstrated by analyzing a large medical claims database. Keywords: INTO:, host-variable, macro, SQL	macro put, proc sql, proc step, macro variable	1
78	Visualize Your Regression Analysis	Fan Xu	Multiple linear regression is a widely used statistical technique in clinical data analysis. A macro is presented in this paper to facilitate the regression analysis with graphics. The macro generates plots of the dependent variable versus every potential independent variable, builds the best regression model according to the user specified criteria, and carries out certain model diagnostics. All relevant statistics are transferred through macro variables with the DATA `_NULL_` step and presented on the plots. The application of the macro is illustrated with an example of a simulated data set. The readers are expected to have a good understanding of the statistical theory of the multiple linear regression analysis and advanced SAS graphic and MACRO knowledge. Key Words Multiple Linear Regression, Macro, Graphics, Output, Data `_NULL_`	regression analysis, predictor variable, macro variable, multiple regression, residual, response variable, correlation, proc reg, outlier, histogram, call symput, normal distribution, macro loop	7
79	Web-enabling Bioanalytic Laboratory Data Loading and QA Processing	James Sun		laboratory data, data governance, sas programmer, clinical data	4
80	XML and SAS: An Advanced Tutorial	Gregory S. Barnes Nelson	One of the goals for SAS applications developers has been to develop three-tier and n-tier applications where the application logic (business rules) is separate from the data, which, in turn, is isolated from the user interface. In a previous paper (Barnes Nelson, 1999)1 we discussed how to implement this logic separation using the SAS Component Language. This paper extends that line of thinking by introducing SAS developers to XML. eXtensible Markup Language, or XML, is a protocol of sorts that can be described as a technique for separating data from its presentation. In this paper, we will discuss XML in the context of SAS applications and how it can be used in the preparation and presentation of data. We will explore some of the features of XML that makes it a good partner for SAS-based applications	dictionary tables, sas programmer	10

Back to Conf go 2001 go 1999

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.