PharmaSUG 2001 Papers - Index

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

#	Title ×	Authors ×	Abstract ×	Keywords ×	Pages
1	%ICS - A SAS Macro to Automate Individual Case Summaries	Doug E. Lassman	This paper describes a SAS macro that has been developed to automate the programming of individual case summaries. Also known as patient profiles or case report form tabulations, individual case summaries are listings of data from a single patient on just a few pages. They are used for regulatory submissions, writing patient narratives or case histories, and data clean up and audit activities. Modeled after `PROC GREPLAY` in `SAS/GRAPH`, output from included code is placed in windows defined on the page. Typically, a complicated DATA `_NULL_` is used which is difficult to write and even more difficult to modify. With this macro, output from common SAS procedures such as PRINT, REPORT, and MEANS, which may already have been written for study listings, can be used for the summary. This macro can have other applications including a laboratory	proc step, proc report, adverse events	8
2	_hitlist Macro - A Tool to Obtain Consistent Results in an Integrated Database	Diane E. Foose, David C. Izard	When using an integrated database to support a submission to the FDA, it is critical for all programs to consistently identify and utilize the same data for analysis of the same patient subgroups. Often many programmers are assigned to perform the programming tasks of this massive effort. The utilization of the variety of programming styles and techniques available within SAS may introduce variations in the patient populations identified, thereby creating the possibility of erroneous results. This paper will present the concept of using a SAS macro as an easy-to-use solution to this problem. Considerations for how to design and use this "develop once, utilize many" strategy for patient population identification and reporting within your own environment will be discussed. An implementation of this concept, the macro %_hitlist, will also be presented	master data management, %if-%then-%else	4
3	A Bit More on Job Security: Long Names and Other V8 Tips	Arthur L. Carpenter, Tony Payne	With the advent of the Nashville releases of the SAS System (Versions 7 and 8), a number of new opportunities have been added to the toolboxes of Job Security afficionados. In previous presentations and papers (Carpenter, 1993; Carpenter and Payne, 1998) a series of tips and techniques have been foisted on the unsuspecting SAS user community with the objective of increasing the job security of SAS programmers by making them indispensable to their bosses. The list of tips continues to grow. And now with the added features of the Nashville releases, the list is greatly expanded. One area of special interest for job security specialists has revolved around the naming of variables and data sets. Now with the relaxed restrictions for SAS names comes a large number of both challenges and opportunities. New system options and the advent of the Output Delivery System, `ODS`, also provide a number of techniques that will surely become favorites in the future. Of course new tips and techniques for all releases are constantly being uncovered, and a number of these are also included. Become a Job Security Advocate.	job security, proc step, dataset, proc format, constraint, proc sort, %if-%then-%else, proc sql	6
4	A Comparison of Cross-Database Access Techniques Using SAS with SAS/ACCESS Version 6.12 and SAS with SAS/ACCESS Version 8.1	Karen Glenn	SAS has been and remains the industry standard for pharmaceutical data analysis, yet frequently these data reside in database products other than SAS such as Microsoft SQL, Microsoft Access or dBASE. The `SAS/ACCESS` Version 6 generation software provided useful tools to access such data, and now the Version 8 generation brings tremendous simplicity and flexibility to data access making cross-database access nearly invisible. Under Version 6 many lines of code were required to read in outside data sources. In addition, as SAS variable names were limited to a length of 8, longer variable names were truncated and numbered to insure short but unique names. These translated variable names could complicate communication between statisticians and database owners. In Version 8.1, the process is executed simply through specific access engines in the `LIBNAME` statement. The increased length of variable names in Version 8 also results in fewer if any renamed variables in SAS	proc sql, dataset	2
5	A Data Null Reporting Method	Frank Senk	Even with SAS procedures getting better every release, there are still good reasons for doing DATA NULL reporting. Some advantages are: /Gb7 Gaining complete control of the output page /Gb7 Delivering output variations based on by groups /Gb7 Flexibility in reporting character and numeric data /Gb7 Ability to design macros that simplify difficult reports This paper demonstrates a DATA NULL reporting method following the step-wise approach as specified below: 1. Design the report 2. Build a report matrix data set to ensure completeness 3. Define variable relationships 4. Use `PROC UNIVARIATE` for summary statistics 5. Use `PROC FREQ` for counts 6. Calculate percents and format cells 7. Use `PROC TRANSPOSE` 8. Use macro variables to assign column widths 9. Use macros to position variables within columns 10. Use DATA NULL to produce report	macro variable, proc step, proc freq, proc means	6
6	A Method to Import, Process, and Export Arbitrary XML Files with SAS	Michael C. Palmer, Cecilia A. Hale	The release of the FDA and industry-supported CDISC XML clinical data standard will make SAS s XML capabilities increasingly important. XML-formatted data are text with the hierarchical, tagged structure of markup languages, not the row and column style of SAS datasets. SAS has some experimental XML capabilities but it cannot import, process, and export arbitrary XML vocabularies as XML. This paper presents a method to import, process, and export arbitrary, data-centric XML files. The method consists of an indexing algorithm, construction of a canonical instance, and processing of populated instances. Populated instances are put into a canonical form, and the algorithm is applied. The resulting indexed instance is pruned to just records that contain data and stored as a SAS dataset with the index as a key, shorn of the markup structure that is hard to work with in SAS. The pruned instance can be mapped into SAS datasets and processed with the index, preserving the XML structure.	flat file, clinical data, pharmaceutical industry, dataset, sample, cdisc	4
7	A SAS Macro for Evaluating Whether All, Any, or None of the Variables in a List Have Been Marked - Application for Clinical Data Validation	Arthur Collins	For those of us utilizing SAS-based data management systems, a common and repetitive validation task is to evaluate the response to "Mark all that apply" field lists. This is a task which can benefit greatly by application of the SAS Macro Facility. The macro that will be presented, is simple and intuitive to apply to variable lists of all sizes and formats. This is one more tool to add to the tool box which will create efficiencies as well as reduce error. The macro call simply passes the variable list and the value (or values) to be checked for, and returns information about how many of the fields contain the values	data cleaning, macro definition	2
8	A Wildcard Character for Variable Lists	Malachy J. Foley	A very simple and powerful, yet relatively unknown, programming technique is the use of a wildcard character in variable lists. The wildcard is the colon. This paper shows how to use the technique to reduce programming time, errors and drudgery. Key Words : variable lists, wildcard character, productivity, colon wildcard character	variable list, put statement, proc step, drop statement, sas function, proc contents, proc print	4
9	Adopting e-Strategy for Information Delivery	Thomas H. Burger, John M. LaBore	Unprecedented technological advances have redefined business strategy. Globalization, e-commerce and accelerated R&D have increased industry reliance on Information Technology (IT). This requires acute recognition of business needs and an architecture providing enterprise-wide business solutions. Competitive advantage will be held by those adopting strategic technologies tightly integrated with the business. We discuss	business intelligence, data governance	4
10	An Analysis Programming Process Focused on Data Derivation	Lee Walke	SAS Programming for clinical trials has traditionally focused on the production of summary tables and listings. These elements frequently represent data that is derived from the clinical trial source data. Though clinical trials source data are subjected to rigorous validation and scrutiny, derived data may not be. This paper will present a programming process that places the highest level of effort on the production of accurate derived data. The process includes a method for defining derivations within a metadata repository. This repository acts as a tool for storing data definitions, and also promotes compliance with the FDA guidelines for electronic submissions. The strict separation of derivation and summary programming allows for robust, task- guided validation. With this separation established, a discussion of modern development lifecycles is possible	raw data, clinical trial, data dictionary, proc step, sas programming, proc freq	4
11	An Application of Continual Reassessment Method Using SAS System	Naoki Ishizuka	The Bayesian technique, Continual Reassessment Method (CRM), introduced by O 'Quigley et al. (1990) is a new design for phase I trials in cancer. The goal of this design is to reduce the number of patients who receive lower doses, which are not expected to be effective, and to obtain a more accurate estimate of the maximum tolerated dose (MTD). The CRM has a couple of attractive characters, which can not be expected with the traditional three-cohort design. The allocated dose level to be administrated is determined when the dose-response model has been updated with observed responses. So that, numerical integration and graphical presentation for the probability of the density function are important in practice. The combination usage of QUAD call of `SAS/IML` and `PROC GPLOT` of `SAS/GRAPH` is a powerful tool	dose, prior probability, clinical trial, phase i, posterior probability, likelihood function, proc step	4
12	Applying Statistical Sampling Plans To Data Entry Procedures To Increase Data Quality	Roderick Lashley	Double data entry is a widely used method to enhance the quality of clinical trials data entered into the computer from paper case report forms. King and Lashley [1] proposed an alternative procedure using single data entry and a procedure known in the statistical quality control literature as a continuous sampling plan. This paper will investigate applying this procedure to data where the entry errors are not randomly distributed, but occur in bursts. Empirical results for the cost to perform the procedure as well as computations for the gain in data quality will be presented	clinical trial, sample	4
13	Automate and Customize Printing of SAS Output in UNIX	Cailiang Mao	During project development, tabulations, listings and tables are often requested to be printed out for review. It may involve several dozens to over hundreds of files depending on the size of the study. Using UNIX print command with the wild card `FILENAME` often results in pages that are not separated cleanly. Using a `FILENAME` statement with pipe device type, a macro is developed to print all files or to selectively print a subset of all files in a directory at once with clean output. The PRINTER parameter of the macro allows the user to direct output to the desired printer. In addition, the macro allows the user to customize printing by printing pages selectively, such as the first n pages of file(s) or any desired pages in the middle of a file. So the Macro provides both efficiency, especially for large study, and flexibility	sas output, sas programmer	2
14	Automatic Estimation of Dixon's Test for Extreme Values Using a SAS Macro Driven Program	Don (Dongguang) Li, Edmond Edwards	Dixon's test[1,2] for extreme values is a convenient method to statistically determine outliers from continuous data. Based on Dixon's simple algorithms, this paper describes a way of automatically estimating outlying values conditionally from the parameters of bioequivalence study data using a SAS macro driven program. The key points of programming strategy are listed and the model result is shown in the paper. This program might be an example that how to use SAS to handle the user defined conditional calculations and logical comparisons.	macro definition, outlier	4
15	Can standards be implemented effectively without compromising science?	Amy Morris, Blue Bell	Development of standard software tools in environments where standards do not commonly exist is a frequently encountered problem, especially in scientific fields. This paper discusses the development of standard tools for statistical analysis and reporting within a Clinical Biostatistics department. The challenges and proposed solutions of implementing standards without compromising scientific innovation and practice, versus the rewards of using such tools, are reviewed. Concepts are discussed with respect to standard data set structures and the implementation of SAS macros to improve efficiencies	macro definition, data science, data cleaning	4
16	Clinical Data Warehouse Development with Base SAS Software and Common Desktop Tools	Patricia L. Gerend	By focusing on the information needed by customers, it is possible to develop an effective clinical data warehouse using tools that already exist on a typical clinical programmer's desktop. The common tools base SAS, SAS macro language, `SAS/FSP`, UNIX, Microsoft Word, and file transfer protocol (FTP) can be harnessed to implement dependencies, scheduling, metadata dictionaries, documentation, and data mart generation	sas base, data warehouse, clinical data, clinical trial, macro facility	10
17	Communicating Data Effectively with e-Data and e-Notes	Sy J. Truong	Wouldn't it be nice to share SAS data with anyone in the world even if they don't have SAS? Delivering and communicating information pertaining to SAS data across the Internet can be a challenge. The data may be too large to be delivered across slow modem connections. Even if the data were successfully compressed and sent via email, it is difficult to discuss and view the details of the data if team members have different ways of browsing the data. This paper will explore the use of two new tools, e-Data and e-Notes, which combine the ability to view SAS data and conduct discussions over the Internet. These tools are available over the Internet and do not require SAS to view data, so they are ideal for delivering data to large audiences. They have features similar to SAS System Viewer which enables quick access and search capabilities of SAS data. e-Notes combines Internet	audit trail, relational database	8
18	Compass: a web interface to a Data Warehouse for Pharmaceutical Decision Support	Christine Vander Vorst	The system that will be demonstrated needs to collect information from different legacy systems and structure them in such a way that on-line analytical processing and scenario handling can be done easily from any JRF location. To satisfy these requirements, a data warehouse has been built to capture all the information; the Web technology will make the data available for analysis. This presentation will explain how this whole system has been developed and what the ambitions and risks were. During the demo you will get a glance of the functionality and the nice look and feel of the user interface. Finally we will give you an overview of the SAS tools used to realize this challenging project	clinical trial, data standard	2
19	Complex Macros v. Simple Programs: Resolving the Conflict	John K. Troxell	Statisticians at Pharmaceutical companies and at the FDA find it difficult to interpret programs containing macros. On the other hand, the need for programming efficiency and quality drives us toward using macros. How can we resolve this conflict? Currently, the typical programming approach is to write programs that call macros. This paper proposes an alternative: use macros to write programs. Macros can write `SAS/GE2` programs that are macro-free, easier for statisticians to review, can be used to do the analysis, and can be submitted to the FDA. No macros need be part of the submission. Programming efficiency and quality are maintained, since programmers are free to continue to use complex, validated macros. There is, however, an important caveat: if the macro has data-dependent branching, it must be re-run whenever the data is updated in order to guarantee synchronization. Pros and cons of three possible ways to implement this idea are discussed	put statement, macro definition	2
20	Converting CP World Application to SAS V8: A Discussion of Issues and Hurdles Encountered	Fang Dong	The CP World reporting system is a SAS-based multi-platform application that runs on a Windows NT Server and a Unix host. It makes extensive use of Base SAS, SAS Macros, `SAS/ACCESS`, `SAS/CONNECT` and SAS Output Delivery System. It is used to report early phase clinical trial data at the Ann Arbor Laboratories of Pfizer Global Research and Development. The system design and features are originally presented in SUGI 25. In converting the CP World application into SAS V8, our primary goal is to take advantage of the new Output Delivery System features. A secondary goal is to simplify SAS coding by taking advantage of long character variable values and explore assigning `LIBNAME` to oracle database versus use SQL Passthrough to extract data from oracle database. The strategy we used is a two-step approach. The first step is to migrate the application into SAS V8. The second step is to explore the new features in V8 such as the `ODS`, assigning `LIBNAME` to Oracle database and long character variable values. This paper discusses the issues and hurdles that we encountered converting the application into SAS V8.	oracle, excel, output delivery system, clinical data, clinical trial, macro variable, proc sql, sas base	4
21	Creating PDF Documents including Links, Bookmarks and a Table of Contents with the SAS Software	Lex Jansen	At the Pharmaceutical Company NV Organon clinical studies are performed and using the SAS system statistical appendices are created. These appendices usually contain huge amounts of listings, tables, analyses and graphs and are part of electronic submissions. Nowadays the Adobe Portable Document Format (PDF) is the standard document format. This format can be read on different platforms and includes objects to easily navigate by using bookmarks and hyperlinks. In this way even large documents are very accessible. This paper describes 2 SAS macros that combine various types of SAS output into PDF files, containing hyperlinks, bookmarks and a table of contents. First, the SAS macro %_SAS2PS combines all SAS output into one big Postscript file. This postscript file contains all SAS output, including a table of contents and so-called PDFmark operators. Then the macro %_PS2PDF will send this postscript file through Acrobat Distiller , resulting in a PDF file that contains a table of contents, bookmarks and hyperlinks.	sas output, macro definition, proc step, proc means	10
22	Data Visualization of Phase 1 Clinical Studies - "Big Al's World" or Using SAS Version 8 to Acquire Quality Ice Cream	Richard F. Synowiec	Data visualization via graphs, colorful tables and the Web can accelerate and simplify the review of data from Phase 1 clinical studies. The Output Delivery System (`ODS`) capability contained within Version 8 of the SAS system provides the means by which data visualization can be achieved quickly and cost effectively. Pfizer Global Research and Development Ann Arbor Laboratories' Phase 1 data visualization utility ("Big Al's World") is an application that runs on Windows NT workstations and uses a Unix host. This application makes extensive use of base SAS, SAS Graph, the `REPORT` procedure, SAS macro language and the new `ODS` capability. Output from this system's execution is stored in html files on a shared server that is accessed via the Pfizer Intranet by interested clients (physicians, clinical scientists, study coordinators, and medical writers)	adverse events, clinical trial, proc step, proc report, phase i, vital signs, output delivery system, study day, data visualization, proc freq	8
23	Detecting Anomalies in Your Data Using Benford's Law	Curtis A. Smith	Analyzing large amounts of data looking for anomalies can be a disheartening task. You need techniques that will allow you to quickly assess the data in ways that will highlight potential anomalies while keeping you from chasing the wind. Benford's Law is one such technique. Using Benford's Law and SAS Software you can quickly identify one or more first digit patterns that defy statistical averages. Within this paper, the author will present SAS code that will enable you to quickly and easily find anomalies in the data you analyze. The SAS code will include the `DATA STEP`, the `MERGE` statement, and the FREQ, REPORT, and `GPLOT` procedures. The author will also present some findings from the data he analyzes. The technique presented is powerful, yet easy to understand and use.	proc freq, data step	4
24	Developing a SAS Macro Library to Create Standard Clinical Data Summary Reports	Chad W. Melson, James T. Decker	A macro library to produce standard summary reports is being developed in SAS Version 8.1 at Procter and Gamble Pharmaceuticals (P&GP) for use with a new clinical database management system. A key objective of this project is to develop macros that maximize the range of outputs that can be produced while minimizing the complexity of the code to be maintained. Each macro in the library produces summary statistics using SAS procedures and formats the output using a vendor macro system, developed by DZS Computer Solutions, Inc., corresponding to a functional report specification. Users reference a library of specification documents and other documentation showing sample outputs to select report formats. This paper includes discussion of the following topics: characteristics of the functional specifications and other documentation, sample macro calls and outputs illustrating report template control capabilities, test and validation processes, and expected future system enhancements	adverse events, data cleaning, macro call, proc means, raw data, clinical data, ods rtf, proc step, dataset, sample	10
25	Developing Clinical Data Management Systems using Version 8.1 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, audit trail, constraint, dataset, sas log, catalog entry, proc step, clinical trial	10
26	Digging for Gold: SAS Tools for Extracting Clinical Study Information from Oracle Clinical	Nancy Brucken	Back in the "old" days, information such as study titles, locations of commonly collected fields and treatment group labels was hard-coded into SAS programs written to summarize data for a single clinical study. During the process of developing standard cross-therapy area reports to summarize data for any clinical study, we found that retrieving this information directly from the database allowed for much more flexibility in coding the programs and reusability across multiple studies. This paper demonstrates tools we have developed using SQL and the SAS `SQL` procedure to extract study titles, view creation dates, the names of the views containing specific questions, treatment group labels and treatment group print order, and other items.	macro variable, macro definition, proc sql, clinical trial, proc step, data cleaning	4
27	Electronic Clinical Study Reports (e-CSR) using ODS in SAS V8e	Hiroshi Otsu, Tadayuki Kitagawa	As for clinical study reports in Japan, it is common to hand over SAS OUTPUT to another tool to create cosmetic tables. For example, using DDE function is one of the popular methods. Although this method had the merit in which the layout of tables can be corrected easily, the validation of this process should be carried out on the two applications, which is a time consuming work. Then, "KANSAI PROJECT", which comprises members of five pharmaceutical companies, has created the pilot system (Template creation) with SAS. The backgrounds of development, the created broad view are reported	proc step, clinical trial, csr	4
28	Energizing End Users with a Slice of SAS and a Cup of Java	Randy Curnutt, Michael J. Pell, John M. LaBore	Many corporate information systems have evolved to integrate a diverse mixture of hardware platforms. Although commonplace, the mainframe has been joined by a plethora of UNIX and NT servers as well as an army of personal computers often connected by Local Area Networks (LAN) or Wide Area Networks (WAN). Further, software tools in this environment are diverse. Users now wish to analyze their mainframe data with PC and UNIX tools in addition to using mainframe tools. It is often necessary to migrate data to new platforms because some tools require local data access. Users may become intimidated and stymied by the prospect of finding an easy and reliable method for moving mainframe data to remote platforms. We explore how the flexibility of SAS system architecture, combined with Java programming capabilities, provides instant access in an easy-to- use tool for point-and-click data migration and conversion (OS/390 SAS, DB2 views, Oracle views) to a PC or UNIX/NT servers	proc step, dataset, delimited file, proc download, raw data, proc sql, excel	6
29	Enhancing Code with the SQL Procedure	Jeff Goodrich	This paper will illustrate ways to enhance your code with SQL. We will compare the `SQL` Procedure versus the base SAS statements necessary to produce summary information. A step by step approach will be used to compare code from both techniques, which produce equivalent results	adverse events, group by, proc sql, sas base, proc step, create table, proc freq	6
30	ESUB11, an Application to Automate the Production of Item 11 For NDA Electronic Submissions	Margaret Hung	ESUB11 is an application written in Visual Basic and SAS to create the Item 11 package for electronic submission (eSUB). This paper summarizes the requirements for Item 11 of eSUB, demonstrates how this application creates all the required pieces, and shows how it has changed the process of electronic submission at GlaxoSmithKline	annotated crf, dataset, cdisc	8
31	FDA Reviewers as Ultimate End Users: Using the SAS System to Construct e-Submissions that Actually Facilitate the NDA / BLA Review Process	Rich Vachal	Building effective electronic regulatory submissions requires that critical focus be placed on the functional needs and workflows of the end users. Since FDA Reviewers spend a large portion of their time seeking to verify and reproduce key efficacy and safety analyses, any extra efforts taken to ensure clarity of statistical programming and stable re-use of programs are likely to pay important dividends in terms of both facilitating the overall review process and expediting an approval decision. This paper addresses these key features of the e-submission development process using a software life-cycle model approach. Emphasis is placed on the structure and packaging of CSR tables and figures programs for immediate re-use by Reviewers. The discussion also covers dataset and data definition table design issues and Agency guidelines for integrating these into the submission dossier. Future directions including an impending role for XML in the electronic submission process are discussed	regulatory submission, clinical trial, clinical research, sas programmer, data cleaning, clinical data, data science	6
32	Fitting Generalized Additive Models with the GAM Procedure	Dong Xiang	This paper describes the use of the GAM proce- dure for fitting generalized additive models (Hastie and Tibshirani, 1990). `PROC GAM`, production in Re- lease 8.2, provides an array of powerful tools for data analysis, incorporating nonparametric regression and smoothing techniques as well as generalized distribu- tional modeling. Compared with other regression pro- cedures such as `PROC REG` and `PROC GLM`, the methodology behind `PROC GAM` relaxes the usual assumption of linearity, enabling you to uncover hid- den structure in the relationship between the indepen- dent variables and the dependent variable. Moreover, you can use `PROC GAM` to model not only Gaussian data, but also data from binary, Poisson, and other non-Gaussian distributions	proc step, proc gam, regression analysis, response variable, binomial distribution, logistic distribution, poisson distribution, proc reg, proc genmod, predictor variable, logistic regression	8
33	Fitting Gompertz Nonlinear Mixed Model to Infancy Growth Data with SAS version 8 Procedure NLMIXED	Cindy Q. Song, Olga M. Kuznetsova	Nonlinear mixed models are an attractive way to describe longitudinal infancy growth data. SAS 8 `PROCEDURE NLMIXED` [1] provides an easy way to fit the infancy growth data with a non-linear mixed model. In this paper, the longitudinal length measurements on 113 boys and 85 girls taken between 0 and 8 months of age were fit with a mixed Gompertz model using SAS `PROC NLMIXED`. The model was built starting with fitting the individual curves using `PROC NLIN` [2]. Then, the non-linear mixed models with one, two, and three random effects were fit to the data using `PROC NLMIXED`. The performance of `PROC NLMIXED` was excellent - good convergence was achieved for all models. Easy ways to output predicted individual growth and velocity curves, as well as population curves, and estimate additional parameters, make the procedure convenient to work with. KEY WORDS: `PROC NLMIXED`, non-linear mixed growth model, Gompertz growth model, relative growth rate, infancy growth velocity	proc mixed, estimate, proc step, correlation, fixed effects, proc nlin, confidence interval, covariance	8
34	From SAS ASCII Output to Word Document - A SAS Macro Approach	Jianlin (Jay) Zhou	Generating SAS ASCII output directly with `PROC REPORT` or a DATA `_NULL_` step is the most common method used by SAS programmers in the pharmaceutical industry. However, because of the many limitations of SAS ASCII files for presentation and handling, more and more medical writers, biostatisticians, publishers, and expert reviewers now request SAS reports in Word document format. This paper introduces a macro that provides a process to produce aesthetically improved Word documents with very limited programming effort. The macro was designed to expand the presentation capability of ASCII files, to accommodate various fonts, font sizes, and margins, to add one of eighteen pagination styles to the final output, and to provide users with an option to compile individual files into one file for easy handling. The macro also automates the process of previewing, saving in either Word document or RTF format, and closing by interfacing with MS Word	txt, footnote statement, macro definition, csr, proc report, clinical trial, proc step, excel, sas output	4
35	Have You Ever Wished That You Do Not Need to Type or Change Report Numbers and Titles in Your SAS Programs?	Aileen L. Yam	In clinical research, the table of contents in a statistical analysis plan is an evolving document. The table of contents contains a list of tables, listings, appendices and figures that are referred to as reports in this paper. The report numbers and titles are subject to change when analysis requirements change. As a result, programmers need to renumber reports and retype titles in the SAS programs from time to time. This paper describes a programmatic approach of retrieving the report numbers and titles from a common source file. The common source file serves a dual purpose of generating a table of contents in a Microsoft Word document and outputting a SAS data set with report numbers and titles. Statisticians can incorporate the Word document as table of contents in a statistical analysis plan. Programmers can create macro variables from the SAS data set for use as titles in reports. During presentation, a demonstration will be given to show how you can make your wish come true	excel, dataset, macro variable, macro definition, data science	6
36	Imputation Techniques Using SAS Software For Incomplete Data In Diabetes Clinical Trials	Naum M. Khutoryansky, Won-Chin Huang	Missing data are common in clinical trials. In longitudinal studies missing data are mostly related to drop-outs. Some drop-outs appear completely at random. The source for other drop-outs is withdrawal from trials due to lack of efficacy. For the latter case the standard analysis of the actual observed data produces bias. An attractive approach to avoid this problem is to impute (i.e. fill in) the missing data. This paper is devoted to comparison of different techniques of imputation for some longitudinal clinical trials with large percentage of dropouts. The techniques being considered include (among others) the last observation carried forward technique, the multiple imputation methods (presented in `PROC MI` of the SAS version 8.1) and new incremental methods programmed in the SAS software framework. The imputation methods were compared on simulated data (to assess preciseness). The most effective techniques were applied to diabetes clinical trial data	imputation, missing value, clinical trial, standard deviation, multiple imputation, regression analysis, sample, proc mi, last observation carried forward, longitudinal data, propensity score, proc step, markov chain, monte carlo	4
37	Integrating SAS/Connect with Java	Randy Curnutt, Michael J. Pell, John M. LaBore	`SAS/CONNECT` provides an easy and reliable method for connecting remote hosts and executing SAS commands on the remote environment. This paper explores the use of `SAS/CONNECT` in conjunction with the robust Java language. Various methods of integration with `SAS/CONNECT` will be reviewed, including dynamic program generation to create and run a web-based application, and the dynamic generation and execution of `SAS/CONNECT` programs to be submitted and executed on remote systems, such as OS/390 mainframes, Unix servers, and NT servers. The following will discuss the advantages and disadvantages of each approach	sas log, create table, proc printto, proc step, macro definition	10
38	Leveraging Existing SAS Programs for Wireless Delivery	Deborah A. Testa, Russell Holmes	Last year during the opening session of SUGI 25, Dr. Goodnight introduced the SAS user community to the potential for using SAS programs to deliver information to handheld devices over a wireless network. Several papers and presentations in SUGI's demo area that same year elaborated on what Dr. Goodnight introduced by going into the details of Palm computing and WAP protocol specifications and requirements. Since that time, wireless devices have proliferated in the U.S., increasing the value of a SAS IntrNet server as a wireless information delivery mechanism. In addition to the Palm VII, there are also WAP telephones and Pocket PC's. The Bluetooth protocol will make these and other new devices more valuable and more ubiquitous. Each of these platforms has its strengths and weaknesses. SAS programs can be written to run on the server and then deliver output to some or all of these platforms so that your users can choose whichever device fits their needs	randomization, clinical trial, adverse events, sample	3
39	Library and File Management: Building a Dynamic Application	Arthur L. Carpenter	In order for a SAS application to be dynamic, it must be able to automatically find the programs that make it work and the data that it is to work against. It must know where to write its output and where to store any new data sets that it creates. More importantly it must do these things without intervention on the part of the user. Even more importantly the application must not confuse the components of one project or task with those of another. The structure and organization of the libraries and directories is central to this ability. Dynamic applications are written to be portable across projects and a key component of the application must necessarily be the structure and location of appropriate files and libraries. While many different styles of organization are possible, a high degree of organization is required. Of course you will need to know what type and how much structure is required for your projects	macro variable, macro definition, stored macro, autocall macro, macro facility	8
40	Loading Oracle Clinical studies using SAS methodology	Curtis Wolf, Steven Light	Oracle Clinical (OC) is becoming a major player in the pharmaceutical industry, as a tool for clinical data management. As it becomes more widely utilized, migrating data into Oracle Clinical from SAS-based legacy systems presents a significant challenge for data management programmers to resolve. This paper discusses two different approaches to the Oracle Clinical batch load process and the upfront work that can make the migration process a whole lot easier. The topics of this paper include developing a study conversion plan, preparing preload data, using the Oracle Clinical metadata to ensure accuracy, quality control of preload data, conversion of preload data to a load file format, and the actual Oracle Clinical load process	dataset, data cleaning, txt, sas programming	2
41	Macros with Global Vision: Using The SAS Dictionary Tables to Create Tools	Michael E. Tomb, James R. Carter	The SAS Dictionary Tables are views of continually updated data describing the current SAS session. In this poster we provide examples of taking this valuable resource of metadata and putting it to work. Each of the three macros presented here automates a solution that involves multiple SAS datasets and libraries. The first illustrates how to instantly compare all like-named datasets within two libraries based on date and a set of ID variables. The second is a simple character "word" search and replace routine that crawls across datasets and libraries. The last macro system reports tabular observation counts of all levels of ID variables after sweeping through every dataset and library that is desired. It can be used, for example, to streamline the process of tracking missing CRF pages within Clinical Trial data	proc step, call execute, dataset, character variable, %if-%then-%else, proc sql, dictionary tables	8
42	Multiple Column Transposition	Solomon Lee		proc transpose, proc step	4
43	New Visualization in V8.2	Himesh Patel	Looking for a pain-free way to combine tables and graphs on the same page? Well, the search is over - with the new `ODS RTF` option, combining graphics and tables is easy. We did not quit there, now you can also print your client-side graphs and tables using the new `ODS` PRINTER option. Along with the enhancements we have made to `ODS`, we have added several new options to the existing `SAS/GRAPH` procedures. This paper also highlights several new visualizations that are part of the solution based SAS products such as WebHound	proc step, bar chart, time series analysis, sample, ods pdf, ods rtf	8
44	Nonlinear Least Squares Analysis of HIV Viral Load Data - Aids in Parameter Estimation	Peter P. Gaccione		proc nlin, proc step, estimate, proc append, proc mixed, proc freq, macro definition, regression analysis	8
45	Open a Window and Lock the Door A User Friendly Application That Maintains Validation Integrity	Brian C. Shilling	In many situations, SAS Programmers create, write and validate programs that are to be used by other departments. In most of these cases, the programs have to be dynamic enough to be able to handle all of the different constraints and subsets set forth by the user. Due to this need, often times non-SAS users are accessing validated code to add or remove macro variables that allow for this subsetting. In the wake lies an invalid program, and the integrity of the program is then breached. This presentation will offer a simple programming solution to this problem, implementing the use of pop-up user windows that allow the user to enter information for the subsetting of data, without actually changing the SAS code in the program. With the use of the WINDOW and DISPLAY statements, and a host of interesting and fun options, a SAS program turns into a controlled, locked and validated piece of code that is both easily usable by users and easily maintainable by the author	data step, macro variable, macro loop, macro definition, %if-%then-%else, proc step	8
46	P-Value Calculation Made Easy with the SAS Call Execute Routine	Huanhong Xia	In many situations we need to compare the counts of an event in two populations to see if the populations differ statistically in terms of the event. The Chi-square procedure or Fisher's exact method are usually used to generate p-values for assessing the difference. It's an easy task to perform when there are only a couple of events under consideration. However, if the number of events increase to hundreds, like adverse events in clinical trials, we want the work to be done in an automatic way. This paper presents a simple SAS macro %p_comp to perform the p-value calculations. Key Words : SAS macro, P-value, call execute, Chi-square test, Fisher's Exact test	fisher exact test, chi-square test, exact test, call execute	4
47	Point and Click Web Pages with Design-Time Controls and SAS/IntrNet	Vincent DelGobbo	SAS Design-Time Controls (DTCs) are a powerful and exciting addition to SAS Web Technologies. These add-in software components integrate back-end SAS software functionality with your desktop HTML editor. You can now create Web pages that contain SAS content in a WYSWIG, point-and-click fashion using any one of several popular HTML editors. In most cases, you do not have to write a single line of code	dataset, output delivery system	8
48	Power and Sample Size Determination for Linear Models	John M. Castelloe	This presentation describes the steps involved in per- forming sample size analyses for a variety of linear models, both univariate and multivariate. As an an- alyst you must gather and synthesize the information needed, but you should be able to rely on the ana- lytical tools to accommodate the numerous ways in which you can characterize and solve problems. Ex- amples illustrate these principles and review relevant	sample size, sample, correlation, anova, proc genmod, regression analysis, power analysis, proc mixed, standard deviation, covariance, multiple regression, partial correlation, fixed effects, proc reg, null hypothesis, one-way anova, primary endpoint	14
49	Pre-requisite to Effective Validation: Evaluating Your Clinical Trials Software Development Environment Using SEI's Capability Maturity Model for Software	David C. Izard	In order to perform effective validation of a computer system you need to incorporate a well-defined software development process into your business model. The development process cannot stand on it own; certain organizational processes and structures must be in place to support the development of validated software. The Software Engineering Institute's Capability Maturity Model for Software offers guidance on incremental steps a software development organization can take to evolve as an entity capable of producing high quality products that meet or exceed the FDA's requirement for the use of validated computer systems in the analysis and reporting of clinical trial results. This paper will focus on the aspects of the Capability Maturity Model for Software leading up to and surrounding the effective implementation and use of a software development life cycle. Practical examples of their use in a clinical trials environment are offered	data cleaning, clinical trial, quality assurance	8
50	Programming Squared (Writing Programs that Write Programs)	Jim Johnson	This paper will demonstrate several techniques using Base SAS and macros that will take your programming skills to a new level by giving you the power to write programs that write programs. These simple techniques, which are powerful used alone, are awesome when combined. Using these techniques when your application is appropriate, you can write one program that will act as though you wrote dozens of individual programs. These programming techniques will give you the ability to write more robust, highly flexible, intelligent programs that can extract data from little known sources, make decisions, write and execute program code depending less on user input. Programs using these techniques are more difficult to debug, but once validated, can be used over and over again by many projects. Although the techniques are simple, this paper is aimed at experienced programmers who know when it would be appropriate and efficient to use them	proc print, macro variable, proc step, dictionary tables, proc sql, macro definition, data step, flat file, data cleaning, macro loop, %if-%then-%else	6
51	Reducing Bias in a Propensity Score Matched-Pair Sample Using Greedy Matching Techniques	Lori S. Parsons	Matching members of a treatment group (cases) to members of a no treatment group (controls) is often used in observational studies to reduce bias and approximate a randomized trial. There is often a trade-off when matching cases to controls and two types of bias can be introduced. While trying to maximize exact matches, cases may be excluded due to incomplete matching. While trying to maximize cases, inexact matching may result. Bias is introduced by both incomplete matching and inexact matching. Propensity scores are being used in observational studies to reduce bias. It has been shown that matching on a propensity score can result in similar matched populations. This paper will describe how to reduce matched-pair bias caused by incomplete matching and inexact matching. Cases will be matched to controls on the propensity score using the presented matching algorithm. `SAS/STAT`/Ge2 `LOGISTIC` procedure code will be given to create the propensity score	propensity score, sample, logistic distribution, logistic regression, regression analysis, response variable, proc logistic, proc step, macro definition	6
52	SAS Routines for Calendar and Clock Elements	Rick Aster, Valley Forge	Data values related to time are conventionally measured and re- ported as combinations of elements of the calendar and clock - for example, a date may be written as the month, day, and year. These composite values can be more complicated to work with than data values that are written as a single measurement. SAS provides a set of functions, formats, and informats that work with specific combinations of calendar and clock elements. International date formats let you work with time data in many different languages. In version 8, you can go beyond the built-in routines and create picture formats to write the date and time of day in any combination of calendar and clock elements. Linear Time In theory, linear time is as easy to measure as linear distance. All you need is a unit of measure and a point of reference, and you can make simple numeric measurements of any point in time. For a few applications, time is actually measured this way	sysdate9, date variable, datetime, time, options statement, datepart, elapsed time, integer, proc step	6
53	Saving Trees: Managing the Edit Check Process Electronically	Timothy D. Kelly	The whole process of cleaning clinical trials data can be very time consuming and frustrating. A computer can be better, more accurate, and serve as "eyes" for cleaning data. Without a validated procedure for storing and retrieving the edit check failures, a lot of energy is spent reviewing old and known issues multiple times. Due to the iterative nature of data cleaning, managing this process electronically can save time and trees. Organizing this process programmatically will enable data management to better use their time on the current issues, link the failures to queries, and generate reports on outstanding issues. This paper will focus on a technique used for managing the edit check failure information and the many incentives it provides. Edit Check Document The Edit Check process begins with the creation of the Edit Check document. This document drives the edit check programming process	data validation rules, data governance	4
54	Security Issues for Web-based Applications: Issues and solutions for the safe transfer of Clinical Trials data over the Internet	Andrew T. Fagan, Christopher R. Olinger	When building any web-based application, the issue of security is always a concern. When the application is designed to allow the sharing of clinical trials data across the Internet, security becomes one of the major topics. This paper describes what approach iBiomatics, a SAS company, has taken in the construction of their iBiomatics Portal. The paper presents a basic overview of security for an Internet based application, describes what security features were built into the application, what software tools were used to implement various aspects of the security model, and how the actual hardware configuration can be a critical piece of the overall security of a web- based application. While the iBiomatics Portal is used as the example for this paper, the concepts presented here apply to most Internet-based applications. The primary product of iBiomatics, the iBiomatics Portal provides a secure, Internet-based application for the warehousing, analysis and review of biomedical data	21 cfr part 11, clinical data	6
55	Softerware: Replace SAS Programs with XML Documents to Help People and Computers Be Happier with Each Other	Michael C. Palmer	In a novel use of electronic documents to replace labor-intensive programming, a SAS-based integration has been implemented that uses XML to automate the creation, revision, and reuse of the publication-quality statistical tables prominent in regulatory submissions. Table content and style revision is XML document-based, not programming-based. The XML documents that define style and content can be reused. This document-centered XML approach facilitates management in the document life cycle, in contrast to the embedding of content and style information in programs where it is expensive to revise. XML is an excellent choice for an intermediate format that can be published to varied final formats and archived. In the implementation, an XML document can be published to paper, Postscript, PDF, or RTF in a hands-off/lights-out, automated process	proc tabulate, dataset	6
56	Standards for Electronic Submissions to FDA	Kay Obenshain	The FDA is moving towards its goal of paperless submissions by 2002. To meet its goal, the agency is defining standards for regulated industry to use when making regulatory submissions in electronic format. Standards for data are being defined on different levels, including content, structure, and format. The	regulatory submission, inferential statistics	4
57	SynCoder: A SAS/AF Application for Implementing MedDRA Coding in Clinical Trials	Deborah A. Testa, Russell Holmes, Daphne Ewing	This paper presents SynCoder, a Version 8.1 `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 8.1 over earlier versions	data mart, clinical research	4
58	Techniques and Strategies Used in Building a SAS-Based Clinical Data Management System	David L. Ward, Bound Brook	This paper will show some of the techniques and strategies used by the leader in validated, SAS-based, clinical software in building its next-generation data management tools. Learn about the benefits of using a SAS -based system rather than systems built on Oracle or other database systems. Security, data integrity, and speed of set-up and use will be discussed, as well as key areas that make a data management application successful. Also presented will be specific techniques using	data governance, clinical data, foreign key, clinical data management, key	4
59	Testing the Trend of a Response Curve to an Increasing Sequence of Doses: A SAS Macro to Automate the Analysis	Donghui Zhang	In animal toxicity studies, treatments are composed of a series of increasing doses including a vehicle control. The Tukey, Ciminera and Heyse (1985) trend test, referred to as Tukey's trend test, is often performed to (1) test for linear trend in the response curve corresponding to three dose scales and possibly different dose ranges by deleting the higher doses, (2) identify the NOSTASOT (NO STAtistical Significance Of Trend) dose: the maximum dose concentration which is not significantly different from the vehicle group. This is an iterative and tedious process. A SAS macro was developed to automate Tukey's trend test. The key to automate this process is to convert the sequential use of Tukey's trend test in identifying NOSTASOT dose into a set of contrast tests where each contrast corresponds to a different dose scale and dose range combination	dose, sample size, sample, macro definition, regression analysis	4
60	The Application of SAS Data Mart in Clinical Laboratory Testing	Cheng Wang, Jianming He, R Peter Mallon	Business driven data warehouses in the area of clinical laboratory testing have demonstrated preliminary success in providing valuable information to pharmaceutical and managed care organizations (Gilmet et al, 1998). Starting January 1, 1998, a cumulative database has been loaded on daily basis with testing data created by a national leading clinical laboratory. The tremendous of amount of data and resource requirements make it difficult to efficiently perform ad hoc queries or comprehensive analyses without database traffic interruption. A data mart in SAS format has been created and is updated each quarter permitting rapid retrospective analyses while minimizing traffic contention. The SAS Macro codes are presented to demonstrate the effectiveness of SAS data mart	create table, proc step, proc sql, macro definition	4
61	The Basics of ODS and Templates for Data Analysis	Sandy McNeill	Do you spend most of your time rearranging the results of your statistical analysis to produce the right format or your client? If so, the Output Delivery System is for you. This paper introduces you to `ODS` and emphasizes the utility for those who work with the statistical procedures. You will learn how to create output datasets from your results, rearrange columns of tables, select or exclude different parts of the output, render your output in HTML, Rich Text (RTF), PDF, and other formats, and customize the appearance of your output. Armed with `ODS`, you can concentrate on the analysis, not the formatting. This paper is a revision of an earlier paper entitled "`ODS` for Data Analysis: Output As-You-Like-It in Version 7" by Chris Olinger and Randall Tobias. The revisions made were to bring it up-to- date for Version 8.2	file statement, proc genmod, proc step, anova, output delivery system, proc glm, ods html, proc template, standard deviation, ods trace, repeated measures, sas output	20
62	The Changing Nature of SAS Programming in the Pharmaceuticals Industry	Steven Light	In the last two years, regulatory initiatives and technology changes have coincided to significantly impact SAS programmers in the pharmaceuticals industry. The Food and Drug Administration (FDA) Guidance for Industry and Electronic Submissions standards (1,2,3) have established new standards and conventions to which we need to adhere. We are also confronted with CDISC (4) data standardization efforts and the maturing of technologies such as XML, desktop publishing and data warehousing. These changes should compel an examination of the strategies, methods and even the mission of SAS programming organizations. Current trends and issues in the industry will be reviewed, with suggestions on how changes can be addressed	data standard, clinical programming, cdisc	4
63	The Efficiency of Proc SQL in Place of Traditional Procedures for Large Data Sets	Cindy Stroupe	ClinTrials Research, Inc. has had a large, ongoing, marketing study for several years. Each year brings additional patients and additional visits for existing patients. A majority of the data sets contain over half a million records. This volume of data creates a problem not only in processing resources but also processing time. The `SQL` procedure is a very effective method of sorting, counting, and selecting data that does not require the same amount of processing resources or time as traditional procedures. This paper will give you practical examples of the use of SQL with large data sets. Key Words: SQL	proc sql, order by, proc step, create table, group by, cpu time, proc sort	4
64	The iBiomatics Portal: Leveraging SAS and other technologies to develop a Web-based informatics Portal	Christopher R. Olinger, Andrew T. Fagan	The iBiomatics Portal is a web-based application designed to bring together all of the information about a specific drug compound, therapeutic area or medical device. The application was developed over the last nine months by iBiomatics, a SAS company. While the Portal uses a significant amount of software from SAS, it also takes advantage of technology widely available on the market from other vendors. The process of developing the application and the integration of these different technologies is the primary topic for this paper. Understanding how technologies can be used and blended to form a solution quickly is the key to success in the fast paced world of web- based applications development. Just knowing what your options are is half the battle, but taking the time to get the pieces to function together is where the real work comes in	clinical data, data governance, proc sql	6
65	Unit-of-Analysis Programming	Vanessa C. Hayden, Fidelity Investments	There are many possible ways to organize your data, but some ways are more amenable to end-reporting and analysis than others. A common tendency is to simply denormalize clinical data to the lowest level and build reports from there. Not only is this inefficient, but the logic is harder to trace and can lead to programming bugs. Building clinical data oriented toward the final unit of analysis will help you avoid these common pitfalls and inefficiencies. This paper will overview basic database structures, simple denormalization, and alternate ways of aggregating and storing your data, based on the unit of analysis. It will demonstrate how such a design facilitates reporting and analysis, and stands up to scrutiny. This paper is oriented towards anyone who works with data, regardless of SAS software experience. Examples will be presented using SAS software code, but the concepts apply regardless of the specific data management tool used	key, clinical trial, lookup, sample, proc sql, data standard, dose escalation, data science, clinical data, proc step, proc sort, clinical research, dataset, flag variable, sample size, regression analysis	6
66	Use of SAS to Automate Nonlinear Regression Analysis in WinNonlin	Darrell A. Russell, David E. Burgio	Previously, compartmental pharmacokinetic analyses were performed using PCNONLIN, developed by Statistical Consultants, Inc. However, PCNONLIN is DOS-based, and is no longer supported due to the more recent introduction of WinNonlin (Pharsight Corporation). Unfortunately, WinNonlin does not easily lend itself to the process of batching analyses using multiple compartmental and weighting schemes. Therefore, new techniques were developed using SAS and WinNonlin, enabling creation of files for continuous and efficient processing of multiple profiles. Scripting Language, an object-based programming language component of WinNonlin, can be used to control executable tasks within WinNonlin. In this paper, the use of SAS to generate individual data files and multiple WinNonlin command files for each subject, as well as the script files needed to initiate WinNonlin, call the appropriate files, run the analysis, output selected data files, and close the software, is described	dataset, file statement, macro variable	6
67	Use of statistical techniques for tracking patients	Franky De Cooman	During the development phase of a potential new drug, the compound is evaluated during several clinical trials. It can never be excluded that patients re-appear in more than one trial, or it is the purpose to do so when the protocol foresees follow-up studies. As one can never write down in a CRF a sort of unique identifier of a natural person, one can not uniquely identify a person amongst several trials. Fields that could help identifying a person are: Initials Gender * Age It is not fictitious to think that the investigator uses different initials for a same person, for example if the patient's name was John Le Duc, that in the first trial, the initials are JLD, and for the second trial, they become JL, or LDJ. A patient also becomes older, so the age might change as well. To cope with such problems, clustering techniques might give a relief for isolating isles of patients having similar characteristics such that they can be uniquely identified afterwards	cluster analysis, clinical trial	2
68	Using Functions and Arrays in the SAS System to Manage and Manipulate Data	Ben Cochran	Oftentimes, SAS users receive data that is alleged to be cleaned, scrubbed, and ready for an application or placement into a Data Warehouse. Even though the data may be clean, many times further manipulation is needed. This paper examines ways of manipulating data through the use of functions and arrays in the SAS System. This paper is intended for the beginning and intermediate level SAS user. Functions and arrays are a part of the base SAS System; therefore, no other SAS product will be examined in this paper. Basic Data Manipulation Anytime users need to change existing data to meet our application needs, they are manipulating the data. One of the most basic forms of manipulating data is rearranging the order of the observations, or, in other words, sorting it. Sorting data not only rearranges the order of the observations, it allows for by- group processing. An example of this is merging two data sets by a common variable	character variable, array, output, set statement, dataset, do loop, input statement, numeric variable, character functions, date variable, ranuni, sas function	6
69	Using Recursion in the SAS System	David L. Ward	Recursion is a friend of most 3rd or 4th generation language programmers. It can be used to slice hundreds of lines of code from complex algorithms, or bring a system to its knees after having consumed all its resources. The concept of recursion and useful applications of it using SAS /Macro and `SAS/AF` software will be presented. You will learn how to traverse directories, trees of information, and other interesting yet challenging topics. After reading this paper you should have a better understanding of when and how to use recursion in the SAS system	macro variable, macro definition, %if-%then-%else	2
70	Using SAS to Create a Centralized Parameter File for Analysis and Reporting	Phebe Joseph	When generating tables, figures and listings for the analysis and reporting purposes of large clinical studies, it is customary to maintain all titles, footnotes and output files for these reports in a centralized parameter file. Each program or macro that generates output for the Analysis and Reporting Plan extracts relevant information from this centralized file. This necessitates a high level of accuracy in both the creation and modification of this parameter file, which is typically column driven. This paper discusses a SAS macro to generate this parameter file, thereby reducing the degree of manual processing. The macro assumes that basic information such as the table number, titles and footnotes from mock tables are maintained in an `EXCEL` file	excel, macro definition, sample, clinical trial	4
71	Using SAS Version 8.1 Output Delivery System to Automate Two Sample	Test Selection	In small clinical trials with continuously distributed outcome variables the standard two sample equal variance t-test may not be applicable due to a violation of either the normality or equality of variance assumptions or because the sample size is too small to assume that the central limit theorem applies. The statistician must choose an appropriate two sample test. When a large number of such tests are to be performed, some automation of the test choice may be desirable. The SAS Output Delivery System can be utilized to automate two sample testing by following a decision tree for test selection. Output from the chosen two sample test can then be merged with appropriate summary statistics for reporting. A macro was developed which selects either an independent sample t-test with equal variances, an independent sample t-test with unequal variances, or the Wilcoxon rank sum test for comparing the measure of central tendency (or distribution) for two samples	sample, sample size, central tendency, response variable, output delivery system, normality test, proc means, homoscedasticity, central limit theorem, primary endpoint, sas output, heteroscedasticity	4
72	Using Special Characters and Formats with SAS	Quan Ren	SAS output is a plain text file, it doesn't use special characters like or special formats like superscript . This paper is to present a way to use special characters and formats in SAS output	sas output, macro facility	4
73	VALIDATION: Let SAS do the comparisons for you	Lara E.H. Guttadauro	Have you ever been asked to validate a listing? It can be a tedious, boring and sometimes inaccurate process if comparisons are done by hand. I have developed a procedure to let SAS do those comparisons. First, the output from the listing needs to be read into a SAS data set. Next, the validation	data cleaning, proc step, proc print, sas output, validation set, proc compare	6
74	Warehousing Clinical Pharmacogenomics Data	Philip M. Pochon	On June 26, 2000 Celera and the Human Genome Project jointly announced that the first reading of the human genome was complete. On Feb 13, 2001 the two presented the first full genotype maps of the genome. For the pharmaceutical industry there can be little doubt that pharmacogenomics will be an ongoing revolution; and as an emerging discipline, clinical pharmacogenomics provides immense opportunities in the areas of drug development and medical therapies. In order to successfully integrate pharmacogenomics into clinical trials, we must recognize the data management issues that the nature of pharmacogenomic data and the state of the science raise	data warehouse, clinical trial, data governance, dataset	6
75	Web-Enabling Your SAS Applications Using Only Base SAS	David L. Ward	Many SAS developers see that the perfect solution to the reporting needs placed on their departments is to provide SAS reports or graphs to their clients via their corporate Intranet. So, they place requests up the corporate food-chain to order SAS Institute's Intrnet product. Months later they often learn that the product was too expensive and thus are left to wonder at what could have been. This paper will present a basic guide to running your SAS applications on the web using a simple CGI program and Base SAS. You will also learn how to create HTML forms that pass parameters to your SAS programs. The techniques presented are taken from a generic, robust, alternative to `SAS/INTRNET`, which will also be demonstrated	macro variable, sas base, proc step, data step, proc printto, sample, sas output, sas programmer	6

Back to Conf go 2002 go 2000

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.