NESUG 1996 Papers - Index

105 papers. Source: NESUG (Northeast SAS Users Group) conference proceedings.

#	Title ×	Authors ×	Abstract ×	Keywords ×	Pages
1	&&&, ;;, and Other Hieroglyphics	Christopher Yindra		macro variable, proc step, run, symbol table, call symput, dataset, where statement, global symbol table, macro conditional, do loop, macro facility, proc print, macro loop, macro definition, &variable	8
2	A Data Warehous/Business Intelligence Facility: Success in an Insurance Company	John Gilbert		nominal variable, data dictionary, ledger, management reporting, raw data, dataset, business intelligence, data warehouse, customer satisfaction, customer segmentation, data cleaning	10
3	A Method for Reading Multiple Input Datasets (including dataset names) From a Single Input File	Danielle Ringstrom	The testing has begun. In order to see if the different parts of your program are working, you need to use `PROC PRINT` or some other procedure to output the data quite often. You practically have one after each `DATA STEP` or `PROC`. What a pain in the neck it is to pull them all out when your testing is done and the program is perfect. Well, now you don't have to do it. A simple little macro will allow you to leave the source code there. Another great use for this macro is to comment out many lines of code where documentation is plentiful. Sometimes it is difficult to remove sections of code with standard comments, where there are comments that exist. Read on to find out an easy way to skip over code with %skip	proc step, macro definition	2
4	A Simple Way to Create a Clinical Trial Study Data Dictionary	Frank Liu	A clinical data dictionary is required to provide the repo'rting and analysis components of products. v:ith informati~n about the underlying clImcal data. This paper introduces an easy, timesaving	data dictionary, clinical trial, clinical data, label statement, proc step, dataset, proc sql	3
5	A Standard Adverse Event Summary Report Generation	Frank Liu	below. is not This paper presents a SAS program that demonstrates how to use the SAS macro facility and `PROC SQL` to generate the AE	adverse events, adverse event summary, create table, proc step	7
6	A Table Driven SAS Parser for Health Level 7 (HL7) Healthcare Data Interchange	Jason Oliveira, Thomas Frenkel	In conjunction with Columbia-Presbyterian Medical Center's data warehousing efforts. a	data dictionary, data warehouse, format statement, macro definition	5
7	A Two-Stage Cluster Systematic Sampling Program for Clinical Quality of Care Studies	Wenbin Mo, Michael Fleming	Managed care organizations increasingly need to assess their clinical quality of care. When review of medical records is necessary for such assessment, the cost of reviewing all relevant records is often prohibitively high. Simple random sampling can also be inefficient in terms of the number of clinical practices that must be visited for medical reviews. A two-stage cluster systematic sampling approach can be used instead to select a more efficient, yet representative sample. When properly used, structured sampling methods save time and resources, and produce results which can be generalized to the whole population. A program to generate a two-stage cluster systematic sample will be introduced in this article. This program was originally used at Blue Cross and Blue Shield of Maine under the MVS environment. A simplified program will be introduced in this article, which can be used in PC , UNIX and other systems	sample, systematic sampling, random sampling	3
8	A Universal SAS/ACCESS Macro to Retrieve Data from DB2 Tables	Chen Xi, Linda Bergin		lookup, macro parameter, variable, create table, macro variable, dataset, macro conditional, proc sql, sas programming, macro loop, macro definition, proc step	4
9	A Word to the Wise or a Cudgel to the Obtuse	Neil Chase		proc step, proc contents, macro variable, flat file	3
10	An Alternative Way to Compute the Kappa Statistics in Observer Agreement Studies	Yukiko Ellis		cohen's kappa, proc calis, proc freq, proc step	8
11	An Introduction to Developing Applications with SAS/AF FRAME Entries	Vincent L. Timbers	Frame entries in SAS/ AF use graphic display devices that enable the developer to easily build interfaces which permit users to point and click their way through applications. The functionality of frame entries assists end-users who have limited computer experience to perform activities such as data entry, data processing, and data analysis/reporting. This paper briefly explains frame entries and describes a data analysis and reporting application called the Consumer Services Information System Menu (CSIS Menu)l that was developed with frame entries. The remainder of the paper demonstrates the basic steps used in building the CSIS Menu with a sample application. 2	sample, sas output	9
12	An Introduction to SAS for The PC	Tom Wickstron		dataset, proc step, proc contents	4
13	An Introduction to SAS/FSP Software	Terry Fain, Cyndie B. Gareleck	SASIFSP is a set of procedures used to perform full screen interactive data entry, data editing, data retrieval, and data query. This tutorial provides a basic overview of SASIFSP software under version 6.11 of the SAS System. Topics include: creating a new SAS data set customizing data screens data entry data query * browsing SAS data sets The focus of this tutorial is on `PROC FSEDIT` although other procedures such as `PROC FSBROWSE` and `PROC FSVIEW` will be briefly discussed. Screen control language (SCL) is considered an advanced topic and will not be covered in this tutorial	proc step, dataset	6
14	Between a ROC Curve and a Hard Place	Joseph Kufera, Kimberly A. Mitchell		roc curve, logistic distribution, regression analysis, sample, type i error, proc step, confidence interval, logistic regression, macro definition, correlation, proc logistic, proc gplot	10
15	BIOEQ4: Bioequivalence Macro to Create both Table and SAS data set according to the FDA Bioequivalence Guidelines Issued in 1992	Mary Kay McPherson		covariance, proc genmod, least squares mean, pk parameter, numeric functions, geomean, sample, proc calis, proc step, proc glm, confidence interval, covariance structure, anova	6
16	Box and Whisker Plots: Definitions and Interpretations	Adeline J. Wilcox		proc step, proc univariate, sample, data visualization, interquartile range, sample size, proc gplot	9
17	Buidling a Data Warehouse with SAS Software: A Recipe for Success	Karen Grippo, John Chen	Building a data warehouse is a complex process involving many different phases; everything from database design, to hardware configuration and benchmarking, to user documentation and training. The authors of this paper have successfully implemented two large (20 GB) data warehouses using SAS on a Unix platform and will use their project as a case study to examine the process of building a data warehouse, from inception to delivery. The major phases of the process (analysis, evaluation, deSign, and implementation) will be discussed in detail, examining various issues and strategies. Special attention will be given to the topic of metadata and the key role it plays in the implementation of a data warehouse	key, data warehouse, cpu time, dataset	7
18	Building a Generalized Extract System Using SAS/AF and SCL	Hung X. Phan	This paper describes how to build an expert GUI system Which provides the users of the data with easy point and click access to large-scale Census data sets without any prior knowledge of the intemal data structures. Users can work with any SAS data sets and/or tables of databases such as RdbNMS, ORACLE/UNIX, Sybase. The system dynamically displays the number of variables, the variable names and the variable types upon the users' selections. The users then have the freedom to specify the criteria they want to extract and the variables they want to be included in the subset data sets. The system generates SAS source code to extract data to the user-spedfied format, i.e. in SAS format and/or ASCII formatted data set. These subsets of data can then be used to run tabulations and statistical analyses. The purpose of this paper is to provide a step-by step description of how to build such a GUI generalized extract system using `SAS/AF` and SCL	dataset, sample, proc step	9
19	Building Efficient Data Warehouses: Understanding the Issues of Data Summarization and Partitioning	Robert Chu, Susan Tideman	An efficient data warehouse enables better and faster decisions. To buDd an efficient data warehouse. you need to know how best to summarize data and how best to partition the summarized	proc means, data warehouse, train-test split, data mining	8
20	Calculating and Illustrating the Probability of Developing Cancer Using SAS and SAS/GRAPH Software	Michael S. Zdeb, Matt Dairman		life table, proc step, data step	7
21	Client/Server Performance Testing: Practical Results You Can Use Right Away	Barry R. Cohen		traffic data, oracle, sas output, proc step, data warehouse	10
22	Conversion of Report Programs to SAS/PH Clinical Templates	Paul M. Gilbert, Steven Light, Andy Siegel, Jack Jacobsen	SASIPH-Clinical, a new clinical data review tool, is being used by several Pharmaceutical Companies as the data review utility of their Computer Assisted New Drug Application (CANDA). In many cases the clinical data listings. summaries and graphics to be included in the CANDA are created outside of SASIPH-Clinical environment using other SAS products. This interactive presentation describes the steps involved in converting SAS report programs to SASJPH-Clinical Templates. The Template Facility is a tool which is used to create reports within SASIPH-Ciinicai	adverse events, sample, dataset, clinical data, macro call, macro variable, options statement	9
23	Cooking up Tools in the SAS/AF Kitchen	James R. Carter	Currently (as of SAS 6.11, TS020 - aka Wave I), the `SAS/AF` development environment does not provide some standard development tools. However, it does serve up a rich programming environment, which allows the programmer to do some creative "cooking". This paper describes some Frame/SCL development tools that are used daily at our site, including a file comparison utility, a catalog entry search/edit utility, and various other useful tools. Outline I. The Current Development Environment 2. Creating a "Build"-Like Front-End The Build Interface Dictionary tables and SCL lists 3. The PROCs Behind the Scenes `PROC BUILD` in batch mode `PROC CATALOG` in batch mode 4	proc step, catalog entry, txt, dictionary tables, catalog, proc catalog, proc sql	9
24	Creating a PC-based Information System: An Evolutionary/Revolutionary Visionary Approach	Peter Parker, R. Keith Daly	This paper is intended for mainframe users who are considering changiDg system platforms. This paper describes why we decided to go with the PC, the considerations made, the problems em:ouutered and, our assessment of the progress made. Finally, it touches on future enhancements that we onticipate. The Office of Textiles and AppazeI(OTEXA) of the U.S. Department of Commerce made a decision to move all databases and all computer programs from the National Institute of Health (NIH) mainframe computer time-share utility onto a PC based system. We have usedmaiDframes for data processing since 1978. UDIil a few years ago, PCs couldn't store all of our data or process it quickly enough. This platform conversion involved moving billions of bytes of data and tsking over functions performed transparently at the Nlll Computer Center: data security, data backups, and system maintenance	data wrangling, proc step	6
25	Creating and Linking Customized SCL Objects	Andrew A. Norton		data validation rules, relational database	7
26	Creating Forms Using The Data Step Graphics Interface (DSGI)	Harvey Monder		put statement, adverse events	5
27	Creating Hot-Keys for Data Entry in FSEDIT	Alexa Parliyan		date variable, sysdate9	2
28	Creating, Maintaining, and Accessing SAS Macro Libraries	Michael A. Walega		macro definition, data cleaning, macro variable, macro parameter, %if-%then-%else, proc step	8
29	Design and Development of the Census Burea's Time Series Analysis Repository	Danielle Ringstrom	One of the mandates of the Census Bureau is to produce accurate and timely statistical data on the levels of and movements in economic activity within the United States. As such, statistical smveys are conducted across all major economic sectors. These data are used by economic policy makers in both the public and private sectors. One of the primary responsibilities of the Census Bureau involves estimating current economic indicators. The indicators are statistics published on a monthly basis that measure critical economic activity. These statistics are not only used to quanillY current economic activity, they are used to predict future economic trends. As such, the production of these statistics is vital to economic policy makers	time series analysis, time series data, seasonal adjustment, macro variable, batch processing, dataset, macro definition	9
30	Devices and Desires: SAS/GRAPH Tips and Techniques	John J. Cohen, Irene Mendelson, Harvey Monder, Michael S. Zdeb	Many times a `SAS/GRAPH` user finishes a beautiful graph 0Ji the screen at his or her computer, only to find frustration and bewilderment in producing bard evidence of the fruits ofbis or her labors. This panel discussion will highlight tips to import `SAS/GRAPH` output to two popular word processing packages as well as tips to produce hard copy output on HP printers		2
31	Doing the Impossible with FSEDIT and AF: How a screen and frame can be Syncronized	Richard A. DeVenezia	Many data entry scenarios involve two datasets related by a key. A header dataset which contains one observation and a detail dataset which contains several observations per key value. Typically an AF frame is implemented with the header information displayed in fields above an extended table which contains the detail information. But what happens when the header information contains hundreds of variables? Maintaining a frame entry with hundreds of objects can be harrowing to say the least. An FSEDIT screen is better suited for such large scale data entry; a frame can still be used to enter the detail data. This paper describes techniques used in a `SAS/FSP` FSEDIT screen which invoke a `SAS/AF` FRAME. Some items of discussion are data structures, pmenus, command parsing, window switching using NEXT and the use of global `SAS/SEL` lists. The Problem An inspection process collects a multitude of parameters regarding some material tested	dataset, set statement	8
32	Engineering Efficiency into SAS Applications	Kirk Paul Lafler	With the ever increasing popularity of SAS Software among users and programmers, guidelines for its efficient use has widespread importance. This paper presents a collection of techniques for gaining efficiency when using SAS Software as an applications development tool. Areas receiving special consideration include program execution, 110, disk space, memory, and program maintenance. Numerous practical and proven techniques will be examined using sample code to illustrate why some methods are better than others	proc sql, dataset, cpu time, drop statement	6
33	Evaluating Ridership On The Municipal Transit System	William J. Montelpare, J. Frost, D. Scott, S. Burgess		sample, proc step	6
34	Field Content Verification Using SQL Dictionary Tables	Jack N. Shoemaker	`PROC SQL` provides a series of dictionary tables which collect useful information about the present state of the SAS session. For example, the table named dictionary . columns contains data about all the fields in all the data sets and views in all the def"med libraries. This paper will demonstrate the practical use of these dictionary data through implementation of a generalized field content verification routine. Field content verification is a technique used to quickly analyze a new data stream by displaying frequency counts of character data and seven-number summaries for nwneric data	proc step, proc sql, call symput, macro variable, character variable, proc print, macro loop, do loop, create view, dictionary tables, dataset, data step, proc report, proc univariate, numeric variable, select, variable list, symbol table	5
35	File Subsetting and Modification Using PROC FORMAT	Allison Levine	Did you ever have the situation where you had to read in a file, and select records matching a value or criteria, and then write it out to another file? What if you needed to modify some fields before writing the record? Perhaps you created a SAS data set with multiple string variables of length $200. Then you had to sort this file and merge it with a selection file. and then use put statements to create the output file. Well, here is a technique which uses `PROC FORMAT` to avoid that lengthy process. Problem There is a large external Master file (record length of2500) with one million records. A subset of records from this Master file needs to be written to an external file. Some fields need to be replaced, zeroed out, and added. This information is provided in the Selection file. Assume the Selection file contains the account number, variables which should replace the values from the Master file. and a variable which should be appended to the end of the file	proc step, proc format	2
36	Forecasting Business Failures Using a Poisson Regression Model	Vasanthakumar Bhat		poisson distribution, regression analysis, poisson regression, degrees of freedom, binary variable, response variable, predictor variable, proc reg	5
37	Graphical Solutions for Market Intelligence	Frederick E. Pratter		proc step, proc princomp, scree plot, regression analysis	9
38	Having a Ball with Strings	Ronald P. Cody		substr function, character variable, proc step, compress function, proc print, numeric variable, put statement, input statement, proc contents, character functions, variable list, string functions, upcase function	7
39	How to Prepare for the Year 2000	Stephan Taubman		sysdate9, options statement	3
40	How to Produce a SAS/GRAPH Reference Library	Michael S. Zdeb		macro variable, proc step, data step	7
41	Implementing a Behaviour Score Model Using a SAS to COBOL Translator	David Wolvick		sas function, flat file, proc step, dataset, macro variable	10
42	Incorporating SAS Programs into a Multi-functional Computer Assisted NDA (CANDA)	Kathryn Eisen, Sam X. Ye, Carolyn Kingman	Providing a user-friendly multi-capability environment that will speed the FDA review of Drug and Biological Applications has become a challenge for many Pharmaceutical and Biotech companies today. Corning Besselaar, Inc. 's (CBI) current CANDAICAPLA is a non SAS-based application which provides robust text, image and data capabilities. This paper takes an in-depth look at the way in which . CBI integrates SAS programs with free form queries to create a user-friendly system which can facilitate review of massive amounts of clinical data. A quick demo of the system shows that even Medical Reviewers, with no knowledge of SAS programming techniques, can use prewritten SAS programs to perform summary statistics on subsets of data they define. The hardware, software and the process of converting data to PC format is discussed	data cleaning, numeric variable	4
43	Inducing a Break in a Curve in a SAS/GRAPH Plot	Earl R. Westerlund		proc gplot, sample	2
44	Introducing Release 6.12 of the SAS System for Personal Computers	Gary Mehler	Release 6.12 of the SAS System for Per sonal Computers provides support for Mi crosoft Windows (version 3.1 using Win32s technology, Windows 95, Windows NT), and OS/2" (Warp). With this release, the SAS System incrementally improves both its user interface and its interoperability with other PC applications. This paper discusses both new features and incremental enhance ments to the user interface. This paper also describes the SAS System for Windows 95 and Windows NT 4.0, detailing the new user interface features that are consistent with the new look and feel for Windows 95 and Windows NT 4.0. The SAS System Viewer, production for 6.12 is described, as is the GUI-based SETUP program. which first ap peared in 6.11. Interoperability topics in clude Windows Explorer integration, elec tronic mail, lotus Notes, OLE. OBOC, and access to extemal OlLs. This paper also discusses the support provided by the SAS System for Windows NT	dataset, excel, put statement	10
45	Introduction to SAS/GRAPH	John J. Cohen	Opening the `SAS/GRAPH` manual for the first time can be an intimidating experience. Rudimentary charts and plots seem to require more study than a programmer can spare. This tutorial will lessen the effort required to take advantage of `SAS/GRAPH`. The presentation begins by examining the relationship between the response data set and the more common SAS procedures used to create displays, such as GCHART, `GPLOT`, and GMAP. Customizing graphics using TIlLES, FOOTNOTES, and LABELS is also covered. The presentation concludes with a discussion of hardware considerations and an exploration of the ANNOTATE and GREPLAY procedures	proc step, proc gchart, proc gmap, proc gplot, bar chart, sample	8
46	Macros Developed for Statistical Summary and Tabulation of Clinical Data	William Sun, David Lago, David Handelsman, Jack Shostak	Summarizing and analyzing data from clinical trials can be b(}th challenging and time-coosuming. In an eff(}rt to reduce the difficulties encountered when performing these tasks, we have developed SAS macr(}S that exploit efficiencies am(}ng cooe developed for different study protocols. De~aphics, vital signs, concomitant medications, adverse events, and laboratory evaluations are just a few examples of data that can be processed by using such macr(}S. SAS macr(}S are powerful tools that can be validated once and used repeatedly with proven, accurate results. Our first priority in developing these macr(}S was to maintain a Oexible, generic template that would pr(}vide us with the most comprehensive data analysis tool. In this paper, we will present eight macr(}S we developed that fulfil these needs. These macr(}S are currently being used to summarize categorical variables, continuous variables, adverse events, medications, and laboratory values	proc step, adverse events, nominal variable, dataset, interval variable, macro variable, proc report, macro call, sas output, proc freq, hypothesis testing, data science, proc means, footnote statement, concomitant medications, anova, proc genmod, sample, clinical trial	10
47	Manipulate and Create with PROC TABULATE	Kimberly A. Mitchell, Joseph Kufera		proc tabulate, proc step, class variable, by group processing, label statement, format statement, disposition table	14
48	Maximum Likelihood Estimation with SAS/IML	Charles B. Hallahan		likelihood function, proc calis, maximum likelihood estimation, estimate, covariance, proc step	7
49	Mimic Your Business Process with SAS/EIS Software	Helen-Jean Talbott, Alberto Cordoba	Many employees perceive and conduct the tasks related to data input, data management, analysis, and reporting as independent activities. This comes as no surprise when responsibility for these tasks is divided among several people and different products (such as `SAS/FSP` and Base SAS software) are required. `SAS/EIS` software can be your solution to conSOlidate, organize, and simplify your business process making it easier to pass data between tasks, reducing system operation errors, and speeding up report generation. This paper demonstrates how `SAS/EIS` was used with existing hardware to build upon a `SAS/FSP` data entry system and to facilitate data file management, data validation, report generation, upload, download, and update operations	data cleaning, catalog entry	7
50	Multi-dimensional Data Model Extensions to Data Warehouses	John McIntyre	Enabling OLAP exploitation of data warehouses means modeling the warehouse data along the dimensions relevant to end-users and their exploitation tools. SAS Software is developing a multi-dimensional data model (MDDB) to assist end-users look at their business data in ways that make most sense to them. This paper examines the MDDB. how it is built and maintained. and how end "users will gain access to it via SASIEIS viewers. OLAP for IT and Business End-Users OLAP as an enabling technology means different things to different audiences. To an IT audience. OLAP offers yet another way to deliver on the mission of providing end-user analysts access to relevant business information. in a timely fashion. It has the additional attraction of offering that access organized in ways that business end-users understand ... by the dimensions of the business. rather than by tables of information. Relevant to IT reviewers will be the relative costs of storage. (i.e		8
51	Objects, Objects and More Objects ...	Patti Brideson, Tammy L. Gagliano, Deva Kumar	The cless library in Release 6.11 of `SAS/AF` software has expanded to include many new visual and non-visual classes. This paper takes a closer look at some of the visual classes and what features they will add to your FRAME applications		8
52	ODBC: Windows to the Outside World	S. David Riba, Elisabeth A. Riba		proc sql, proc step, sas log, select, dataset, excel	10
53	Organizing Your SAS Graphs	Steven E. Elkin	Writing programs to run SAS Graph software has long been a challenging task for many programmers. Understanding how to display, store and print the output are all difficult issues which must be faced even after appropriate SAS Graph syntax has been developed. By using standard GOPTIONS, the GOUT option to store graphs in catalogs, and `PROC` GREPLA Y to name the graphical entries in the catalog, a simplified method for organizing your SAS Graphs is achieved. This method allows for both on-screen displays and printouts of your graph. Additionally, once stored in a SAS catalog, future access of your graph is possible without the need to re-submit the program which originally created the graph	proc step, proc gplot, where statement	2
54	PC Based Direct Marketing Regression Model Production System	Rich Masi	This paper presents a PC SAS application that automates the production of direct marketing regression models. The system has cut turnaround time for modeling projects from a few weeks to a few hours. There are three logical modules in the system that assist the analyst in creating and presenting high quality models. The data profile analysis module provides a description of how each potential predictor variable relates to a criterion variable. . The model development module evaluates many candidate models and selects the model that maximizes the system's model goodness criteria. * The deliverables module creates a Microsoft Word report that is deliverable to the modeling client. Also, this module produces scoring information that is deliverable to a service bureau. The system utilizes SAS's BASE and STAT Windows products and uses Dynamic Data Exchange to pass information to Word documents	predictor variable, data cleaning, regression analysis, sample, macro variable, correlation	3
55	Playing With the Mandelbrot Set	John J. Cohen	Fractals generally and the Mandelbrot Set in particular have offered a rich area for research and exploration for students of mathematics and graphics. A delightful result has been a plethora of dissertations and publications brimming with beautiful graphs. For SAS programmers, in contrast, these have provided us unwished for opportunities for testing the limits of our patience, our programming skills, and the hardware platforms on which we run. All too frequently the unhappy consequence of our dabbling has been headaches, programs which run for hours (or days!), and empty toner cartridges. There is no reason to let others have all the fun, nor to wonder about just what kind of arrangement made it possible for their plots to print. We will offer here the details of a successful experience in producing pictures, secure your first born, and list programs worth copying (assuming proper citation, of course)	proc step, macro facility	5
56	Poor Mans's Missing Value Recovery Methods	Leonardo Auslender		imputation, missing value, mean imputation, regression analysis, proc calis, binary variable, missing at random, interval variable, correlation	10
57	Porting a SAS/AF Application from PC to a MAC	Sharilyn Fabian-Ross, James R. Carter	SASIAF provides the ability to construct intricate GUI applications for various platforms including Pes and Macintoshes. Given the nature of Murphy's Law, if you have constructed the SASIAF application on a PC, a customer will materialize saying 'We'll use your application IF it runs on a Mac." Since programmers regularly tum Murphy's Law to their advantage, this paper will cover the issues encountered when a SASIAF application is ported from a PC to a Mac. Issues include transforming frame size, maintaining widget size and style, providing interactive help, accounting for user expectations, developing program branches based on platform, accesSing local directories and changing system options	sample, macro variable, sas base, catalog entry, proc cport, txt	10
58	Practical Approaches to the Epi Info/SAS Software Link	Margaret Ann Goetz		date variable, numeric variable, character variable, length statement	10
59	PROC FSVIEW: A Real Programmer's Tool	Alan C. Wilson, Marge Scerbo	Although `SAS/FSP`* is often regarded as the domain of application developers using `SAS/AF`, `SAS/EIS`, seL and FRAME, new enhancements have made PRoe FSVIEW an efficient and effective tool for programmers and researchers to browse and edit data, debug SAS code, perform multi-level queries on-line and create reports and new data sets interactively. An on-line demonstration will show subsetting with WHERE and WHERE ALSO clauses, interactive SORTing, and rearranging the displayed columns as scrolling or ID variables. This tutorial will also include examples of modifying existing variables and creating new variables interactively using FSVIEW formulas. In addition, and perhaps most importantly, the when and why to use PRoe FSVIEW will be discussed	proc step, where statement, proc print, data science, dataset	8
60	PROC REPORT: An Introduction to the Batch Language	Ray Pass		proc report, proc step, sample, proc print, character variable, class variable	10
61	PROC SQL - A Closer Look	Jim Peters		proc sql, proc step, proc sort, group by, where statement, create view, inner join, order by, by group processing, data step, dataset, relational database, right join	10
62	Putting Yourself on the Map with the GMAP Procedure	Michael L. Davis	Many users are fascinated by maps although they seem too complex to be produced by an average user. This paper introduces to new SASJGRAPH users the concepts necessary to create maps. The paper offers guidance in finding those pesky coordinates required to put the `GMAP` procedure to work. The major features of `PROC GMAP` that are required to draw a geographic map are explored. The paper also discusses elements of good graphic design as they apply to maps, and presents tips on using graphic devices and drivers intelligently. Part 1	proc gmap, proc step, dataset, sample	10
63	Quality Assurance and The SAS System	Thalene T. Mallus	In an ideal research environment, all data would be entered and stored in the same format, from the same operating system, and would have no inaccuracies, duplicates, or data entry errors. Unfortunately, in the real research world, data managers and analysts are often faced with the challenge of extracting, combining, and cleaning up data that have been entered by a variety of personnel or obtained from multiple sites or repositories. nus paper describes the related concepts of data validation and data 'scrubbing', and reviews some general SAS System tools and techniques available to ensure the accuracy and consistency of existing data, as well as tools available to ensure the quality of new SAS data sets. General data quality assurance guidelines are also discussed	data cleaning, proc step, dataset, master data management, quality assurance, proc compare, data governance, proc sort, sample, proc contents	10
64	Quick & Easy SAS/AF Applications Using SAS/ASSIST Software, SAS Data Views, Block Menus and HTML	Jeanne M. Spicer	The paper describes .techniques used to develop a user-friendly SAS application for accessing a large archive of data files at a university research center. The application was developed on a UNIX network, but can be ported to graphical or non-graphical platforms with little modification. No prior `SAS/AFEI` experience is required	sample, raw data, dataset, proc step, filename statement, proc contents	6
65	Reading and Writing Character Data	Craig Dickstein, Marge Scerbo	This is the information age. Client server, dynamic data exchange (DOE), object Hnking and embedding (OLE), and open database connectiViity (ODBC) have been added to our vocabulary. Each of these allow quick access to data in a variety of formats. But with all these advances, the need to read character data files and to create ASCII text files is still a major function in the data processing environment. The necessity to share data across platforms, operating systems, and software packages adds to the complexity of daily tasks and often the most direct solution is character data. This paper wHl discuss the process of reading and writing character data. Examples wiD be provided with each step. Beginning programmers will be able to follow the conceptual process quite well, while the more experienced analysts may gain some insight into problem solutions. So, the short and tall of this paper will include the simple and the complex	file statement, infile statement, input statement, put statement, dataset, txt, filename statement, character variable, data step, do loop, length statement, list input, retain, missing value	8
66	Reading Hiearchical Files	Larry Gertzog	Hierarchical files are composed of non-homogenous records. That is, records with different data elements (fields) are intermixed together in one file. The particular structure of each record is defined by a 'record type' field. Groups of related records are identified by a 'key' field. This form of organization is vel)' useful for keeping diverse and varying data elements together in one physical file structure. But it can be tricky - to put it mildly - to navigate such a file. The process of converting the 'mixed' record format of the hierarchical file to the 'uniform' structure of a SAS data set involves managing multiple passes through the `DATA STEP` and carefully coordinating input from the external file with output to the SAS data set. The SAS language is rich in the tools necess8l)' to accomplish this task. Input, logical control, and output statements provide the basics. This tutorial will review these, as well as the behavior of data values in various situations	dataset, input statement, output, conditional do loop	6
67	Repeated Measures Analysis with Discrete Data Using the SAS Systems	Gordon Johnston, Maura E. Stokes	The analysis of correlated data arising from repeated measurements when the measurements are assumed to be multivariate normal has been studied exten sively. In many practical problems, however, the normality assumption is not reasonable. When the responses are discrete and correlated, for example, different methodology must be used in the analysis of the data. Generalized Estimating Equations (GEEs) provide a practical method with reasonable statistical efficiency to analyze such data. This paper provides an overview of the use of GEEs in the analysis of correlated data using the SAS System. Emphasis is placed on discrete correlated data, since this is an area of great practical interest		6
68	Round Pegs Into Square Holes: Data Warehouses for the Hardware Impaired	Michael L. Davis	One of the dirty secrets of most data warehouse projects is that they require vast amounts of disk drive space and robust computers for successful implementation. Unfortunately, not every organization that lusts for a comprehensive data warehouse can finance the tab for the hardware that may be required to create the warehouse of their vision. Bassett Consulting Services has helped two clients make better use of limited computing resources through a two step approach. First, an active data dictionary permits "point and click" selection, renaming, joining, and sub setting of data, even when some of the elements reside on tape cartridges or in hierarchical files. Then "code engines" create SAS code on the fly to extract the requested data from their actual physical locations and transform the data into SAS data sets. These data sets even contain variab Ie labels and formats, courtesy of the data dictionary, and are ready for further analytical processing	variable list, data dictionary, dataset, data step, input statement, variable, set statement, label statement, excel	8
69	SAS ARRAYS: A Basic Tutorial	Bruce F. Gilsen		array, do loop, temporary array, numeric variable, dataset, missing value, character variable, array bounds, sample, macro variable	9
70	SAS Dates: Dating Activities and Millennial Considerations	August V. Treff	We have all had the experience of reading a text date like 020CT96 using a date informat and later printing the value 13424 when we forget to assign a format. After we recover from the shock of printing numbers instead of dates, we can proceed to more productive date activities. This paper will examine applications using SAS date functions and values. The applications will include printing date values in titles and using date values in duration calculations. Coding techniques which avoid problems associated with the approaching millennium will be presented	macro variable, sysdate9, put statement, date variable, character variable, data step, mdy, call symput, proc step	9
71	SAS MACRO - An Introduction	John Genzano		macro definition, macro facility	3
72	SAS Printout in Chinese	Lou Chen		proc step, proc format	2
73	SAS Printout in Chinese	Jin Pihuan, Chen Chunwei		macro variable, time series analysis	2
74	SAS Program Efficiency for Beginners	Bruce F. Gilsen		dataset, where statement, if-then-else, subsetting if, input statement, character variable, conditional do loop, proc step, numeric variable, set statement, sas function, missing value, proc print, put statement	10
75	Self-Modifying SAS Programs: A DATA Step Interface	S. David Riba	There are many situations where it is useful to have a SAse program modify itself during execution. Some examples include: conditionally execute a macro based on the data in a SAS dataset conditionally execute a procedure when there is no data In a SAS dataset generate in-line SAS program code based on the contents In a SAS dataset write SQL statements for the SQL Pass-Through Facility "0n-the-f1y" This paper explores a littIe-known routine in the SAS System that allows a SAS program to write SAS code "on-the-fJy" during execution. Since CALL EXECUTE is a `DATA STEP` CALL routine, the full capabilities of the `DATA STEP` can be applied to conditionally generate SAS program statements while the program is executing. If you have ever written program code to a temporary file and then %INCLUPEd it back into your program, you need to take a closer look at CALL EXECUTE. The paper will discuss the uses of CALL EXECUTE with specific examples based on real world situations	call execute, dataset, proc step, proc sql, macro facility, sample, proc print, macro variable, create table, proc sort, excel, if-then-else, macro definition	8
76	Simplifying Case Report Form Automation: An Example Application Using SAS, ODBC, OLE, and Visual Basic	Michael Tomb, Jeffrey D. Hart	SAS offers a new level of integration with MS Windows Automation Technology with release 6.11 wave 2. Software developers can now employ an endless variety of tools to control SAS programs and to edit SAS data files. This paper describes the fJrst phase of an application suite being built by the authors. The system allows simple setup of screens for dual entry and verification of CRF data. Although transparent to the users, all entered and derived infonnation is stored directly into SAS datasets. Using the Visual Basic development environment, the authors will share their experiences with applying SAS support for OLE and OOBC	dataset, proc sql, crf, proc step	4
77	Solving Business Problems with SQL Procedure	Kirk Paul Lafler, Sunil Kumar Gupta	Often, techniques for solving typical data processing problems involve a great deal of data manipulation and computing resources. When confronted with problems of this nature, you could approach them using conventional DATA, andlor `PROC STEP` methods, or you could use the strengths of the `SQL` procedure to manipulate and process this data. Real world problems will be illustrated using an online tutorial approach to solve problems such as sorting and grouping data, using summary functions, performing two-, three-, and multi-table joins, and constructing subqueries to avoid having to pass the results of one query to another for further processing	proc sql, right join, full join, left join, proc step, create view	4
78	Standardizing Output: PROC TRANSPOSE to the Rescue	Judy Loren	`PROC SUMMARY` nway; class sex age music; var party dances; output out=summed mean(dances)=avgdancs sum(party)=atparty n=atconf; The first 10 obs of the results are printed in Figure 2. You'll notice that the values of MUSIC are different for females in their 20's and females in their 30's. Next we use the `TRANSPOSE` procedure: `PROC TRANSPOSE` data=summed out=trans' id music; I by sex age; The results are shown in Figure 3 (which you may note is produced with a `PROC REPORT` NAMED WRAP instead of a `PROC PRINT` because it was too wide for this format). `PROC` 1RANSPOSE creates an observation for each numeric variable within the BY variables SEX and AGE. The numeric variables in the incoming dataset become separate observations with the name of the variable stored in the ' variable `_NAME_`. By specifying ID MUSIC, we asked TRANSPOSE to create separate columns for each value of the MUSIC variable in the incoming dataset, and use the values to name the variables in the new dataset	proc step, proc means, proc transpose, class variable	2
79	Statistical Analysis of Self-Organizing Maps	Susan B. Garavaglia, Asha Sharma	The Self..()rganizing Map (SOM) introduced by T. Kohonen (1982) is a type of artificial neural network that is typically applied to data analysis, including pattern recognition and data clustering. It is generally developed in an unsupervised learning mode. A set of statistical analysis steps are proposed to determine if the SOM bas been properly trained and if the resulting weight vectors and topology "make sense" in both quantitatively measurable and intuitive contexts. The application used to demonstrate the statistical methodology is a large sample ofactive U. S. businesses from Dun & Bradstreet's database. l. Overview Artificial neural network based models have been proposed as replacements for more traditional statistical techniques in areas of classification, predictive modeling, and other applications in which one or more dependent variables are available	neural network, sample, unsupervised learning, data science, euclidean distance, response variable, proc freq, dimensionality reduction	10
80	Syndromes for Medical Diagnosis: A search Method in SAS Language	Victor Kamensky, Ilya Muchnik, Leonyd Yampolsky	Symptom is an indicator of a health disorder. Syndrome is a conDination of Syq1toms which can occur on sick patients only. Macro THREE finds all syndromes of 1,2 and 3 Syq1toms. An ex~le of syndromes on Beck Inventory (Beck & Steer, 1987) is described	macro definition, sample	6
81	Take Your Project Tracking System to a New Level - Using SAS to Manage Your Projects	Connie X. Li, James Sun	This paper presents an approach to build a project management system. base on a simple `SAS/AF`-based project tracking system. In addition to collecting and updating the project's status information, the system takes advantages of SAS's rich functionality and provides managers with process analysis tools to find and tackle tbe problems that slow the whole business process. By building the system with SAS. management can easily utilize the tracking data to enbance the system for the purpose of performing sophisticated modeling for the business process. This is one significant advantage for using SAS·based svstem m'er other over-the-shelf project scheduiing andlor project management software. This paper illustrates a business application for clinical trial data processing in phan11aceutical industry	proc step, clinical trial	5
82	The Bisquare Weighted Analysis of Variance: A Technique for Nonnormal Distributions	Rebecca Regeth, William Stine		anova, weighted mean, proc step, dataset, predictor variable, proc genmod, p-value, normal distribution, central tendency, response variable, sample, regression analysis, proc glm, proc nlin, outlier	9
83	The Dirty Dozen: Twelve Common Programming Mistakes	Bob Virgile		error message, input statement, sas log, proc step, error, if-then-else, missing value, comment statement, sample	6
84	The Evil Twins of Real Numbers That May Cause Unexpected Results in SAS Applications	Aileen L. Yam	The real number system is infinite. Because oj computer hardware limitations, real numbers are being converted internally and are represented with an equivalent finite set oj numbers. Some real numbers cannot be represented exactly and can vary very Slightly according to different plat/orms on which the SAS System runs. Thus, numeric representation has the potential Jor imprecision. This paper is a non-technical guide to understand numeric representation, with examples to illustrate when numeric representation can cause unexpected results and how to minimize representation problem	&variable, do loop	3
85	The Fuzzy Feeling SAS Provides: Electronic Matching of Records without Common Keys	Charles Partridge		agent, dataset, proc step, merge statement, proc sort, insurer, macro definition	9
86	The Role of SAS Programmers in Clinical Trial Data Analysis	Ming Wang	This article shows in-depth the role of SAS programmers in clinical trial data analysis. It outlines the task flow of clinical trial data analysis, discusses project programming planning and documenting procedures, descn'bes SAS programmers' tasks and programming sldlIs, and provides insight on how to work with people in your team: clinical data managers, statisticians, programmer manager and project manager. This paper is a valuable overview for programmers who are starting out or plan on being involved with clinical trials, and for data managers and statisticians who work with SAS programmers in a clinical trial team. It is also a valuable management guideline for experienced SAS programmers	sas programmer, clinical trial, clinical data, data science, dataset, format statement, macro definition, sas programming, data cleaning, proc step, data step	6
87	The SQL Query Window	Dana Rafiee		group by, order by, inner join, proc sql, end= option	10
88	Tips on Designing SAS Macros	Michael Keohan	This paper will discuss certain things to keep in mind while designing SAS programs using SAS Macros. The SAS Macro facility is in essence a pre-processor which allows programmers a way to neatly bundle similar lines of code together and execute them by invoking a macro call. Some programs do not require the use of the macro facility, and therefore, should not use them. The use of SAS Macros require more advanced skills particularly in the debugging phase. This is true because the line number reference you receive back in the SAS Log refers only to the line where the macro was invoked. Meaning, the error message does not have a corresponding line number. H you get a syntax error back and you cannot f"md where it is coming from, submit the SAS code outside a macro definition. Macros can span across multiple data steps and `PROC` steps. Macros can encompass just a few lines of code or thousands of lines of code. Macros can contain all macro language	macro facility, proc step, macro definition	1
89	To Subset or Not to Subset	Janet E. Stuelpner	Sometimes you need all the data in a dataset. Sometimes you don't. When testing a program, it is better to use a subset of the data. How can you write a program without the need to remove a bunch of code after you are finished testing? Macros are the answer. Macros can be great tools when trying to subset data. By defining three small macros at the beginning of your program ( %iff, %wear, %and ), very few changes need to be made to change from one subset to another. Or you can just run the entire population from the dataset. This paper will show you how	where statement, if-then-else	2
90	Transforming Data From Household-Level to Person-Level: PROC TRANSPOSE or DO Loop?	Mary-Elizabeth Eddlestone		proc transpose, proc step	2
91	Two Many Variables, Too Little Time: A Macro Solution	Peter Liberatore	Depending upon your analysis it may not be uncommon to work with a SAS data set containing a few hundred variables. In most cases, it is not necessary to embark on the time conswning task of keying each variable name as input to procedures. SAS provides a few techniques to include subsets of variables. There may be instances, however, when it is necessary to key the names of each variable. This paper presents a problem where such a situation occurred. To avoid the time consuming task of typing 545 variable names, a SAS routine and macro was written to generate the necessary information	proc step, flat file, proc contents, macro variable, predictor variable, proc reg, variable list, name range list, dataset	4
92	Two Perils of Moving Your Mainframe Processing to PCs: Memory and Processing Time	Peter Knapp	When considering a move from a mainframe platform to a PC platform. many concerns need to be addressed. While moving SASe programs from one environment to another is easy - remove the JCL, add a few `LIBNAME` statements your newly converted code may not run the way you expect it to. Problems may crop up that you would not experience on the mainframe. Two problems that my office encountered moving it's programming from a MVS mainframe system to Windows based PC~ were memory and processing time. This paper will address these concerns using code to illustrate attempts that looked good in theory but that didn't work along with solutions that did. With these examples I will illustrate how memory and processing time concerns can impact your move from one computing environment to another. Coding techniques I came up with will show that it is possible to minimize the impact of processing time and memory	proc step, cpu time, proc sort, proc sql, if-then-else	5
93	Using Across Variable in PROC REPORT Procedure	Min Fu	When using PRoe REPORT, one can define a set of nested across variables. This is a useful feature when values of a group variable need to be printed on top of values of an another group (subgroup) variable and the values of both variables need to be presented horizontally rather than vertically to span multiple columns of	proc report, proc step, numeric variable, macro parameter, %macro parameters, class variable, macro variable, macro definition	3
94	Using Base and SAS/GRAPH Software to Identify and Geographically Display Health Care Labor Markets in New York State	Matthew Reilly	This paper describes an application developed using Base SAS to identify regional health care labor markets in New York State and then maps these discrete markets using `SAS/GRAPH`. The average salaries of the labor markets identified, are used to develop factors to adjust for regional wage variation. These factors are incorporated into public payment systems for services under Medicaid, or in negotiated rates between managed care organizations and providers. A number of Base SAS and `SAS/GRAPH` concepts and language components are demonstrated by this application. Procs Sort, Summary and Chart are used to develop county weighted average registered nurse wages. The regions are mapped using `PROC GMAP` and annotate datasets are used to customize the map. Finally, `PROC REG` is used to test whether the resulting factors better explain the county wage values than an existing scheme	proc step, if-then-else, anova, regression analysis, weighted mean, proc reg, response variable, proc gmap, sample	10
95	Using Graphics Capabilities to Enhance SAS/AF Frame Output	Perry Watts, Samuel Litwin	System developers can use graphics capabilites to enhance the user interfaces they aeate with `SAS/AF`@ fRAME Entry software. Rve different types of graphs are desaibed and illustrated in this article. The fmt application shows how a member of the leon Class 00ds clarity to multiple selection options at the main menu. Next. output from a GRSEG catalog is used to acate an organizational logo advertising sponsorship. Two additional applications show how to superimpose fixed Hotspot Classes over a bar chart where the heights of the bars vary at run time. and how to simulate animation by clicking on hotspots positioned over a graphics object belonging to the SASIGRAPH Output Class. The fmal application calls an external `SAS/GRAPH` program from inside FRAME to customize axes ad plot error bars with thicker lines on a dynamically generated plot	bar chart, catalog entry, proc step	8
96	Using Macros to Recode Sensitive Data	Mary-Elizabeth Eddlestone		proc sort, macro definition, proc step	2
97	Using PROC TRANSPOSE to Facilitate the Processing, Analysis and Reporting of Health Care Claims Data	Bryan K. Beverly	In the effort to control health care costs, private and public health care insurers are increasing their computerization, analysis and reporting of claims data. These data represent a rich source of outcome management information such as cost of care, resource utilization and reimbursement fraud and abuse. Health care claims also provide useful data on diagnoses, procedures and the periodicity of claims administration. In seeking to capture patient and provider specific information, it is often necessary to summarize charge and reimbursement data elements from a stack of claims into a single health care episode. The summarized record enables one to achieve more efficient processing and more effective decision support activities. The traditional approach in performing claim summarization consists of complex arrays and other `DATA STEP` processing. However one can obtain the same results sans time consumptivity or labor intensity using `PROC`	proc transpose, proc step, sample, insurance claims	6
98	Using SAS to Compute Variances For Poisson Samples	Terry L. Pennington	Poisson sampling is a method ofunequal probability sampling in which each sample unit is se1ected independently. It is a sample design common for economic surveys at the Bureau of the Census. Such sample designs offer increased sampling efficiency compared to stratified equal-probability sampling. This paper discusses the module for calculating sampling variances for Poisson sampling. The module is a component of the standardized economic processing system that is currently being developed at the Census Bureau. This SAS-based system will process and tabulate survey data. Design-specific variances are then calculated for the various survey data. The SAS code for the Poisson-variance module is displayed and discussed in detail	sample, poisson distribution, macro definition, proc calis, dataset, macro loop, macro variable, proc step	6
99	Using the SAS System for Continuous Quality Improvement	Melissa A. Durfee	Using control charts is an obvious quality technique to analyze part or process data. However, `SAS/OC` e offers many more procedures which facilitate continuous quality improvement. An	histogram, main effect, correlation, sample, quality control, interaction effect, anova, proc freq	10
100	Using the SAS System to Perform McNemar's Test and Calculate the Kappa Statistic for Matched Pairs of Data	Lisa Suchower, Margaret Copenhaver	Dichotomous responses from matched pairs of data at different timepoints are often displayed in 2 by 2 tables, and McNemar's test is performed to test the hypothesis that the proportion of subjects with a certain response is equivalent at both timepoints. A kappa statistic can determine the level of agreement in these responses. The SAS `PROCEDURE FREQ` can perform a large sample approximation to McNemar's test when the number of discordant matched pairs is large (n > 20). The CMHI option in FREQ is used since McNemar's test is a special case of the Cochran-ManteI-Haensze1 statistic. In SAS Version 6.11, McNemar's test can also be performed using the new option AGREE in FREQ. If the number of discordant matched pairs is small (n ~ 20), the SAS `PROCEDURE UNIVARIATE` will perform an exact McNemar's test. An example is presented performing McNemar's test using the `PROCEDURE UNIVARIATE`	sample, cohen's kappa, proc calis, confidence interval, proc freq, proc step, degrees of freedom, null hypothesis, sas output, binomial distribution, proc univariate	8
101	Using the SAS System to Produce HTML-Based Text	Richard D. Langston	The author has previously producad a postar session regarding the preSQntation of gallElalogk:al dala. The next step in the process of producing a usaful document of resaarch is to usa emerging HTML technology in conjunction with the Wo~d Wide Web. The author has used the SAS System to produce a set of HTML files consisting of text and image data. Tha resultant files can be examined by common Web browsars and can also be converted into a serial form suitable for publication. INTRODucnON In looking forways to preSQnt my ganealogical research, I found the most affeoIive means was to provide individual family worksheets with page refereooes where the parants were children and where the chUdren were parents. The system I developed to produce these worksheets was extensivaly documented In a poster session presented at SUGI 191_ PfOC8I!Jdings, pp. 914-923}	sample, output delivery system	4
102	Utilizing SAS To Creat A Patient's Liver Enzyme Profile	Erik S. Larsen		proc gplot, macro variable	4
103	Visualizing Repeated Measures Data in Clinical Trials Using SAS/INSIGHT	Jan W. Buzydlowski	The Radiation Therapy Oncology Group is conducting a Phase II clinical trial of the effect of radiosensitizer plus standard external beam radiation for the treatment of locally advanced prostate cancer. One of the measures of response in the trial is the marker of prostatic-specific antigen (PSA) and its value over time. This paper discusses the ease of use of SASIINSIGHT to graphically display the repeated PSA measures of the trial and how the use of a graphic representation as opposed to a previously used report format lead to an important insight which changed the method of doing the analysis	scatter plot, clinical trial, proc step	3
104	Why Neglect SELECT?	Roger Lustig	The select: keyword in the SAS language (distinguishedfrom the same word in `PROC COPY`, `PROC SQL`, etc.) offers a structured alternative to if then-el se passages in programs. While adding hardly any programfonctionality, select: makes it easier to define and debug case-logic structures such as recodes. Thispaper is based on a comparison between if - t:hen else programming and sel ect: programming. (The in "cases" jUnction is introduced in passing.) The presentation is geared to the beginnner; this printed version focuses on learning and teaching these programming concepts in the SAS environment. O. Introduction Full functionality-the ability to accomplish a full set of tasks--is no longer the standard of usefulness in a computing system. Today, computing must allow the user to reach a goal in an intuitive way, typically allowing a multiplicity of approaches	if-then-else, otherwise, select, proc step	8
105	Writing WordPerfect Documents as SAS Output: Updates and Extensions	Wenrui Wang, Larry Thorderson	One way that numerical errors can be introduced into technical documents and scientific publications is through the process of typing. The number of numerical errors can be reduced by creating word-processing documents (in this case WordPerfect files) directly from SAS System programs. This presentation explores some ways to create tables and listings more efficiently and accurately by improving the link between output from the SAS System and WordPerfect documents as they relate to the Windows-based SAS System (Version 6.08) and WordPerfect for Windows (Version 6.1). There is always a certain amount of difficulty involved in accurately transferring analysis	create table, file statement	4

Back to Conf go 1997 go 1995

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.