HOME
QUICK SEARCH
AUTHORS
KEYWORDS
HELP
BUGSSUGI 1994 Papers - Index
258 papers. Source: SAS Users Group International conference proceedings.
| # | Title× | Authors× | Abstract× | Keywords× | Extras | Pages |
|---|---|---|---|---|---|---|
| 1 | A Case Study in the Use of SAS/PH-Clinical for an Electronic Regulatory Submission of a Megatrial | Kathy R. Boussina, Dorene M. Emmrich, Guy Pawson, Alan Hopkins |
SAS/PH-Clinical was used for a Product License Amendment (PLA) of the GUSTO (1,2) trial, an international megatrial comparing four thrombolytic strategies in the treatment of acute myocardial infarction. Using commercial software, Genentech was able to prepare an electronic regulatory submission within 8 weeks of receipt of the final database. The overall package included text, graphic!" programs, data sets, supportive documentation and usage instructions contained on two 550 megabyte CDs. SAS/PH Clinical allowed both medical and statistical reviewers to review and analyze the data |
clinical research, data governance | source | 11 |
| 2 | A Case Study: SPC Analysis Using the SAS System | Bill Henley, Amitava Ghosh |
Statistical Process Control in a data. rich environment may prove in some cases to be more of a curse than a blessing. Techniques for obtaining and managing large amounts in a pseudo real time manner are described. Creating, appending and summarizing SAS datasets while the subject DATASETS are con- stantly being updated will be the primary focus of this presentation | source | 3 | |
| 3 | A Comparison of the GLM, IML, and MIXED Procedures for Use in Spatial Statistical Analyses | William J. Price, Bahman Shafii |
Incorporation of spatial information into statistical analyses can greatly enhance the estimation process. However, this may not be easily realized due to intensive computational requirements and a lack of a comprehensive software package. One proposed method of analysis is the SASe procedure PROC MIXED. Use of this procedure has certain drawbacks and potential problems when compared to more familiar SASe products such as PROC IML and PROC GLM. Limitations as well as advantages associated with all three products are discussed with reference to a previously published data set exhibiting spatial dependencies |
proc step, proc mixed, proc glm, proc iml, proc genmod, irregular component, covariance, covariance structure, anova, correlation, likelihood function, estimate, fixed effects, maximum likelihood estimation | source | 6 |
| 4 | A Development Environment for Applications Based on SAS Software | SAS Institute (a company) | Data structures. design methodologies, and programming tools are the foundation components of an application development environment. This paper describes these components using a SAS software perspective. Specifically. the paper covers design methodologies, management of application components, preparation and maintenance of parallel test and production environments, and reusable code libraries. A sample SAS application that uses the described techniques concludes the paper | libname statement, sample, catalog, dataset | source | 4 |
| 5 | A Macro to Associate Time-Oriented Data From Two Independent Sources | David Arnold | A macro is presented which automates the process of associating appropriate values from time-oriented data. Time-oriented data, or event data represents conditions present at a given time, or conditions that continue over time. Often event data can come from independent sources, having been collected by separate methods, without common identifying time values. It may be necessary to describe the conditions in one source in the context of conditions present concurrently in another. The question is essentially, "what happened while a particular event occurred?" One accepted way of handling two independent sources of event data is to form a Cartesian product (map every event in A to every event in 8), and then use logic to single out the appropriate associated events. This method is costly in terms of space and processing time. The macro performs the association without a Cartesian product, and thus is more effici!'lnt | raw data, adverse events, macro call, clinical trial, macro loop | source | 5 |
| 6 | A Macro to Facilitate the Visualization of Individual Patient Efficacy and Safety During an Investigational (Phase III) Clinical Trial | Marjorie Bell, Marcella D. Stricklin |
Intensive statistical analysis is usually performed on data collected in clinical trials to describe both the efficacy and safety of a new or investigational drug for the study population as a whole. However, the clinical investigators and FDA reviewers frequently have an interest in summarizing the course of the study for an individual patient including the patient's study medication dosage, plasma concentration levels, and efficacy as well as safety responses to the drug. A single page of customized graphs allow the investigator to view the individual patient's responses to the study medication with respect to the patient's dosing and toxicily information, all within the same time frame. A macro writlen for SAS/GRAPH software referred to as RUNGPH accomplishes this goal. The macro uses the ANNOTATE, GPLOT and GREPLAY procedures in SAS/GRAPH. Examples of the use of the macro and the output produced are presented and discussed |
proc freq, adverse events, clinical trial, proc greplay | source | 5 |
| 7 | A Macro-Based Approach for Calculating Binomial Probabilities | Daniel R. Bretheim | This paper outlines a SAS· System macro-based .approach for use in calculating binomial probabilities. The sections that follow describe the methodology, code, and sample output related to a macro designed to accomplish this task. II. THE BINOMIAL PROBABIUlY FORMULA In general, the probability of r successes in n trials is: n! p' q(n-r) r!(n-r)! where r is the number of successes; n is the size of the sample; p is the probability of a success; q = (1 - p) is the probability of a failure; and P(r} = probability of exactly r successes. Using the bent coin toss example (Spurr & Bonini, "Statistical Analysis For Business Decisions", Irwin, 1973). we can determine the probability of getting 3 heads and 2 tails using a bent coin that turns up heads 60 percent of the time | binomial distribution, probability distribution, macro parameter, probbnml, sample | source | 6 |
| 8 | A Poor Man's SAS/ASSIST Software | Tracy L. Lord | This paper describes a method of documentation used by IBM in SAS educational classes to help students learn SAS programming techniques. While this system of documentation does not replace all the features of SAS/ASSIST or on-line help, it does provide a wealth of information for the novice and professional programmer |
sas programming, sas syntax | source | 3 |
| 9 | A Problem Tracking System Using the Graphics Object in FRAME | Samuel Johnson | $AS software gives you many tools to produce graphics based applications quickly. This particular application provides examples of how some of these tools can be used. The vertical bar charts in the graphics object are used to represent the number of problems, which each employee supports. With this application you can easily subsel these problems, subgroup the bars, or change the Independent chart variable with the click of a mouse | vertical bar chart, bar chart | source | 14 |
| 10 | A Review of SAS/AF Decision Support Systems Based on an SQL/DS Data Warehouse | Candy R. Habich | data warehouse, proc sql, relational database, normalization | source | ||
| 11 | A SAS Approach to the Theory of Optimal Level of Output and Employment: A Management Decision-making Case | Seid M. Zekavat | proc step, proc corr | source | 4 | |
| 12 | A SAS/AF System for Entry, Validation, Analysis, and Reporting of Diverse Survey Data from Multiple Sites | William A. Harris, Charles W. Warren |
Standardization and processing of data can be a challenge when survey sites have complete flexibility with the survey instrument. The Centers for Disease Control and Prevention (CDC) develOped a core questionnaire to elicit information about health risk behaviors among representative samples of U.S. high school students in approximately 71 sites. Participating sites may alter the qu~,stionnaire by adding, deleting, rearranging, or modifying questions or response options. Data from each site must be standardized and added to a master data library. The system described in this paper uses Base SAS release 6.08, SASI AF, SAS/FSP", Screen Control Language, and SAS Macro Language to provide automated standardization and analysis consistent with the core questionnaire. Data descnbing the site version of the questionnaire are input, and the system generates and submits Job Control Language and SAS code to load the survey data into a master data library |
raw data, macro facility, proc freq, batch job, macro definition, dataset, libname statement, data validation rules, macro variable, master data management, proc step, sample | source | 6 |
| 13 | A Set of SAS Macros for Producing Customized Reports | Greg A. Grandits, Ken Svendsen |
Producing customized reports is a high priority in many research and business settings. SAgtJ has several procedures that generate reports, but only the PUT statement within a DATA STEP gives complete flexibility to placement of text and data values. However, DATA STEP processing and writing PUT statements is cumbersome to program. This paper describes a' set of macros that produce customized reports that are easy to program and give complete flexibility to placement of text and data values. The user first defines columns and column widths across the report page. Text or data values (often summary statistics) are then moved to these columns and specified lines using macros MOVE or NMOVE. Items can be moved to single columns or to combined columns with the items automatically centered. Text can also be under1ined. Lines to where items are moved can be listed or a starting line can be given along with the number of lines to be printed with optional skip patterns |
proc means, class variable, dataset, put statement, proc step, set statement, correlation | source | 6 |
| 14 | A Strategy for Running Fractional Factorial Experiments | Robert A. McLean | A SIratagy fer running"""- two IeveIfractionallactDrial designs Is gIVan. It is expedBd that SUCh designs wiD contain InIcrmation on _ significant main eflecls. UnIcr1unalBly SUCh eII8cts may be confounded with two _ in18ractions or higher ader inIeractions. Thus W Iwo _ inl8raCtions are plausible, the experimenIBr must be ",spared 10 continue the experimentation procedure 10 break this possible confounding. The sllalBgy presented consisls of using a ... _ design 10 break the confounding between main effec1s and two_ inlBradions. PROC OPTEX 01 the SASIOC"soflware can then be used 10 produce additional obseovaIions thai break the confounding among 8tr'J Iwo or more in_ns that are aliased together. The standard errors of least squares means ere used to measure the relative amount of information available to various celt means as the resutt 01 the competition among various non-orthogonal effec1s in the final model |
proc step, main effect, proc calis, anova | source | 5 |
| 15 | A Use of External Files in Dynamic Code Generation | Greg M. Woolridge, Henry B. Winsor |
This paper illustrates the technique of having the program write executable code to an extemal system file, then using a %INCLUDE command to insert the contents of this file back into the program for compilation and execution. The program can use input data to decide which lines of code need to be written to the extemal file, allowing for dramatic simplification of program code . and often enhanced performance. An example that demonstrates the specification of exact formats for printing numeric data is presented |
if-then-else, macro call, put statement, macro variable | source | 5 |
| 16 | Accelerating Maximum Likelihood Classification: An IML Application | Cecil R. Hallum, D. Mark Carpenter |
In classification processing using the standard maximum likelihood classifier, a large amount of throughput time is attributable to the necessity of having to calculate each density function (or more commonly, the logarithm of each density function) for each point to be classified. In this paper the standard maximum likelihood classifier is reformulated so that J in most cases, only a small number of density functions need be computed each time a data point is to be classified. In particular, the percentage of points that will be classified by the reformulated maxi mum likelihood classifier without having to compute all the densities is directly related to the degree of sepa ration of the classes. The use of IML provideS insight into the utility of the approach and its applications. The technique relies upon class thresholds which are obtained at the beginning of the classification process and which remain fixed thereafter |
likelihood function, maximum likelihood estimation, proc step | source | 4 |
| 17 | Accessing Enterprise Data | Mark Lochbihler, Candy R. Habich, Emily P. Wallace |
Accessing Enterprise Data Mark Lochbihler Emily Wallace Candy Habich SAS Institute, Inc. SAS Institute, Inc. Eastman Chemical Company Every organization is faced with a set of common concerns when implementing a successful enterprise-wide data access strategy. This paper will define two distinct views of enterprise data -- the data provider and the information seeker. Data is a valuable resource for decision making only after it has been made accessible to seekers who need the data. There are two barriers which must be overcome to implement a successful enterprise-wide data access strategy -- diverse data sources and data distribution. This paper will also take a look at a company that has successfully implemented several decision support applications with the SAS System, supplying users around the world with valuable information | dataset, proc sql | source | 8 |
| 18 | Act Local, Think Global in Installing the SAS System Release 6.08, for Microsoft Windows 3.1 in a Networked Environment | Gerardette M. Furlow | Supporting the SAS System Release 6.08 for Microsoft Wmdows 3.1 in an academic or corporate environmen4 can be an exhaustive task for the SAS consultant. Often when a new release comes out. the SAS consultant spends a considerable amount of time just installing the software OD numerous file servers, or on individual stations for departments at their site. In many instances, due to limited resources, remote installation of the SAS System offers the SAS consultant many advantages-one of which is more time for supporting the SAS System in areas besides installation. This papet will focus on installing the SAS System for Windows 3.1 to a local file server and to a remote file server Nnning Novell Netware 3 .11. The setup process for the file server and client stations will be discussed. Moreover, the advantages and disadvantages of remote installation, and the Windows 3.1 considerations prior to installing the SAS System will be addressed | sas consultant, sas base | source | 4 |
| 19 | Advanced SQL and Database Connectivity | C. Michael Whitney | This paper will discuss SAS 6.07'5 Sal Pass-Through Facility and how it eliminates the need for access and view descriptors when retrieving from and updating D82 databases. Techniques described here can be applied to other relational databases. Sev eral of SAS Sal's other features will also be covered, including SOL and macro variables, summary functions, the case expres sion, and mUlti-table selects | macro variable, proc sql, create table, proc step, relational database, dataset, macro put | source | 4 |
| 20 | An Application of SAS Procedure In Evaluation of Drug Effect Estimation of Mean Residual Lifetime | Jianli Li | The life table method has been widely applied to compare the difference among the drugs in the survival rate and healing rate. This paper describes a method, which is developed on the basis of the l Ue table method, to estimate the expected lifetime or time to heal ing of individuals beyond a particular time point, mean residual lifetime, and its standard error. The estimates of mean residual lifetime and its standard error could be derived from the output of LIFETEST procedure. Furthermore the c~rison of mean residual lifetimes among two or more treatment groups could be made with SAS program. 1. IntndJction In the pharmaceuticaL industry it is a conventional |
proc calis, survival function, sample, life table, sample size | source | 6 |
| 21 | An Automated Approach to Patient Exclusion Accountability: Summaries Using SAS Macro Language | Carl Arneson, Randall Austin, Beth Sherrill, Cam Huffman, Greg Silva |
Often in clinical trials, some or all of a patienfs data may be unreliable due to various circumstances. It may be desirable to exclude these data from certain analyses or summaries. However, it Is also important to keep detailed accounts of when and why such exclusions are made. This can be a difficult task, especially when such exclusions are made in many different programs, and the information about the exclusions is continually being updated. We have inplemented a system for simplifying this process using the SAS Macro language. All exclusions are listed in a central set of files. and the infonnation in these files is read into each program upon execution. Whenever a program is run, all relevant exclusions are incorporated into the analyses. and a detailed report of these exclusions is created. This system makes it easier for the user to keep track of and report exclusions, resurting in more reliable and efficient analyses | missing value, clinical trial, macro facility | source | 5 |
| 22 | An Educational-Assessment Database for the State of Tennessee | John F. Schneider | The Education Improvement Act of the State of Tennessee mandates that the influence of school systems, schools, and teachers on measures of student learning be assessed. Students are tracked across years since the assessment is made on a gain basis, instead of the raw score or percentile basis. Although most students have the same identification information from year to year (e.g., name, Social Security Number, etc.), many do not. Even students who do not match contribute information to the analysis, and are included in the database. The database was begun using data from the 1989- 1990 school year with approximately SOO,OOO records. Currently, over 2,300,000 records are in the database. Beginning last year, data about teachers is being collected, such as subject taught, etc. Naturally, these two databases must link together by student. When this project was started, many "experts" told us creating this database would be impossible | sample, data step | source | 5 |
| 23 | An Executive Information System for General Hospitals | Sabina Beullens | horizontal bar chart, bar chart | source | 7 | |
| 24 | An Information System for All Users Built Using a Statistical Package on a Hacker's Paradise Platform | Panagiotis S. Karalis | A discussion of the potential of using SASe products, such as SAS/ASSISL" and SAS/AF" to build the user interfaces, the data management and the reporting capabil~ies of an end-user based Information System. The discussion focuses on how these SAS products interact wtlh such issues as the sens~ivity of data, data security, mu~~ platform environment, hardware, software, and the variety of end-user interests. Section 1: Information System Issues Those of you who have a computing system composed of numerous PC's, MACs, DECstations and a huge IBM" mainframe, where you run all your production applications, wouldn~ you like to free up some CPU cycles on your mainframe from certain non-production applications and use the mainframe primarily for your production? A:; you know, these cycles are very expensive! And those of you who don~ have such worries how about your data? Wouldn~ all of you like to tum your data into information? After all, we are in the so called Information Age |
data wrangling, flat file | source | 6 |
| 25 | An Introduction to PROC TABULATE: A Hands-on Workshop | Christopher Toppe | The TABULATE procedure is, along with PROC REPORT, one of the most powerful and difficult report generation tools available to SAS programmers I analysts. Its power and its difficulty arise from the same fact: PROC TABULATE allows you to exercise nearly total control over both the contents and the appearance of its output. But the inherent complexity of this procedure should not stop you from becoming skilled at its use. As a matter of fact, an hour or two of structured ""1"'rience with PROC TABULA IE is enough to teach you how to control its major features and options, and to give you the tools you need to use this procedure with confidence in the future. 1ms workshop provides such an experience. It tackles PROC TABULATE in a step-by-step fashion, building and enhancing a single table. 1ms paper is meant to accompany the workshop and presents the topics covered. However, only the final PROC TABULATE program, not each of the intermediate steps, has been included for reasons of space |
proc tabulate, proc step, class variable, missing value, dataset, proc freq, label statement, format statement | source | 6 |
| 26 | An Introduction to SAS/FSP Software | Terry J. 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 6.0816.09 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 PAOC FSEDIT although other procedures such as PAOC FSBAOWSE and PAOC FSVIEW will be briefly discussed. Screen control language (Sel) is considered an advanced topic and will not be covered in this tutorial | proc step, dataset, where statement | source | 5 |
| 27 | An Overview of the ADX Menu System and Design of Experiments | Almira A. Dumaual, Timothy E. Cooley |
The ADX menu system in SAS~ aids in the design and analysis of experiments. However, a complete understanding of this software cannot be accomplished without some background information on design of experiments. This paper will provide both an overview of design of experiments and ADX through the use of an example and will emphasize how the ADX menu system can simplify the process from the development of an experiment to the analysis of its data | main effect, regression analysis | source | 6 |
| 28 | Another Point of View: Color Stereographic Projections for Machine Capability Studies | Christopher L. Bonar | Machine Capability Studies (MCSs) are used throughout manufacturing industries to help understand the natural variation of machine tools. This paper presents a case study in which a new method was developed for conducting and analyzing a MCS. The new analysis technique uses SAS/GRAPH GCONTOUR procedure to produce color stereographic projections or "maps" of the variation within test parts. These maps can reveal interactions between machine axes that are otherwise hidden using conventional techniques |
contour plot, histogram | source | 6 |
| 29 | Application of Random-Effects Model for Categorical Data to Antiemetic Clinical Trials in Cancer Patients | Regina Louie, Alex Yaroshinsky |
The random-effects model for categorical response was applied to the simulated data based on a multicenter study of an antiemetic drug in patients with chemotherapy-induced emesis. The response was defined as a proportion of patients with complete control of emesis. This response for active control is relatively high (55-75%) and varies significantly across different patient populations. This fact and a high (up to 95%) anticipated rate of response for the experimental drug led to different treatment by-site interaction estimates depending on the scale used, as described by DerSimonian and Laird (1986). Three alternative scales can be used to estimate the treatment effect of the experimental drug comparing to the active control: difference in proportions, log relative risk and log odds ratio. Effect size homogeneity across sites is highly desirable to provide an evidence of consistent treatment effect | treatment effect, odds ratio, confidence interval, clinical trial, relative risk, sample, proc mixed, proc step, sample size, effect size, macro definition | source | 5 |
| 30 | Automating the Plotting of Significant Effects in Analysis of Variance | Matthew Grover, Huixing Tang |
The current SAS procedures for analysis of variance (e.g., PROC GLMlANOVA) do not provide automatic ways of plotting signHicant effects. This article presents a procedure which accomplishes statistical computing and graphic display in a simunaneous and data· driven fashion. Essential to this procedure is the automated generation and execution of codes for plotting the data according to user·specified criterion. In addition, generic code is written where possible to enhance flexibility in user·specifications of the criterion value, variable names, and plotting options. The procedure is particularly helpful in large-scale data analysis |
proc step, interaction effect, main effect, anova, predictor variable, macro definition, sample, macro variable, proc glm, proc calis, response variable, p-value, proc gplot, proc genmod | source | 6 |
| 31 | Avoiding, Accepting and Taking Advantage of Missing Data | Warren Repole Jr. | missing value, macro variable, proc step, input statement, where statement, character variable, symbol table, proc freq, retain, sum, sas log, response variable, predictor variable, options statement, macro quoting function, character functions, macro function, call symput, %if-%then-%else | source | 9 | |
| 32 | BestClass: A Robust Nonparametric Classification Package | A. Pedro Duarte Silva, Antonie Starn |
In this paper, we introduce BestClass, a set of mainframe-based SAS macros designed for solving two-group classification problems using a class of recently developed non parametric classification methods. The criteria used to estimate the classification function are based on either minimizing a function of the absolute deviations from the surface which separates the groups, or directly minimizing a function of the number of misclassified observations in the training sample. The solution techniques used by BestClass to estimate the classification rule utilize the mathematical programming routines of the SASjOR software (SAS Institute Inc. 1989a). Recently, a number of research studies have reported that under certain data conditions this class of classification methods can provide more accurate classification results than existing | sample, txt, discriminant analysis, dataset, linear programming, normalization, integer programming, macro definition, macro facility, covariance | source | 6 |
| 33 | Biostatistics Study Management System Using SAS/AF Software FRAME Entry | Faith Reneé Sloan | With the introduction of the SAS/AF software FRAME entry ( developers are now able to incorporate graphical user interface (GUI) and object-oriented programming (OOP) methodologies in the development of applications. Objects can now be drawn from the developer's toolkit and used to develop GUI-based front ends. The SAS/AF software's list box and push-button facilities enable users to interact with applications much more efficiently and intuitively. Not only is this technology powerful, but it is fun and exciting as well! |
source | 5 | |
| 34 | Building a Simple Time Tracking System Using Screen Control Language | Orion V. Hanger | proc sql, create table, conditional do loop, group by | source | 10 | |
| 35 | Business Decisions in Selecting Platforms for Information Systems | Daniel J. Squillace, Gary Burchett, Tom Cole, James C. Weathers Ili |
This paper is intended for anyone involved in the selection of computing platforms for new applications, or anyone considering moving existing applications to a new platfonn. Both the business and technical aspects of making such a decision are discussed here. This paper is a companion to the interactive panel | availability, data integrity | source | 4 |
| 36 | Calling External Modules from the SAS System | Richard D. Langston | The new MODULE routines allow for invoking external subroutines written in COBOL, Cf assembler, and other languages within DATA steps. SAS/IML steps. and SCL steps. This paper introduces the reader to the MODULE routines. These routines are an outgrowth of the COBOLINT routine that has been discussed in previous articles. INTRODUCllON There have been many requests over time for the SAS user to have the ability to call external subroutines from within the SAS System. The ability has always been there via the X command for invoking an external command, or via the PROe statement to invoke an external program. However, users have external subroutines that need to be called with argument lists. Also, these routines may wish to return values andlor update the arguments. These need is beyond the scope of the X command or the PROe statement The first attempt at providing the routine invocation ability was through the COBOLINT routine, which accesses COBOL subroutines |
character variable, sysrc | source | 12 |
| 37 | Catalog I/O Using the SAS Access Method Supervisor | Amitava Ghosh, Jeffrey A. Polzin |
source | 10 | ||
| 38 | Chart Smart: Design Graphs, Maps, and Tables for Effective Communication | LeRoy Bessler | bar chart, horizontal bar chart, proc step | source | 10 | |
| 39 | Code-Free Data Validation and Verification | Samuel Berestizhevsky, Tanya Kolosova |
The material exposed in our paper is intended to show how to solve data validation and data integrity verification problems by means of code-free approach to development SAS System based data-entry applications. The problem of data quality assurance exists for each application. Since the quantity of data grows and their relations extend, the problem of data validation and verification becomes more and more complicated. Data Verification (DV) facility is an application generator that creates data-entry applications with abilities of dataset access, data entry through screen forms, data validation, and data integrity verification. Applications generated by DV facility work under SAS System that includes SASIAF andlor SAS/FSP Software. DV facility consists of SAS Screen Control language (SCl) templates, and SAS Macro programs. SAS SCl templates create the initial kernel of data entry screen forms and editing facility |
data cleaning, macro definition, key, data integrity, foreign key, error message, proc step | source | 4 |
| 40 | Colored Candies and Base SAS: A Sweet Way to Produce Chi-Square Control Charts Part 1: Tutorial | Sherry Joyce King, Melvin T. Alexander |
Colored candies are easy-ta-understand tools thai can . iUustrate Statistical Quality Control principles. Candy companies want each bag to have about the same piece counts of each color as the other bags. The objective of this tutorial is to show how Base SAS software can help to improve understanding of a manufacturing process where homogeneity of proportions is important, using candy color piece counts as input to SAS programs. Base SAS software will be used to produce a chi-square (X2) control chart that checks the stabirlly of piece counts for candy colors during the bag-filling operation. x' is a statistical measure that compares actual values to specifoed values. x' has three principal uses; we concentrate here on its ability to measure homogeneity of proportions. This tutorial (Part 1 of the topic) teaches the use of the SAS DATA STEP and the PLOT procedure (among others) for this purpose. Part 2, in the Statistics section, explores more statistical aspects of the topic |
proc step, sas base, proc sort, proc transpose, proc means, sample, sample size, proc freq | source | 6 |
| 41 | Colored Candies and PROC MACONTROL: A Sweet Way to Produce Chi-Square Control Charts Part 2: Statistical Presentation | Melvin T. Alexander, Sherry Joyce King |
standard deviation, proc freq, proc step, sample, fisher exact test, exact test | source | 6 | |
| 42 | Combined Estimates of Carryover Differences in Mixed-Model Procedure | Louis Munyakazi, Richard L. Hintz, B. D. Selby |
degrees of freedom, fixed effects, proc mixed, proc genmod, proc step, proc glm | source | 4 | |
| 43 | Comparison of COPD Admission Adherence Scores by Hospital | Joel A. Dubin | dataset, if-then-else, %if-%then-%else, macro loop, macro definition | source | 13 | |
| 44 | Computing Case Diagnostics for Structural Equation Models | Noel G. Cadigan | A SAS@ program is presented to compute case diagnostics for the maximum likelihood anal ysis of a LISREL type of structural equa tion model. The diagnostics computed are Cook's Distance, COVRATIO and Likelihood Distance. The SAS program essentially con sists of a DATA STEP and a macro and is very easy to implement. An example is considered and the application of the diagnostic measures is briefly discussed |
likelihood function, covariance, estimate, maximum likelihood estimation, cook's distance, sample | source | 5 |
| 45 | Constructing Multivariate Control Charts with SAS Software | Melissa A. Durfee | Simultaneous control of two or more related quality characteristics has become an important subject, particularly due to the increased use of automated inspection which may measure many parameters on each unit of manufactured product. Referred to as multivariate quality control, this technique surpasses standard control charts generated on each individual characteristic since the probability of a type I error (i.e., "false alar~") is reduced. Using SASISTAT and SAS/QC M procedures, a Hotelling T2 control chart on related character istics may be constructed. Since the state of the process is characterized by a single number, the value of the T2 statistic, this method is advantageous when there are two or more quality characteristics of interest. Using a control chart preserves the time sequence of data. Therefore, the identification of runs or other nonrandom patterns is facilitated |
outlier, sample, covariance, normal distribution, qq plot, quality control, proc step, proc princomp | source | 9 |
| 46 | Consulting Questions: Should I Become a Consultant? Which Consultant Should I Hire? | Deb Cassidy | As more companies down-size their permanent staff, the more consultants are becoming a necessity. However, not all consultants nor projects are the same. Do you set up a business of your own or do you join an existing consulting company? Do you work out of your home/office or go into the client's office? Do you only do local work or regional/national work? What specific skills do you offer? How do you handle the unexpected such as a broken arm? If you are the client, which person/company do you hire? TIlis paper poses these and other questions you should consider about consulting -- from the perspective of both the consultant and the client It is based on personal knowledge and iilformal interviews with consultants and clients. It is intended as a base for decision-making and not as a guide to starting a consulting business or evaluating companies | data science, past due | source | 6 |
| 47 | Converting Mainframe Technical Information Resources to a Distributed Environment Using SAS: Two Case Studies | Kalman J. Gyirnesi, Gregg A. Spindler, Richard A. DeVenezia |
Engineers, statisticians and managers in manufacturing organizations often have poor access to product and process information. A continued and growing emphasis on quality improvement relies on timely analysis of product and process data. Information system groups are often overburdened with resolving traditional data processing needs in Accounting, Sales, Inventory Control and MRP. leaving technical information by the wayside. The 90's see many companies discovering the utility of moving to distributed network environments. Manufacturers embracing such networks are provided an opportunity to improve and simplify the analysis of technical data in the organization. It is not uncommon to require a large, formal overhaul of technical information resources in order to make it more accessible to process engineers and managers | dataset, data science, data governance, quality assurance | source | 5 |
| 48 | Counting in a PROC FSEDIT Subset | John P. Elrod | where statement, proc step, macro variable | source | 4 | |
| 49 | Creating Character Collating Sequences Using the Translate Function | Gary L. Katsanis | proc step, character variable | source | 2 | |
| 50 | Creating Portable GU/-based Decision Support Systems with SAS Software | Julianne Staub Perry | source | 9 | ||
| 51 | Cross-Architectural Comparison of Processor Speed Using the SAS System | Orion V. Hanger | cpu time, sas log | source | 3 | |
| 52 | Customized Training for SAS Users: Organization-based and Industry-based | Warren Repole Jr. | sas base, insurer | source | 6 | |
| 53 | Data Selection Techniques in SASjAF: Making Users' Lives Easier | Scott Rompala | Recently, the trend in software development seems to be inducing the user to rely less and less upon documentation todetermine what values belong in the fields of an application. Instead, when running an application, a user oiten needs to make choices, either in data entry or selecting parameters for obtaining specific output. On the data entry side, the kind programmer will add functionality to an application so that the user can not make errors which might be costly to fix later. On the output side, the programmer can aid a user in choosing value(s) so that he/she does not have to remember the correct value(s) to cause the results that he/she wishes. Fortunately, SAS/AF presents a programmer with the concept of the selection list, which remedies both of these problems |
catalog entry, character variable | source | 9 |
| 54 | DATA Step Efficiency and Performance | Jeffrey A. Polzin | missing value, where statement, dataset, subsetting if, proc step, proc means, length statement, if-then-else, data step, input statement | source | 7 | |
| 55 | Developing a SAS System Autocall Macro Library as an Effective Toolkit | Steven A. Wilson | This paper discusses using the SAS Autocall Facility for the development of a common set of macro utilities for use by application programmers. The autocall facility allows users to invoke a SAS macro without having to define the macro in their current job or session. This facilitates the development of a centralized "toolbox" of SAS macros that many individuals may utilize. Additionally, the development of an effective autocall library within a systems group allows programmers to quickly perform common processing tasks with consistency and accuracy. Note that this is not a presentation on macro coding. Instead, the focus of this paper is using SAS macros as utilities. Techniques for developing and managing an effective macro library are discussed | macro definition, autocall macro, macro variable | source | 6 |
| 56 | Developing an Air Quality Data Management System | Patricia Tobin | Managers of Air Quality databases must review and validate large quantities of data. A data management system using Version 6 SAS" software has been developed at the Salt River Project, Phoenix, Arizona, to replace a system which was created in the early 1980's. The original system was used to perfonn all necessary functions, including data entry. uploads from data loggers, validation, and the final storage of validated data. This system was originally developed using Version 4 SAS software (later converted to Version 5) and was comprised of SAS/FSP" screens in conjunction with SAS DATA steps and procedures. It has now been replaced with a data management system in Version 6 SAS software, using SASI AF" and SAS" Screen Control Language |
data cleaning, lookup, data governance, dataset | source | 7 |
| 57 | Developing Custom Training Solutions | Chip Rhodes, Claire McCullough |
A well-developed training program is essential for users to gain the skills they need to maximize the full power of the SAS System. Recognizing the diversity of users and their training needs, SAS Institute offers a broad curriculum of training span ning several media: self-paced SASITUTOR online training software, video-based courses and tutorials, and instructor based training. There are obvious advantages to a training pro gram utilizing multiple media. Formats can be effectively mixed and matched to allow users to meet their personal training needs. Cost-effective training mixes can also help you stretch your training dollars. Examples of mixed media solutions to training needs are presented for consideration. Efficient use of the SAS System is the common denominator for all organizations seeking training, but each organization has unique elements of operation | source | 5 | |
| 58 | Developing Easily Maintained SAS Code | Steven J. First | Getting a program working correctly is sometimes only half the problem. Good programs are easy to understand and maintain by both the original programmer or others. This is especially true in a production environment or where someone is contracting to write SAS code. Users are paying large amounts for SAS systems and they deserve efficient, maintainable code when the project is finished. This paper will pull elements from several large SAS implementations and examine the techniques used to create tight, efficient data structures from within programs that are easy to write, understand, and maintain | proc step, catalog, input statement, run, format statement, put statement, dataset | source | 8 |
| 59 | Developing Integrated Clinical Trials Systems: The ClinAccess Experience | Martin J. Rosenberg | Motivated by the desire to better manage an ever increasing volume of information and to reduce the length of time required to introduce new drugs around the world, the pharmaceutical industry and regulatory agencies such as the U.S. Food and Drug Administration have sought to facilttate the drug development and approval processes through innovative uses of computer technology. One such effort that has received great attention is the computer assisted NDA or CANDA and its cousin for biologicals the computer assisted PLA or | clinical trial, crf, data review, clinical data, audit trail, clinical research, data validation rules, pharmaceutical industry, key, dataset | source | 7 |
| 60 | Discovering the FUN in SAS Functions | Neil H. Howard | missing value, proc step, input statement, put statement, lookup, numeric functions | source | 6 | |
| 61 | Discovering the Secrets to a Successful SAS Users Group | Sally A. Roberson | Are you involved in a local, in-house or special interest SAS users group? Here's your opportunity to hear how you can keep your group flourishing. Experts from various types 01 users groups share their secrets for running successful groups. This paper. presented in panel fonnat, will cover such topics as programs, newsletters, leadership, and management support | source | 3 | |
| 62 | Donut Charts: Poking Holes in Pie Charts | Valerie Blettner, Lee Richardson |
Two popular graphs used throughout Asian business and print media are the donut chart and subgrouped pies. Donut charts are pie charts with a hole in the middle where text or graphics can be placed for added emphasis. Subgrouped pie charts have two or more concentric circles with the slices arranged for easy comparison of slice variables. Donut charts can also be subgrouped. Using the SUBGROUP= option produces a legend with the PIE and DONUT statements | proc gchart, proc step | source | 4 |
| 63 | Downsizing a Mainframe SAS Application to UNIX: An Application Developer's Perspective | Daniel M. Plath | This paper will present experiences of migrating a major mainframe SAS application to a UNIX platform. This migration was part of a large downsizing effort aimed at taking advantage of the lower costs offered by UNIX-based hardware. The application involved consolidating pharmaceutical sales and marketing data from five production applications and formatting these data into a single file for input to a LAN based Executive Information System. Extensive merging and summarizing of data at dHferent levels and a variety of SAS features utilized provided a very robust application to migrate. While the SAS code proved to be very portable, migrating to a new environment posed a Variety of technical hurdles. Four areas are to be discussed: major operational differences between UNIX and the mainframe environment; key elements to executing SAS in the UNIX environment; specific conversion problems and their resolution; and performance aspects of the two environments | length statement, macro facility | source | 4 |
| 64 | Easy Host File Selection Via Dialog Box for the SAS System, Version 6.08, for Windows | Randy C. Finch | The SAS Sysbm. Version 6.08. for Windows provides no mechanism for easily selecting a host file using a selection list window (slandard SAS/AF" method) or a dialog box (slandard Windows method). The Microsoft" VISual Basic'" Programming System for Windows (VB) pr_ a Common Dialog conlrollhal makes fts very easy 10 add a Windows file selection dialog box to a SAS/AF application. A VB program IhaI displays a file dialog box can be caned from a SAS/AF application. After seJecting a file, the path and FILENAME are passed back 10 Ihe appIicaIian via a file on a hard disk or RAM drive. The path and FILENAME can then be used by the SAS/AF application 10 access the chosen host file |
if-then-else, dataset | source | 5 |
| 65 | Eating Our Own Cooking: The Role of SAS/CPE Software in Managing Information Systems Resources at SAS Institute | Daniel J. Squillace, Virginia M. Dineley, David A. Fahey, Robert N. Bonham |
This paper describes how the SASlCPE family of software products is used in managing SAS Institute's own complex networked environment, which includes IBM mainframes, VAX midrange systems and clustered workstations, and over 1,000 HP workstations and file servers. Specific examples will be drawn from the areas of ad-hoc performance studies, service level monitoring. and resource usage reporting | source | 7 | |
| 66 | Effective Utilization of Region Attachments in a FRAME Application | Bud Whitmeyer | source | |||
| 67 | Enhancements to the Graphical User Interface for the SAS System on Personal Computers | Carol Williams Rigsbee | This paper describes Graphical User Inter face (GUI) enhancements to the SAS Sys tem in Release 6.10 for Microsoft Windows and OS/2. The goal of this paper is to dis cuss the major enhancements including a description of the improved GUI, increased application integration capabilities, and the CD-ROM installation process. Some of the improved GUI capabilities include a configurable tool bar, a more robust help system, more methods to configure your GUI, printing improvements and electronic mail (e-mail) support. Application integration enhancements include support for Object Linking and Embedding (OLE) and Open Data Base Connectivity (ODBC), a method to access extemal Dynamic Link Libraries (DLL's) and the ability to import and export graphics to and from common PC data file formats | sas output, sample | source | 9 |
| 68 | Enhancements to the SAS System to Support Data Acquisition in a Real Time Environment | Amitava Ghosh | This demonstration will highlight and show the new component Which will be available in the SAS System to collect data from different devices in a continuous manner as would be the case in a real manufacturing environment. This component includes a robust data server which will communicate and collect data from different data devices-like PLC's, scanners, and so on, and a SAS IJO engine to allow a SAS user to communicate and extract data from the data server. Initial implementation will include the support for devices which can communicate using TCPJIP sockets. However, API will be provided for users to write their own device drivers to talk to devices which are not supported by the TCP/IP driVer. This data can then be fed in a continuous manner to the SHEWHART procedure tor immediate out of control analysis |
source | 2 | |
| 69 | Environmental Monitoring Data Entry and Data Quality Application | Pamela Y. Goldberg | Data entry with data quality checks used in a -ussr-friendty- menu- driven environment is 8 vital data management tool. This poster preesnb an onvironmental monitoring detabaae application using SI>SIPF. SASlFSP. and ScreenConIJoi Language (SCl) commands on a VAXNMS mainframe. The application offers data enby, double data entry. and dala qualily checks through a ·user·friendly" menu driven system. Quality checks consist of placing value limitations on entered values and comparing the data entry dataset with the double data entry dataset for identical matches or error conditions. Both entry datasete are built through data entry screens acceaod from the same menu system. The data entJy dataset is used as the master dataset and the double data entry dataset is used for backup and quality control. The easy-to-follow menu-driven system allows data entry and access by an experienced programmer or a computer user | data cleaning, sample, quality control, proc step | source | 6 |
| 70 | Estimating Components of Variance for a Linear Model Having a Mixed Fixed/Random Factor in a Large Data Structure | Dawn VanLeeuwen, N. Scott Urquhart |
Real situations can lead to random or mixed linear models with many levels. Variance component estimation with SAS software's PROC GLM can bave memory requirements exceeding the memory available on any particular platform. This paper presents a simple computation scheme using both SAS statistical procedures and a small SASIIML software program to obtain Type IT mean squares and their expectations so that the variance components may be estimated. This scheme is applicable to classes of models possessing certain types of nested or interaction structures |
proc glm, proc step, proc genmod, main effect, anova, confusion matrix, degrees of freedom, proc anova, sample, proc mixed | source | 5 |
| 71 | Estimating Spatial Regression Models with SAS/IML | Charles B. Hallahan | regression analysis, likelihood function, sample, maximum likelihood estimation | source | 5 | |
| 72 | Estimation of the Values below the Detection Limit by Regression Techniques | Shi-Tao Yeh, Gayland Ridley |
The environmental or laboratory data set may contain some observations which may be very small or near zero. These data are measured. but measuring devices or procedures used are unable to detect low concentrations. The analytical laboratories may report it as below "detection limit" (Dll. The data report forms from the laboratories may indicate: o not detected. o less than a specified detection limit. or o zero. The most common techniques to estimate values below the Dl are the substitution and deletion techniques. Deletion techniques delete the observations below the Dl from the data set. This approach uses the observations above the Dl only. Substitution techniques use zero. half of the DL. or the Dl as the value for substituting any below the Dl observations. Both deletion and substitution techniques generate bioses from estimates of parameters. This produces inaccurate descriptive statistics and incorrect statistical inferences. This paper provides two regression methods | regression analysis, sample, proc step | source | 4 |
| 73 | Evaluating the Performance of the Wilcoxon Signed Rank Test in SAS Software | C. J. Tian | As one of the nonparametric methods, the Wilcoxon signed rank test is widely used. In the recent years, SAS Institute has made a number of changes and enhancements related to this test, which include the addition of exact p-values for small sample cases, the Student's t approximatkm for large sample cases, as well as some new output utilities. The advantages of these changes and enhancements are illustrated in this paper. Some comments are also presented from the viewpoints of statistics and programming. Numerical examples and a SAS macro are provided | sample, rank test, wilcoxon signed-rank, sample size, proc step, macro definition | source | 2 |
| 74 | Exploiting the Scheduling Algorithms in SAS/OR Software | Radhika V. Kulkarni | The scheduling algorithms that are part olthe SAS/OR soft· ware product, when combined wfth the flexible programming and graphical tools available in the SAS* System, provide a rich environment for modeling problems that arise in pro· duction and operations management. The main purpose of this paper is to show that the use of the CPM procedure is not Iimfted to tradftional project management sruations. Several heuristic algorithms used in job shop or flow shop scheduling can be easily programmed using PROC CPM, as shown in this paper. In addftion, some of the new fea tures in PROC CPM that allow you to associate calendars with resources and specify resource driven durations are illustrated in a manpower scheduling example |
proc step, cpu time, resource allocation, proc means | source | 12 |
| 75 | Exploring Broadway with SAS/ETS: A Statistical Analysis of the Acting Profession | Joseph E. Earley, James D. Ryan, Archie J. Calise |
proc step, time series analysis, regression analysis | source | 3 | |
| 76 | Exploring Data With Base SAS Software | Thomas J. Winn Jr. | Statistical methods are tools which are used to summarize and analyze data. Exploratory data analysis is the application of graphical and statistical techniques to discover the structure of data. The goal of exploratory data analysis is to characterize the data and to reveal fundamental relationships among them. It is quick, dynamic, and highly interactive. Furthennore, exploratory data analysis is not just for use by professional statisticians - the methods also are used by scientists, engineers and many other types of researchers. This paper explains how to produce and to interpret scatter plots. histograms, stem-and-Ieaf plots, box-and-whisker plots, and various descriptive statistics, using Base SAS software | proc step, central tendency, exploratory data analysis, data science, interquartile range, proc univariate, correlation, numeric variable, proc corr, standard deviation, sas base, cv, proc freq, proc means, bar chart, box plot, data analyst, raw data, dataset, histogram, outlier | source | 6 |
| 77 | Find the Fish: using PROC SQL to Build a Relational Database for a Mark-Recapture Study | Mary C. Fabrizio, Scott R. Nelson |
Reliable estimates of abundance and survival, gained through rrarl<-recaptwe studies, are necessary to better understand hoNto manage and restore . lake trout populations in the Great Lakes. Vlbrking with a 24-year data set from a rrarl<-recapture study amducted in Lake Superior, we atterrpted to disdose information on tag shedding by exarrining recaptures of doltJIe·tagged fish. The data set oonsisted of 64,288 observations on fish which had been marl<ed with one or rrore tags; a subset of these fish had been marl<ed with two tags at initial capture. Although DATA and PROC statements could be used to obIain some of the information we sought these stalements could not be used to extract a CIJIllllete ~ of results from the double-tagging experiments. We therefore used SOL processing to aeale three tables representing the same information but in a fully namaliZed relational structure |
proc step, flat file, proc sql | source | 6 |
| 78 | Finding Business Solutions by Extending SAS/EIS Applications | Merry G. Rabb, Ben Cochran |
SASIEIS software provides an interactive applications development environment and toolkit that can be very useful for building end-user applications. The application objects provided in the pnxfuct range from ones that are used to issue a simple command to the much more complex Variance Report or Business Graphics application objects. Applications developers who are new to SAS/EIS sometimes find that the pre-existing objects provide much of the functionality they need in their EIS (executive information system), but only up to a point. Eventually, they get to the stage where they must extend their E1S by making use of the other tools provided as part of 1he SASe System. Ttis paper addresses some strategies for extending your SASIEIS applications. We present examples of business information delivery needs that you may have and then present we a possible solution |
sample, proc step, proc report, class variable | source | 9 |
| 79 | Flipping Your List: Using the REVERSE Function to Break Up Text Strings | Lary Jones | source | 2 | ||
| 80 | Forecasting Operational Indices Using SAS/ETS Software | Laura McCarty | feature selection, confidence interval | source | 5 | |
| 81 | From 'A' to 'VSE': Questions Most Frequently Asked about the SAS System under the VSE Operating System | Catherine B. Corbett | Catherine B. ColbBtt is a senior. systems developer in the Host Systems Division at SAS Institute. Her areas of expertise include the VSB operating system, SAS data library 00, host options and host windows. Catherine has a BS degree in computer science from the University of North Caronna at Chapel HI7L She has been a SAS software user for seven years. 10 some users of Release 6.08 of the SAS System under the VSE operating system, the SAS System is new and unfamiliar, but VSE is not. To others, VSE is new, but the SAS System is not. Regardless of your ~rience level with the $AS System or whh VSE, this article will answer practical programming and opera tions questions to help you effectively use many of the powerful features of Release 6.08 of the SAS System under VSE | libname statement, sas base, options statement, proc step, filename statement, proc upload | source | 11 |
| 82 | From the Ridiculous to the Sublime: Getting Files from There to Here | Tamara R. Fischell, Robert H. Upson, Gail M. Barnes |
proc step, proc copy, dataset, sas library | source | 9 | |
| 83 | Gems in the FORMAT Procedure | Aileen L. Yam | This paper makes use of gems in the FORMAT procedure to obtain efficiency, precision and flexibility in programming. A real-world application in the pharmaceutical industry is pro-oided to illustrate that creati-oe use of the VALUE statement in the FORMAT procedure together with the ROUND function has the benefit of attaining efficiency and the precision in unit con-oersion that are otherwise obtained with many IF-THEN statements and clumsy computation. In -oersion 6 of the SAS System, the flexibility and efficiency of creating and maintaining user-defined formats are expanded by the CNTLIN option. The application is further enhanced with the CNTLIN option |
proc format, proc step, numeric functions | source | 6 |
| 84 | Getting Intimate with Extended Tables | Karen Crandall | do loop, automatic variable | source | 10 | |
| 85 | Getting Started with Interactive Programming | Ted Bandy | This workshop introduces you to both the technique and the art of programming in the SAS Display Manager System. an interactive environment in base SAS software. At the beginning of the workshop a step-by·step approach will be used to teach you the basics of programming in the display manager. You wilileam how to edit and submit programs. to view and to PRINT procedure output, and to save programs. Next, you will be taken through a series of examples to demonstrate that the display manager is an efficient and convenient environment for working with SAS data sets and for testing and developing programs. A sampler of interactive tools available in the display manager will also be demonstrated. These tools include the hierachialty arranged data management windows. interactive procedures, and graphics. The display manager can be customized to your individual preferences and work habits |
proc step, proc reg, sas log, proc sql | source | 9 |
| 86 | Getting the Most from the SAS LOG | Robert G. Hall, Judith H. Mopsik |
merge statement, input statement, missing value | source | 6 | |
| 87 | Give Your MVS Users Equal Access | Scott G. Maurer | The SASe system provides many tools for users to access their data once the physical dataset is defmed via the LIBNAME Statement. The LIBNAME and FNAME windows under DMS provide users access to "allocated" datasets. To aIlocate a new !ibref or fileref MVS users often find themselves exiting SAS to use utilities such as ISPF /PDF just to locate the name of the dataset. The SAS system under GUI platforms such as OS/2 provides tools for the user to scan devices and subdirectories for the desired file name. This paper describes a tool that facilitates MVS catalog searches in a SAS full-screen environment. This tool, caIled MVSCT, uses SAS/C" to interface with MVS routines. SASrroolkit" is used to provide a SAS callable function capability and SAS/ AF"' to provide the user interface |
if-then-else, catalog entry | source | 6 |
| 88 | Graphical Analysis of Multidimensional Ecological Community Data | E. Barry Moser | In the study of ecological communities it is very common to make environmental measurements on many subjects on each of sev· erat species, and then to order the species along real or hypothe sized environmental gradients. Examples would include fish collections where salinity and water quality measurements are also made, or foraging birds in a forest where the foraging heights in the trees and the type of foraging maneuvers used by the birds are recorded. Because of the complex associations of the species and the ordination technique applied, the ordinations may be non linear and difficult to interpret if only a numerical summary of the data is used. Biplots and graphical displays of ordination and clus· tering analyses, including the minimum spanning tree, can greatly aid in the interpretation of the species' associations and with their relationships to the environmental gradient | proc corresp, proc freq, data visualization, sample, proc princomp, macro definition, regression analysis | source | 6 |
| 89 | Graphical User Interface to Report Generation in a Pharmaceutical Environment (Using SAS/AF Software FRAME Technology to Keep Your Head Above Water) | Ken Salatka, Nancy Brucken |
This paper describes the user interface developed at PARKE-DAVIS Pharmaceutical Research. This interface is used as part of a CANDA (Computer Assisted New Drug Approval). The system was developed with SAS/AF' FRAME software. Two important aspects of any New Drug Approval are listing tables that contain all patient information and summary tables that describe the safety and efficacy of the drug. We have developed a reporting system that allows any user to qUickly produce and review' a production quality report (listing or summary table). This is an object orientated ·point and click" system that will execute SAS' Base software to produce the desired output |
macro variable, by group processing | source | 6 |
| 90 | Guided Data Analysis with SAS/LAB Software | Katherine J. Roggenkamp | outlier, anova, data visualization, class variable | source | 10 | |
| 91 | Hierarchical Reporting (Mimicking Data Base Using SAS/AF) | Alex Ostrovsky | When 8 report has several thousands lines. It is limost impouibIe to review on-line. Even the PROC REPORT is a subject 01 this "Von Neuman Curse" - rigid sequentlafrty. This paper explains how to build and Implement an on-line data _r. which allows you to ... an overall summary or you- data. then to 'dr1ll down' on selected foelds to cisplay detaH lines that make up those siat .. ments. Therelore you can target SpecifIC ar_ or Interest without hav Ing to view or IICfOII an entire report. This is a two step procedure. First. lor each subtotallevet In the report a DATA member Is bum; I.e .. each _ is represented wtth Its own DATA. all In the Ame LIBREF. The lowest _ is a window to the INFILE. Each oo-vallon on this level Is actually net or detail obser vations grouped together " as many as wtU Hli up the screen leaving room lor the header and bottom fines. By paging back and lorIh you can see the wIloIeINFILE. The next levet DonIains fins! subtotals only, grouped the same way |
proc step, macro conditional | source | 3 |
| 92 | How to Downsize a Mainframe SAS Application to the OS/2 Platform | Barry R. Cohen | This paper provides a tutorial for developers who are considering downsizing mainframe SAS applications to the OS/2 platform. The various issues you can expect to face in your downsize project are introduced, and guidance is given for handling these issues. The ~or issues covered are (1) designing the OS/2 directory structure, (2) porting the code, (3) changing code for file access, (4) the user interface, (5) backup and printing, and (6) the data download | filename statement, sas base, sas library, proc step, dataset, libname statement, macro variable | source | 9 |
| 93 | How to Write a Macro to Make External Flat Files | H. Ian Whitlock | This paper is an expanded version of -A Macro to Make External Rat Files" given at SUGI1S. In addition, several corrections to tho macro have boon made and ~ has boon Improved through tho uso of CALL EXECUTE to dump tho linal stop in tho input stack. The original macro used arrays of macro variables created by CALL SYMPUT to write tho final stop. Tho array processing can be significantly slower. A SAS macro to construct oxtemal flat files from SAS date sots is considered from the view point of the user interface; The central issue is * How do you give the user as much control as he wants without requiring more work than it takes to write out the whole program? Tho universaJ~ of tho problom and tho simplicity 01 tho 'PUT statemont DATA stop program mako ~ a clessic macro problem. The topic is presented as a tutorial teaching how to develop a SAS macro. A plan is laid out, tho paramoter interface as a system of defaults is discussed, and then the macro code is prosonted | proc contents, proc step, dataset, numeric variable, call execute, flat file, macro variable, sysdate9, macro loop, macro definition, macro call, macro quoting function, %if-%then-%else | source | 9 |
| 94 | Importing SAS Graphic Files into WordPerfect (Comparing Several Device Drivers to Determine Which Produces the Best Result) | Lori D. Griffin | This paper demonstrates several different device drivers that were used to import a SAS graph into WordPerfect. The ultimate goal was to determine which device driver displayed the best result Criteria for best result was that the imported WordPerfect graph closely resemble the original graph. A comparison process took place between examples of each imported WordPerfect graph and the original graph. Several aspects were taken into consideration in this process, such as color to color transfer, font styles, and the size of the files that were compared. Two different graphs, an annotated pie chart and a scatter plot, were taken through this comparison process. (The following paper does not include the scatter plot printouts. For a copy of these results, contact the author.) The comparison process began with the device drivers recommended by WordPerfect. Next were the device drivers recommended by SAS. Concluding the process was a modified SAS device driver | scatter plot, bar chart | source | 5 |
| 95 | Insuring Down-sizing Is Right-sizing with SAS/OR Software | Douglas L. McAllaster, Andy Parks |
The Army is down-sizing. senior Army leaders want to insure that the Army retains enough commis sioned officers in each career field so that the Army can fill its jobs at the conclusion of the drawdown. This paper de scribes the use of SAS/OR PROC NETFLOW to determine the number of officers, by career field, that the Army must retain in order to fill its jobs. Retain ing enough officers, having required skills, insures that down-sizing is right-sizing |
proc step, character variable | source | 5 |
| 96 | Integrating SAS Software into a Telephone Information Retrieval System (TIRS) | Shikha Khan, Derek Drummond |
One of the hottest new technological advances involves the use of telephones to interact with computers and retrieve information. Members of the financial industry develop and use such systems to provide over·the-phone services such as balance inquiry, current loan rates, etc. Until recently, other industries have not employed such technology. Washington Gas, a Washington D.C. area utility company, and esc Professional Services Group have made a breakthrough, developing a Telephone I nformation Retrieval System (1"1 RS) that uses SAS/AF'" and SAS/SHARE" software to retrieve up-to date information on participants in Washington Gas' energy conservation programs. Residential customers who apply for energy conservation incentives can call the TIRS to check the status of their incentive application. This service is normally available 24 hours a day, whenever the Washington Gas mainframe is available |
batch job, sas library, dataset, proc step | source | 4 |
| 97 | Integrating Statistical Information into Graphical Displays | Susan J. Kenny | proc step, proc freq, txt, frequency analysis, data visualization, macro variable, proc gplot, anova, proc anova, post hoc test, regression analysis, proc reg | source | 10 | |
| 98 | Integrating the SAS System for Personal Computers into Your Enterprise | Gary Mehler | traffic data, proc step, network data | source | ||
| 99 | Interactive Data Management and Analysis Using JMP Software, SAS Software, and OpenVMS in a Networked User-Friendly Environment | David N. Ikle, William F. Kastner |
Large clinical investigations involving multiple investigators present problems in the design, implementation and support of data management systems that are reliable, flexible and easy to use. The data must be of high quality and reflect current project status, and numerous staff having varying computer skills must have access to the data. Current technology makes it unnecessary for clinical investigators to be insulated from their data by numerous layers of programmers and biostatisticians who become part of a batch process of query and analysis. A computing environment has been developed using Base SAS software, SAS/AF and SASlFSP to create a data entry and validation system on a VAXstation 4000 workstation running OpenVMS and PathWorks. An image of the relational SAS data base is accessed by investigators as SAS transport data sets through a network utilizing AppleTalk and Ethemet protocols |
data cleaning, data science, data governance, proc step | source | 5 |
| 100 | Interactive Report Writing with the REPORT Procedure | Alan Eaton | PRoe REPORT is a tool for both interactive and batch reporting. Users are able to design reports in teractively and see the impact of their design changes immediately. Reports can be simple listings or com plex presentations of grouped observations, summary lines, and computed columns. In this workshop users will design several reports using the interactive tools of PROe REPORT. The reports will incorporate excep tion reporting, drill down, and the use of customized pull down menus | proc report, proc step, catalog entry | source | 5 |
| 101 | Interapplication Communication through Object-Oriented Programming with SAS/AF Software | Joseph M. Carter, Randy Pierce, Duane E. Ressler |
The introduction of object-oriented programming (OOP) features in SAS/AF software provides applications developers with enhanced capabilities for achieving greater communication between applications .. Classes that are developed within an organization can be shared across the organization more effectively with the use of application tools. This paper advocates utilizing OOP features to develop an application 1001 set that establishes a protocol for managing communica1ions between classes and applications. The importance of assigning a person to administrate classes and applications is also emphasized |
catalog, transaction data | source | 2 |
| 102 | Interpreting Complex Nonlinear Models | Lawrence C. Marsh, Maureen A. McGlynn, Debopam Chakraborty |
This paper demonstrates the use of SAS software in the systematic evaluation and interpretation of complex nonlinear models. The impact of a unit change in one explanatory variable on the dependent variable of a nonlinear model is difficult to determine since the change in the predicted value is conditional on all of the other variables for that observation. Furthermore, attempts to approximate this relationship have proven inadequate and often meaningless. In this paper. we present an a1temative | predictor variable, response variable, proc nlin, neural network, network optimization, logistic regression, sample, logistic distribution, regression analysis, likelihood function | source | 5 |
| 103 | Interval-Censored Survival Data | Ying C. So | There are often times in statistical data analysis when a specific methodology is called for, which is not pro vided by SAS/STAT software. In many situations, the analysis involves maximizing a certain function that is nonlinear in the unknown parameters. The. estimation of these parameters requires an iterative scheme, which is often difficult to program. Starting in Version 6.08, SAS/IML software provides many nonlinear optimization functions that are useful for implementing specific inhouse methodology. As an illustration, this paper implements the methodology of computing the classical estimates (Peto 1973, Turn bull 1978) of the survival curve for interval-censored data. The regression analysis of Finkelstein (1986) is also considered |
likelihood function, censoring, regression analysis, maximum likelihood estimation, proc phreg | source | 7 |
| 104 | Introducing SAS/PH-Clinical 2.0 Software | Sandra D. Schlotzhauer, Andrew T. Fagan, Martin F. Michael |
source | |||
| 105 | Introduction to FRAME Entries in SAS/AF Software | John C. Boling | dataset, return, conditional do loop, response variable, date variable | source | 8 | |
| 106 | Introduction to Pull-Down Menus | Roger Staum, Jeremy Staum |
Pull-down menus, or pmenus as they are known In the SAs.. system, are a key component In creating modem, inleracti'le appIicaIioolS. This I\ItoriaI will help you become a more effective user or developer by explaining: tum pmenus on and off pmenu components binding 1.-10 create custom pmenus 1.-10 assign pmenus 10 windows pselldocommands | proc step, run | source | 6 |
| 107 | Introduction to Repeated Measures | William G. LeBlanc | response variable, covariance, proc step, proc glm, correlation, proc genmod, univariate analysis, class variable, compound symmetry, residual, null hypothesis, f-test, interaction effect, anova, p-value, variable list | source | 9 | |
| 108 | Introduction to SAS/CALC Software | John C. Boling | SAS/CALC software provides all-purpose spreadsheet capabilities for information management. Spreadsheets provide robust data modelling behavior. Although financial applications are typical exam· pies, mathematicaJ and statistical applications such as Monte Carlo 5imutations can also exploit the spreadsheet's capabilities. This paper highlights the major features inCluding importing and expon ing files, two-dimensional and three-dimensional spreadsheets, link ing, consolidation, formulas, program entries, integrated graphics, and goal seeking. Structure SAS/CALC applications are based on spreadsheets which are tables of rows and columns. Although financial or ledger sheet appli cations typically come to mind, any infonnation that can be repre sented as a table of rows and columns can be placed into a spreadsheet. +CA1.(: r I nVl .CAl.C It) ______________ _ I rUe "it Vi ... Ineut. Cbarts Locall G10bds Hell' 1 , . 1 1110_ ... d CUll rlo .. Stato_lIt 1 |
dataset, catalog entry | source | 4 |
| 109 | Introduction to Scientific Plotting Using SAS/GRAPH Software | Irene Mendelson | This paper will give a quick introduction to SAS/GRAPH- with an emphasis on preparing graphics for a scientific presentation. This is illustrated using three basic· graphic types of particular interest to scientists: an introductory page of text, a bar chart, and an X-Y plot or line graph. All of these examples use the strategy of starling out simple using all of the defaults and then enhancing this ugly graph with several key options. The paper concludes with a short discussion of how to produce hardcopy output on several popular output devices and has been updated with some useful items new with SAS 6.06 and 6.07 |
bar chart, title statement, proc step, proc gchart, proc gplot | source | 6 |
| 110 | Introduction to SCL Lists | Roger Staum, Jeremy Staum |
The SCl list is a ftelCibie and powerful __ '" which first appean!d In version 6.07 of the SAS sysIem. This tutorial will help you: utKlersland what SCll1sIs 811!, and hoW they diller from oIher _structures learn list terminology c:ategorize lists and Items by access. type, and attributes manipulate lists using SCl functions and routines * decide when your application might use lists | catalog entry, numeric variable | source | 6 |
| 111 | Introduction to the UNIVARIATE Procedure | Kim L. Kolbe Ritzow | PROe UNIVARIATE is a powerful BASE SASe PROe that combines many of the features found in other analytical PROes such as FREQ, MEANS, | proc step, proc univariate, box plot, dataset, proc freq, histogram, by group processing, sample, interquartile range, normal distribution, standard deviation | source | 8 |
| 112 | IntroductiontotheSCLDebugger | Lynn T. Julian, Raymond E. Barnes |
proc step, do loop | source | 9 | |
| 113 | Keys to the DATA: Using the KEY= Option on the SET Statement | Ben Conner | One of the most efficient and powerful features to come out of SAS release 6.07 is the KEY = option on the SET statement. In many cases it rivals the conciseness of SOL for merging data files while retaining all the flexibility of DATA STEP programming. This paper discusses the advantages of the KEY = option and the pitfalls to avoid when using it |
set statement, proc step | source | 3 |
| 114 | Local SAS Users Groups Remove Barriers to Information/Experience Exchange: the WISAS Model | LeRoy Bessler | source | 4 | ||
| 115 | Log Negative Binomial Regression Using the GENMOD Procedure SAS/STAT Software | Joseph M. Hilbe | The negative binomial model is a member of the GLM..type exponential family of distributions. The Iog-linked form of the distribution allows useful modeling of many types of overdispersed count data. The mathematical properties of the negative binomial are derived and a GLM-Iype Log Negative Binomial (tHB) macro is developed using the SASlSTA" GENMOOo Procedure. Applications In terms of .-irnulation data and a clinical study are presented and modeled. KEY WORDS: SAS/STAT. GENMOD Procedure. Generalized linear model. Poisson. Overdispersion, Negative binomial. Log negative binomial |
binomial distribution, negative binomial regression, poisson distribution, regression analysis, proc genmod, goodness of fit, likelihood function, poisson regression, proc calis | source | 6 |
| 116 | Macros - the GOOD, the BAD, and the OBNOXIOUS | Margaret K. Schrempf | In 1982 the SAS Institute introduced to SAS programmers the MACRO facility and Language. Approximately 6 months after this introduction a strange and until now, unidentified disease began to pervade the SAS programming community. Left untreated MARCOITIS causes indecipherable black boxes disguised as MACROS in SAS programs throughout the nation. Macros can make life as a SAS programmer easy or can become a nightmare of maintenance and support. There bave been many GOOD MACROS and MACRO applications that bave been written. Unfortunately, the BAD and the OBNOXIOUS far outweigh the GOOD. It will be intent of this paper to arm our community with the tools to identify the symptoms of MACROITIS, create preventative treatment, and for severe cases introduce a new innovative vaccine called MACRO | sas programmer, default parameter, data step, macro loop | source | 5 |
| 117 | Macros and Functions in C and SAS Software | Lillian L. Randolph | Lillian L. Randolph, Ph.D. American Medical Association Chicago, Illinois Macros and functions are procedures which offer pro grammers both advantages and disadvantages in writing efficient and understandab~e code. Some advantages are cammon to both procedures, while others result from either the one or the other. In C c~ared to BAS software, programmers have a greater freedom to define macros and functions, although both procedures are p~entifu~ in both ~anguages. Therefore, understanding the contributions of macros and functions can ~ead to rationa~ choices in programming and to overa~~ better code. 394 | macro call, macro function | source | 5 |
| 118 | Macros Made Simple | Tom Mannigel | macro definition, macro variable, macro facility, &variable, proc step, macro loop | source | 5 | |
| 119 | Macros Made Simple: An Introduction to the SAS Macro Facility | Almira A. Dumaual, Timothy E. Cooley |
macro variable, macro definition, macro facility, macro loop, if-then-else, stored macro, %if-%then-%else, call execute, do loop, proc step, conditional do loop | source | 8 | |
| 120 | Macros Simply Stated | James C. Stokes | AI1hough!he term MACRO does sound a btt forbidding, tt's bark is certainly worse than it's bite. Using MACROS eliminates the need for repetitious coding and generally makes maintaining code much easier. This paper will describe what a MACRO is, how to identify when using a MACRO would be advantageous, how to define a MACRO, how to call a MACRO, and define and describe MACRO variables both SAS-defined and User-defined. MACRO Defined A $AS Macro is a collection of SAS statements stored either 'temporarily or permanently under a MACRO name that can be repeatedly invoked during the execution of a SAS program. When MACROs should be used Anytime you find yourself coding virtually the same syntax with minor variations in the same program. chances are that the code could be greatly reduced by defining it as a MACRO. In addition, by reducing the amount of code, maintaining the program is simplified. Consider the following example: Example A | macro variable, macro call, macro definition | source | 2 |
| 121 | Making the Crystal Ball Clearer: Using the SAS System to Develop a User-Oriented Demand Forecasting System | Michael F. Reed | Demand forecasting for short-term operational planning is a task not well understood or executed in most organizations. Generally speaking, corporate efforts at demand forecasting are sporadic, not well received, and not well understood. In effect, most demand forecasters are viewed as gypsies reading a crystal ball. Using the SAS System, an organization can capture the data needed, analyze it, process it and present it in a way that makes the crystal ball clearer | regression analysis, demand forecasting | source | 2 |
| 122 | Managing Census Data to Improve Public Response | Jay K. Keller | regression analysis, correlation | source | 9 | |
| 123 | Managing Clinical Lab Data with SAS/ AF Software - an Online Demonstration | Eric C. Brinsfield, Bradley W. Klenz |
laboratory data, data governance, clinical research, data cleaning | source | 4 | |
| 124 | Managing Large Financial Data with Ease: CRSP, COMPUSTAT, Etc., with SAS | Paul J. Ratnaraj, Carol M. Katzman |
During the past decade use of large and complex data sets across academic environments has grown substantially. This usage explosion has compelled schools to experiment with better access and management methodologies for a diverse and very dynamic user environment. In addition to budgetary constraints, there are constant changes in computing technology. This paper describes the changes that the Wharton School is making to better manage its information delivery strategies and objectives. The paper highlights the transition from using traditional languages like Fortran and in-house developed systems to commercial database management products, to SAS and Hs newly released SASlETS DATASOURCE procedure. The paper also discusses the merits and disadvantages of the various methodologies and the reasons for using a unified data management and analysis tool for infomlation delivery in an academic environment |
dataset, time series analysis, data governance | source | 5 |
| 125 | Managing Your Phone Calls in a Help Desk Environment | Mary A. Garner, Lisa P. Wayte |
User Services is a division of Computer Services at the University of Central Florida, who provide help desk support. The help desk is available for all software and hardware problems. The help desk handles over 19,000 calls a year with an average of 74 to 100 calls a day. The phone calls are logged in an on-line system called Phonelog. level 1 support answers the phone and logs all calls as they come in. If the phone call is more technically involved than level 1 's expertise or is too time consuming then it is passed to level 2. At this time there are 2 full time staff members at each level. Our current Phonelog was written in REXX'" on an IBM 4381 running under IBM VM/CMS'" 3 years ago. The current system accesses an IBM SQUDS'" database with over 10,000 entries. Due to the large volume of calls to the help desk, the database continually grows and expands. Over the last year the volume has grown to the point that the old system requires constant maintenance | master data management, proc freq | source | 5 |
| 126 | Mapping - a Strategy | Stephen M. Noga, Heather Gorski |
In our job, we produce several books and studies a year about the nonprofit sector and the charitable behavior of Americans. We use different components of the SM3" system to do the "leg" wCHk (data manipulation, statistics, and graphics) neoessary for producing a publishable product. This paper concentrates on the graphical aspect of production, spec~ically using some of the features of SASIGRAPH in designing and constructing various styles of maps. We try to utilize the SAS system as much as possible in production even thoogh other commercial packages, such as Corel or Maplnfo, may be better suUed to the production of graphics and maps. We stay with SM3 because we use U in the inUiaI step of data management, and we find working with one system as much as possble is more efficient than continually transferring data and other information to different software packages | proc gmap, proc step | source | 6 |
| 127 | Maximize Return on a Minimal Software Investment: Build an Online VIS (Visual Information System) without SCL | LeRoy Bessler | sas base, batch job | source | 5 | |
| 128 | Menage a Trois - UNIX, SCL, and SAS/SHARE Software! | Marge Scerbo | sysrc, where statement, libname statement, proc step | source | 5 | |
| 129 | Migrating to SAS 6.08 for Windows: The Merck CANDA Experience | Frank S. Palmieri, Rob Rosen, Wanda Bidlack |
dataset, data science, proc sort, catalog entry, data wrangling, proc step | source | 6 | |
| 130 | Mixed Model Analysis of Data: Transition from GLM to MIXED | Ramon C. Littell | The GLM procedure has been the workhorse for mixed model applications in the SAS System. Other procedures, including NESTED and VARCOMP, are used for specific applications. Since its introduction in 1976, GLM has been enhanced with several mixed model facilities such as the RANDOM and REPEATED statements. However, there are aspects of certain models that none of these facilities fully accommodate, such as structured covariance matrices for repeated measures data. The MIXED procedure allows applications of models previously not possible within the SAS System. In this paper, an overview comparison is given between GLM and MIXED. Examples will be presented comparing output from both procedures when either is appropriate to assist users in the transition from GLM to MIXED. Other examples will be presented which illustrate the use of MIXED in applications for which GLM is not adequate |
covariance, proc genmod, proc calis, proc mixed, proc step, restricted maximum likelihood, degrees of freedom, likelihood function, covariance structure, anova, fixed effects, p-value, estimate, repeated measures, proc glm, standard deviation, correlation, response variable, f-test | source | 8 |
| 131 | Model Diagnostics for Three Factor Models | Eric P. Smith, Kyoungah See |
Three factor experiments can be difficult to analyze, especially when there is only one observation per cell. For the two factor experiment with one observation per cell, research has focused on tests for interaction (such as Tukey's test for nonadditivity), modeling the interaction using multiplicative models and model diagnostics using the biplot display. The biplot display is a plot associated with the decomposition of the two way table and interpretation of the results in terms of the parameters of the two factor model. Extending the biplot to more complicated models is difficult because there is not a simple extension of the singular value decomposition. This paper discusses a plotting technique which is useful for visualizing three factor data. The method is based on three way principal components analysis and uses joint plots of effects to assess the model. The method is also useful for detecting outliers, finding submodels and for evaluating effect sizes and differences | interaction effect, proc princomp, main effect, outlier | source | 5 |
| 132 | Monitoring a Supplier's Quality Performance: A Drilldown Approach Using SAS Software | Patrick D. Bivens | Caterpillar Inc. developed a supplier quafity system that uses drilldown capabilnies to provide information conceming a supplie~s performance. The system was designed and developed intemally for Caterpillar Inc. using SAS software. This paper focuses on the use of SAS software to develop a user interface that significantly reduces the time required to gather the data relating to a supplie~s qualny performance. INmODUCTION A supplie~s qualny performance is critical to any business seeking to maintain high levels of customer satisfaction. Caterpillar Inc. has striven since 1985 to achieve one standard source to retrieve a supplie~s quality performance, Part of achieving this goal was the development of the Supplier Oualny Report Card (SORC) that mon~ors a supplie~s total qual~y performance | macro definition, proc step | source | 4 |
| 133 | Most Effective Use of PROC GMAP: Solutions for Professional-grade Statistical Mapping | LeRoy Bessler, Steven J. Subichin |
proc gmap, proc step | source | 6 | |
| 134 | MOVE=(+0, +5): Making SAS/GRAPH Work For You | Deb Cassidy | This paper shows you some of the options for enhancing your graph. The following code created a basic graph in | proc step, run | source | 6 |
| 135 | Moving Off the Mainframe: Downsizing and Cost Reductions | Bruce Andrais, John Kirtz |
Recent government budget restrictions have had a significant impact on administrative and support functioning at AADAC (the Alberta Alcohol and Drug Abuse Commission). In response to these restrictions, it was necessary for AADAC to completely re-engineer its SAS based corporate information systems. As a resuH of this re-engineering, corporate information system costs were cut by more than 90%, the number of staff was reduced and processing time was decreased by 66%. In addition, all transition costs were recovered within the transition year. These resuHs were achieved by changing how corporate information was handled and by using different, more efficient computer hardware and software to do the job | data cleaning, audit trail | source | 5 |
| 136 | MrPD - A SAS Software Application of Optimization of Multiple Responses Using Desirability Functions | Walter T. Morgan, Ray W. Hawley |
MrPD (Multi-property Robust Product Design) is a SAS software application that implements the technology for mUlti~le response optimization of Derringer and Suich using desirability functions. Using the powerful capabilities of SAS Screen Control Language, the application leads the product developer through the optimization process of finding the product configuration that provides the best balance of response values. MrPD combines regression models fit to individual responses v.ith desirability functions to produce an overall desirability surface, while strong graphic capabilities provide an intuitive feel for results. The maximum for overall desirability locates the optimum configuration. Extra features include capabilities to save regression models and desirability functions fitted, and the assignment of weights to responses to explore the impact of individual responses on the optimum configuration | regression analysis, response variable, geomean, median | source | 6 |
| 137 | Multiple Applications in SAS Software | Jonathan M. Siegel | SAS Software allows users to open multiple application windows at the same time, giving users power and flexibility to extend and combine applications. However, developers should provide safeguards when you desigu applications which may be open in conjunction with others. This paper illustrates the benefits of having mUltiple applications. It explains why safeguards are needed and how to provide them. Examples emphasize the IBM OS/2 operating system, but apply generally | create table, proc sql | source | 6 |
| 138 | Multivariate Analysis of Employee Surveys &Customer Surveys: Using New Computer Technology to Collect, Analyze, &Display Data | Palmer Morrel-Samuels | An example of a customized employee survey is examined. The theoretical foundation of the work is outlined by describing recent advances in psychology and computer technology, and by describing recent research (by Kaplan and Norton, 1992, 1993) on the Balanced Scorecard. Muttivariate statistics are used to examine the links that exist in the customer's company between employee motivation, productivity, quality, and profitability | regression analysis, logistic regression | source | 5 |
| 139 | N/C Milling Machine Capability Study - Resultant for all parts | Christopher L. Bonar | sample, proc step | source | 10 | |
| 140 | Neural Network Implementation in SAS Software | Warren S. Sarle | The estimation or training methods in the neural network lit erature are usually some simple fann of gradient descent algo rithm suitable for implementation in hardware using massively parallel computations. For ordinary computers that are not mas sively parallel. optimization algorithms such as those in several SAS procedures are usually far more efficient This talk shows how to fit neural networks using SASJOR , SASJETS , and SAS/STA Tsoftware |
proc step, neural network, regression analysis, macro loop, proc model, proc reg, logistic distribution, residual, proc fastclus, macro variable, macro definition, sample, data science, proc genmod, macro conditional | source | 23 |
| 141 | Neural Networks and Statistical Models | Warren S. Sarle | There has been much publicity about the ability of artificial neural networks to le:ilT1 and generalize. In fact. the most commonly used artificial neural networks, called multilayer perceptrons. are nothing more than nonlinear regression and discriminant models that can be implemented with standard statistical software. This paper explains what neural networks are, translates neural network jargon into statistical jargon. and shows the relationships between neural networks and statistical models such as generalized linear models. maximum redundancy analysis, projection pursuit. and cluster analysis | neural network, regression analysis, proc princomp, proc nlin, response variable, predictor variable, proc reg, logistic distribution, cluster analysis, unsupervised learning, data science, i/o, sample, maximum likelihood estimation, training set, simple linear regression, discriminant analysis, likelihood function, dimensionality reduction, euclidean distance, polynomial regression, sample size | source | 13 |
| 142 | New Developments in SAS Three Dimensional Visualization | Stuart A. Nisbet, Ali Dogrusoz |
In this paper, we present some of the current three-dimensional visualisation development efforts of the computer graphics division' at SAS Institute. We will discuss the current functionality in SASISPECTRAVIEW'" and SASINVISION" software. We also discuss a new product, tentatively called NAVIGATOR as well as ideas for their future directions and applications. Although it is in the R&D stage. we have included it in this paper to provide a feel for some of the avenues we are exploring in this ever-growing area of three-dimensional computer graphics | data visualization, scatter plot | source | 5 |
| 143 | New Features for Remote and Open Access to Enterprise Data: Enhanced Distributed Data Access through Multiple Engine Architecture | Jack Wallace | Access to data from the SASe System Is constantly being expanded and enhanced. In the last year. features have been released that allow transparent access to remote data on machines with different machine architectures (called remote library services). A new feature in development will OPEN access to SAS Data for non-SAS applications (such as Microsoft Word) which utilize the OOBC API In a Windows environment. These new features are built on a modular system architecture that often provides more than one way to accomplish a given distributed data access task. To choose the best method, It Is adVantageous to understand the processing performed by the components of Multiple Engine Architecture. Future enhancements for remote and open data access are also dependent on this architecture. This paper Introduces the new features but concentrates on the archHecture and Irs Implementation | source | 10 | |
| 144 | New Features in SAS/TOOLKIT Software | Richard D. Langston | There are several new platforms on which SASfTOOLKIT Software became available in Version 6.09 and Version 6.10 of the SAS" System. Also, two new primary capabilities, SOL pass-through engine writing, and Access Method Services implementation, will become available during Version 6. And in addition, a new user interface is being prepared for release which will make developing easier for SASlTOOLKlT Software users. This paper discusses the new platforms and the new features. INTRoDucnON The purpose of SASITOOLKIT SoftWare is to provide programmers the ability to write their own SAS procedures. functions, formats, informats, and engines | sample, filename statement, proc sql, proc step | source | 3 |
| 145 | New SAS System Features for Experienced Programmers (Or, TeachingOldDogsNewTricks) | Earl R. Westerlund | The SAS" System has always been easy to use and flexible in its ability to read, manipulate and present data and information. That, combined with SAS Institute's constant additions and refinements, is why so many users are so loyal. There is one drawback to this constant addition of new products, features and options, however: it is now nearty impossible to keep up with the SAS System. Between the flood of "Changes and En hancements" technical reports, and the day to day pressures of getting work done, there is a strong temptation to rely on the tried and true methods of program development. After all, who needs PROC REPORT when you have PUT statements - and know how to use them? Yet it's worth the effort to keep up, because many of the new features can improve the efficiency of SAS applications, or the time it takes to develop them |
proc step, where statement, proc report | source | 5 |
| 146 | No Puts Allowed: Completely Customized Tables with the PRINT Procedure | James P. Young Jr. | The PRINT procedure has been underutilized as a tool for generating tables. It can, however, be easier to use, more flexible, and more powerful than the TABULATE or REPORT procedures, or collections of PUT statements. This is achieved by printing a single character variable that has been manipulated to resemble a table. Statistics from procedures such as MEANS, SUMMARY, or UNIVARIATE are added· to the character string by a macro, mainly by use of the SUBSTR function. If necessary, the table is built by concatenating the variable in a series of data steps, each preceded by a macro call that builds a row or several rows of the table. These data steps allow additional string manipulation. The final table is essentially a PROe PRINT of the final single-variable data set. Macro variable substitution in the TITLE and FOOTNOTE statements of PROC PRINT provides further flexibility. A final macro passes the output through a page numbering DATA STEP and does final customization |
proc print, macro variable, macro call, data step, put statement, proc step, proc freq, proc means | source | 6 |
| 147 | Nonlinear Regression Analysis and Nonlinear Simulation Models | Donald Erdman, Mark Little |
This paper is a sU/vey of SAS System features for nonlin ear models, w~h emphasis on new features for nonlinear regression. Topics include automatic calculation of analytic derivatives, estimation with noniinearparameterrestrictions, tests of nonlinear hypotheses, maximum likelihood and gen eralized method of moments (GMM) estimation, estimation of simuttaneous systems of nonlinear regression equations, and distributed lags and time series error processes for nonlinear models. In add~ion, this paper will briefly discuss solving nonlinear equation systems, dynamic simulation of nonlinear systems, and optimization of nonlinear functions. The MODEL, NUN, NLP, and GENMOD procedures are discussed | proc step, regression analysis, proc model, time series analysis, proc nlin, proc genmod, proc calis, likelihood function, response variable, maximum likelihood estimation, monte carlo | source | 9 |
| 148 | Nonstandard Uses of PROC MULTTEST: Permutational Peto Tests; Permutational and Unconditional T and Binomial Tests | Peter H. Westfall, Keith A. Soper |
The main feature of PROC MULTTEST is its calcu lation and tabulation of raw and multiplicity-adjusted povalues, when a user-defined collection of tests is spec ified. The adjusted povalues are calculated primarily using resampling methods, allowing correlations and distributional characteristics to be incorporated into the multiplicity adjustments. We discuss lesser-known applications ofPROC MULT TEST involving tests for a single variable. The soft ware computes exact permutation tests for stratified 2XC tables; we apply this method to analyze rodent carcinogenicity data with time and cause of death in formation. The test procedure is the life table method described by Peto et al. (1980), but their large-sample normal approximation to the critical value for this test can be quite inaccurate when the number of observed tumors is small. We also describe methods to ad just permutational p-values for the multiplicity of tests from separate analyses of each tumor type |
proc step, sample, binomial distribution, bootstrap, multiplicity, significance level, permutation test | source | 4 |
| 149 | Object Oriented Reports Using the FORMS Procedure | Warren Repole Jr. | proc step, label statement | source | 2 | |
| 150 | Opening the Doors to VSE | Tony Dean | This paper discusses connectivity solu tions for VSE mainframe environments. Connectivity issues must be addressed for VSE to be a viable operating system. There are two primary methods of com munication between VSE and other plat forms: 'terminal-based communication and program-to-program communication. Examples of terminal-based communica tion protocols include 3270, High-Level Language Applications Programming In terface (HLLAPI), and asynchronous communication (ASYNC). mM's Ad vanced Program-to-Program Communi cation (APPC) provides VSE with peer to-peer communication capabilities. The SAS System supports all of these com munication protocols and provides the VSE community with a variety of con nectivity solutions. This paper focuses primarily on program-to-program com munications, as the most advanced form of communication | sample, proc step | source | 8 |
| 151 | PAGE_COUNT.SAS: The Solution to Customized Pagination of Your PROC REPORT Output | Bryan K. Beverly, Phillip J. Screen |
proc report, proc step | source | 6 | |
| 152 | Playing with Macros: Take the Work Out of Learning to Do Macros | Arthur L. Carpenter | The macro language can add an additional level of complexity to programs written in SAS. Macro statements are often complicated and may use logic that appears to defy the rules used by all proper SAS programmers. Regardless of the complexities, learning to use the fundamentals of the macro language need not be difficult. This workshop will take users familiar with the basics of the SAS System and introduce them not only to the basics of the macro language, but also to 8 process for writing their own macros. The course will start with macro variables and will examine their differences and similarities to data set variables. Existing code will then be converted to macros and named and positional parameters will be introduced. Examples will include discussion on the resolution of macro variables and the use of the double ampersand (&&). Several macro programming statements, such as, %IF will be introduced along with selected macro functions | macro variable, macro facility, %if-%then-%else, proc step, proc print, macro definition, macro function, macro parameter | source | 5 |
| 153 | Preliminary Data Management and Report Generation Using the SAS System on the PC | Carmen F. Gillem, William C. Murphy, Ronald J. Billings |
Preliminary data management is often as important as the final analysis of the study information. At Eastman Dental Center, most of the complex statistical data analysis in large epidemiologic studies is performed by the biostatistician, but often the principal investigator may require interim ad hoc reports. These can be readily prepared using the SAS system. Initially. SAS language data steps are used to create a demographic database; then, PROC FREQ, PROC MEANS, or PROC SORT are used to create tables, frequencies, and lists that help the investigator track the study population. In addition, this preliminary data manipulation helps to identify erroneous variable values before the raw data files are transferred to the division of biostatistics for statistical analysis. If an error is found during the final analysis, a copy of the SAS program database is returned on a floppy disk to the project investigator and PROC FSEDIT is used to make the necessary corrections |
proc step, proc sort, data step, data science, dataset, proc freq | source | 3 |
| 154 | Principles Of Animation As Applied To SAS/NVISION | Enrique Leoni, Greg Shank |
ThiS paper abstract describes the processes involved in creating an animation short. Topics covered include developing a concept. creating a story board, producing the final video. The ideas are drawn as thumbnail sketches. These drawings should include interesting positions of the characters and dramatic camera angles, then the sketches are assembled into a storyboard. Using SASINVISION each character and prop piece is lIlen modeled and assigned attributes, for example, specularity. reflectivity, and polish. Key framing of the characters begins; the script file is saved and each scene is rendered and dumped to tape. Finally the tape is edited with sound and music | source | 6 | |
| 155 | PROC REPORT Batch Language: Tips and Techniques | Jean Hardy | proc step, proc format, proc report | source | 10 | |
| 156 | PROC REPORT: A Hands-on Introduction to the Batch Language | Ray Pass | proc report, proc step, sample | source | 10 | |
| 157 | PROC REPORT: An Introduction to the Batch Language | Ray Pass | proc report, proc step, proc print, sample | source | 10 | |
| 158 | Processing Large SAS and DB2 Files: Close Encounters of the Colossal Kind | Judy Loren, Alan Dickson |
lookup, proc sql, dataset, proc step, where statement, order by, data merging, proc append, cpu time, create table, db2 access, macro put, proc freq, macro definition | source | 8 | |
| 159 | Programming the NUN Procedure Using the Negative Binomial Yield Model for ASIC Semiconductors | Jon A. Patrick | Tbis presentation will sbow bow easily tbe negative binomial yield model is programmed using tbe SAS NLIN procedure, and describe tbe cbaracter istics of tbe output parameters: alpba - tbe cluster parameter, lambda - tbe average fault density, and y. - tbe gross yield. Tbe predicted output will be overlaid witb tbe actual data and plotted witb SAS/G RAPH. Tbe benefits to tbis metbod of cbaracterization are: Maverick product is easily identified. Yield projections on new, larger size die can be easily determined |
estimate, proc nlin, binomial distribution, sample, regression analysis | source | 4 |
| 160 | Properties of Power, An Educational Tool | Julie Wildman-Pepe, Susan C. Schott |
Power is a difficult concept for students to grasp. The purpose of this paper is to give SAS code to illustrate the various properties of power. The program is designed to be used as an educational tool for an undergraduate statistics class. Three properties are shown with the use of plots and tables. All analyses look at the large sample test of hypothesis concerning a single mean. The first property addressed is that power decreases as the value of alpha is increased. This is done by a plot of power versus alternative values of p. over varying values of 01. The 1 %, 5%, and 10% significance levels were chosen. The second property is the fact that power increases as the sample size is increased, assuming 01 remains fixed. A plot of power versus alternative values of p. with a fixed 01 shows this relationship. The third property is that power increases as the distance between the null and alternative value increases. This is shown with a specific example of Ho: p. = o versus H,,: p | sample, sample size, normal distribution, proc calis, proc step | source | 5 |
| 161 | Providing User Friendly Access and Subsetting Capabilities to Non-SAS Data Across Operating Platforms | Jim Anderson | macro variable, macro facility, macro definition, %if-%then-%else, sas base, dataset, options statement, proc step, &variable, macro call | source | 6 | |
| 162 | Querying Data Easily with the SQL QUERY Window | Henrietta Cummings | The SQL Query window is a production feature in SAS/ASSIST software beginnin[ with Release 6.08 TS40B and Release 6.09 TS037 of the SAS@ System. This feature provides a point and click environment to build sal queries and reports with minimal ef fort and no knowledge of SAS System syntax |
dataset, group by, proc sql, format statement, order by, view | source | 10 |
| 163 | Recent Development in PROC REPORT | Alan Eaton | Recent development in PROC REPORT includes new presentation capabilities and user interface improve ments. The enhancements will be available first under the name PROC TREPORT. The formal demonstra tion presents these enhancements in the course of designing and interacting with several reports. Relationship of PROC TREPORT to PROC |
proc step, proc report | source | 3 |
| 164 | Recent Issues in Statistical Process Control: SAS Solutions USing Statistical Modeling Procedures | Robert N. Rodriguez | A~hough the Shewhart chart serves well as the fundamental tool for statistical process control (SPC) applications, its as sumptions are challenged by many modern manufacturing environments. For example, when standard control limits are used in applications where the process is sampled fre quently, autocorrelation in the measurements can resu~ in too many out-of-control signals. Other situations considered in this paper include the presence of mukiple components of variation, the issue of short run process control, and the effect of nonnormal process data. While some olthese prob lems are subjects of ongoing research, statistical models that extend the basic Shewhart model can provide effec tive solutions. This paper demonstrates the use of SAS procedures for statistical modeling in conjunction with the SHEWHART procedure |
sample, proc step, dataset, standard deviation, proc sort, sample size, proc arima, histogram, outlier, box plot, proc calis, acf plot, residual analysis, proc mixed | source | 18 |
| 165 | Replacement Methodology or Maintaining the Ranking of Treatments in Clinical Trials with Discontinuations | Maureen Fulcher Mele | In our clinical trials, we altempt to compare differences in skin conditions resulting from repeated exposure to treatments, in a controlled test protocol. To do this, an ordered-Calegorical grading of trealment effects is conducted across multiple sessions for a number of products. If a trealment is discontinued during the trial due to skin damage, the rank of the product effect is maintained throughout the remainder of the study. We call the dala handling for this the "replacement methodology" since the data is replaced after discontinualion with its appropriate ranking. This paper discusses how the ranks are maintained in the SA S data set or how the "replacement methodology" is implemented for the duralion of a study | proc step, data science, proc print, proc sort | source | 6 |
| 166 | Replay Your SAS Graphs Into One Template | Irene Mendelson | proc greplay, bar chart | source | 2 | |
| 167 | Report Production System-"Report Line " | Samuel Berestizhevsky, Tanya Kolosova |
Report Production System REPORT LINE is a program that makes it easy to produce custom reports from your SAS System data set, and it can be integrated to any your applications based on SAS Software. REPORT LINE is a way for you to solve your application problems while maintaining a great degree of flexibility of data processing and data presentation. REPORT LINE is based on relational data dictionary and preserves the data integrity by the powerful verification facility. While other reporting methods require a lot of programming, no programming is required with | raw data, sysrc, data dictionary, libname statement, missing value | source | 4 |
| 168 | SAS 6.09 on a CONVEX C3840: First Impressions | Kenneth A. Hardy, Sally M. Muller |
The armitecture of the CONVex C3 series of processors shoufd offer memory address space, va and computational speed advantages for running the SAS System. The University of North carolina at Chapel Hill has been an experimental and beta test site for Ile development of SAS 6.09 under ConvexOS- and has been running the production version of SAS 6.09 since January. 1994. This paper provides our initial impressions of running version 6.09 on a CONVEX C3840 and compares it to SAS running on several other platforms on our campus | proc step, missing value, elapsed time, cpu time, proc mixed, proc reg, logistic distribution, proc freq, proc logistic, proc sort, dataset | source | 8 |
| 169 | SAS as a Means to a Different and Better End | David J. Ross, Maria Lupetin |
proc step, relational database, proc sql | source | 6 | |
| 170 | SAS Database Management Systems Used for Semiconductor Defect Learning | Tracy L. Lord, Ken A. Wiggin |
With increasing requirements for more complex analysis, a structured database management system is essential. This paper describes some of the structures as well as the advantages and disadvantages of the file systems used at IBM's semiconductor production facility in Essex Junction, Vermont | statistical software, sample | source | 3 |
| 171 | SAS Institute's Involvement in Current Software Standards | Cynthia H. Morris | All engineering disciplines involve the establishment of standards and hundreds of groups have been formed to provide standards within the computer software and hardware industries. SAS Institute is actively involved in the standards development process and is committed to supporting standards that provide an important benefit to users, particularly those that allow the SAS System to be portable across different platforms. SAS Institute has participated in the development of various industry standards, such as the ANSI C, POSIX (IEEE 1003), and SAA standards, and currently is participating in various committees. For instance, the Institute is participating in the Microsoft User Interface committee to ensure awareness of the standards for native interfaces. In addition, the Institute is active on the Software Quality System Registration Committee to establish A Guide to Software Quality System Construction using ISO 9001 | source | 4 | |
| 172 | SAS Macro Techniques Useful in Development of Flexible Applications | Christian M. Forster | Building powerful, easy-to-use, flexible applications that prove useful for years can be an elusive task. Proper analysis and design as well as end-user involvement are essential to the preparation of system specifications for these applications. Breaking down the specifications into small, manageable, well defined tasks or modules makes successful applications development possible. This paper emphasizes the overall design considerations and development techniques used in a large, powerful SAS Macro Language application called GENTABLE. This generic application allows users to easily produce a variety of presentation-ready summa!), tables. The paper will document GENTABLE's main process flow and illustrate novel coding | variable, macro variable, proc step, macro definition, macro loop, keyword parameter, %macro parameters, proc univariate, in=, macro facility, %if-%then-%else, macro put, proc contents, proc report | source | 7 |
| 173 | SAS Oriented BBS Systems: Online Help 7 Days/Week | Ben Conner | This paper describes electronic Bulletin Board Systems (BBS) and how they can be useful to the SAS user community. It covers character istics of BBS systems in general and what differ ent ones can do. Finally it describes 2 BBS sys tems that cater to SAS users | group by, txt | source | 9 |
| 174 | SAS Presentation Tools: Indiana University's Library Management Information System | Mark Feddersen | Indiana University maintains one of the largest research and academic collections in the world, holding over 6 million volumes in 45 libraries across the state. IU has automated the card catalog and many of the back-room business functions of a large library. Library staff and administrators need access to information about the usage and management of the collection generated by the automated system. IU and other large academic libraries have standardized on SASe> for simple statistical reporting, but SAS has more to offer. At IU, we are developing a "library management information system," using a variety of SAS data presentation tools in a UNIX/AIX environment to provide statistical reports, ad-hoc queries, and high-resolution graphics. Front-end interfaces are tailored for occasional as well as "hardy" users and delivered statewide. Examples of point-and·click menus, and color graphics displayed with X-windows graphic terminal emulation software, are presented and discussed | proc sql, sas programmer | source | 7 |
| 175 | SAS Server: Client/Server Computing | Joe Wang | Client/Server technology has been used by many companies as a strategic weapon for moving applications off mainframe computers during the past decade. In January 1993, the Clinical Data Management Unit of Upjohn Laboratories launched the SAS Server project. The goal was to move SAS programming for a high priority drug development project from the overutilized IBM 3090 mainframe to a Client/Server environment in order to provide version control, fast development time, and fast execution time for those SAS programs. This was done in two phases during the summer of 1993 in order to ease the migration from the familiar mainframe | dataset, phase ii | source | 5 |
| 176 | SAS Software Techniques in Longitudinal Studies of Health Outcomes and Costs | Julia Hecht, Jenifer Ehreth, Mary Durham, David Grembowski, Joseph Picciano |
Health outcome and cost research involves many kinds of data from multiple sources. Base SAS software enables us to combine survey and health care delivery system data involving single events in time, such as interventions, with data from periods-of·time, generally utilization and cost data spanning months or years. Naming conventions and file structures become critical in longitudinal studies. Complex relational file structures are necessary because our point of reference often shifts: sometimes we focus an individual's experience prior to an event; next we consider the experience of an entire clinic prior to the implementation of an intervention. At times we are interested in cost per patient and at other times on cost per type of physician. Arrays and macros assist in efficient replication of files across time periods and different kinds of data, for example, inpatient admissions or outpatient visits | randomization, label statement | source | 6 |
| 177 | SAS Software Utilization in the Production of Fibers | Robert V. Baxley Jr., Jerry L. Oglesby |
sample, standard deviation, proc step, outlier, dataset, line chart, proc freq | source | 8 | |
| 178 | SAS Software: Tools for Managing Your Company | Suzanne S. Gordon, Jerry J. Hosking |
SAS Institute prides itself on using its own technology to run its business. Several applications are discussed by the MIS programmers who support them. A variety of SAS software products. SASlAF. SASIFSP, SASICALC, SASIENGlISH. SASISHARE. IMAGE Extensions to SAS/GRAPH@. and base SAS software, plus Screen Control Language are showcased by sample applications in use .at the Institute. Typical applications are Application Strategic Online Services Institute Directory Account Management System CPA Application Budget Information System Human Resources Information System DescMptioniProduct(s) Highlighted Tracking and resolution of customer problems and requests. Object-oriented programming techniques, SOL Procedure, SASlAF, SASfFSP, and SASISHARE software Data access and visual representation, both as pictures and in hierarchical structures. IMAGE Extensions to SAS/GRAPH and |
source | 11 | |
| 179 | SAS Tools for Assessing Gage Repeatability and Reproducibility | Julie A. LaBarr | Measurement systems are essential to the quality of a manufacturing process. The gages or instruments that take measurements are subject to variation. Too much variation in the measurement system may mask variation in the process. One type of measurement variation is caused by condttions inherent in gages. This variation. known as repeatability. is obtained when one person measures the same charac teristic several times wtth the same gage. Another type of measurement variation, known as reproducibility, occurs when different individuals measure the same characteristic wtth the same gage. Three ways of determining gage repeatability and repro ducibility (R&R) are the range method (also known as the short method), the average and range method (also known as the long method), and the variance components method (also known as the average and variance method). The range and average and range methods use ranges to es timate gage R&R | dataset, proc sgplot, sample, proc mixed, proc step | source | 10 |
| 180 | SAS Training Experiences in Our R&D Environment | Maureen Fulcher Mele | It started out as a simple question from one scientist, "how can I learn to use SAS software to analyze data?" That inquiry resulted in the painstaking project of developinff& and implementing afour day course entitled, "SAS Software Fundamentals for R&D" for researchers at our site. This poper describes the development of the training coune and its impact | proc step, proc print | source | 6 |
| 181 | SAS vs. DB2 as a Relational DBMS for End Users: Three Corporations with Three Different Solutions | Stephen C. Scott | Three corporations with different sizes and types of Relational DBMS are reviewed. All three started with DB2 as the DBMS and SAS as the analysis and reporting system. Corp. A sought to build a information warehouse and to store its data in DB2 tables - but in the process discovered that SAS software as a DBMS reduced CPU times by over 86%. Because of the size of this database - 30 gigabytes - stored on 17 3380 triples . the potential saving were in the millions of dollars. Corp. B purchased a DB2 based Human Resource and Payroll System. They also built a DB2 corporate reporting database based on the production system and updated daily - and a SAS reporting database from which the weekly/supplemental/monthIY/Quarterly/annual reports are produced. By reporting from SAS instead of DB2 or Flat File they reduced potential CPU costs by over 90%. Corp. C had a small DB2 database containing charges for computer services - software, hardware, cpu time, programming etc | cpu time, dataset, flat file, sas library, proc step, proc sql | source | 10 |
| 182 | SAS/AF Features: Easy for You or Easy for Users? | Heidi Markovitz | SAS/AF includes many features that automate for developers standard data entry processing functions. such as field validation and selection lists. These functions can also be programmed in SCL using more conventional procedural techniques. Using concrete examples. this paper examines the relative merits of each approach in the areas of rapidity of development. speed of end·user training, and ease of use for both developers and end· users |
data cleaning, date variable | source | 6 |
| 183 | SAS/CPE Software for OpenVMS An Enterprise-Wide Solution | Virginia M. Dineley | SAS/CPE software for OpenVMS provides a variety of analysis and data management tools for OpenVMS performance data. I! supports the OpenVMS Monitor utility. SPM. DECps and the OpenVMS Accounting facility. In addition, SAS/CPE software can be used to analyze disk usage and Ethernet traffic. This demonstration focuses on new features available in the next release of $AS/CPE software for OpenVMS including a new Menu interface, reporting interface, Performance Data Base (POB) Management and dynamic facility definition |
data governance | source | 2 |
| 184 | SAS/GEO-New Tools in the SAS System for Geoscience Professionals | Gary S. Franklin, Delpfine E. Welch |
SAS/GEO is a new product in the SAS System to access popular geoscience applications, databases, and file formats from a single SAS session. This product is intended for geoscientists in a variety of disciplines. including petroleum, environmental, governmental, mining. and academic. The product design includes user interfaces, data format translators, and a metabase. The user interfaces include the ability to access data; manage data. projects, and the metabase; and invoke applications. The data format translators are programs that read and write data in a variety of formats, both third party vendor formats and external file fonnats. The metabase is the data dictionary that underlies SAS/GEO. The product is designed to be a user-friendly environment in which to use SAS software to manage data with direct links to third party applications that use the data |
data dictionary, data standard | source | 3 |
| 185 | SAS/GIS Software: A Map Is Worth A Thousand Pictures | Jack Bulkley, Samuel Johnson |
SAS/GIS software displays, analyzes and queries spatial data. This paper discusses the GIS aspects of a larger application that incorporates several SAS products. It discusses which data was used for this application, importing the data, and setting up the SAS/GIS maps. Finally, this paper discusses. how the maps were combined with reports, presentation graphs, images, and interactive visualization tools needed to analyze the attribute data in a complete application. INmoDucnoN To show one of the many possible uses of SAS/GIS software, a imaginary up-scale grocery store, Nature's Harvest, was postulated. Nature's Harvest specializes in selling: locally and organically grown fresh fruits and vegetables health food locally-made baked goods, pasta, jam low-fat |
source | 6 | |
| 186 | SAS/GRAPH: Using the Annotate Facility | Jack S. Nyberg, Stuart D. Nichols |
The annotate facility in SAS/GRAPH is a powerful tool for graphic presentation but llOtil now has mainly been used io conjunction with the traditional SAS/GRAPH procedures. Used with PROC GANNO, the annotate facility has unlimited power that can create stunning presentation graphics |
proc step, proc gchart, bar chart | source | 5 |
| 187 | SAS/OR Optimization Procedures with Applications to the Oil Industry | Trevor D. Kearney, Marc-David Cohen |
proc step, network optimization, integer programming, decision analysis, linear programming | source | ||
| 188 | SAS/PH-Clinical Software: Study Startup Hints | Juliana M. Ma, Sandra D. Schlotzhauer |
macro variable, label statement, numeric variable, nominal variable, sample | source | ||
| 189 | SAS/TUTOR Online Training Now on UNIX | Nancy N. Goodyear | proc tabulate, proc step | source | 2 | |
| 190 | SAS/VIDEO: Easier to Program than your VCR | Sanjay N. Matange, Jade Walker |
This paper is an overview of the features and application uses of SASNIDEO software, that provides a muHimedia interface to data presentation. The first part of the paper lists and describes the features available in SASNIDEO software: how to set up, convert, and run a video clip. After a brief discussion on planned enhancements and on interfaces to other parts of the SAS system, the paper suggests applications that can use this capability and provides an example of an ar;plication | proc step, sample | source | 5 |
| 191 | Scientific Visualization in Oil and Gas Exploration | Leon L. Fedenczuk, Brian Wyvill, Kristina Hoffmann |
In this paper we present a method for interpretation of statistical results from discriminant analysis. The specific attention has been given to the application of Scientific Visualization to the presentation of results from statistical analysis. Techniques are presented to aUow a geologist in oil and gas exploration, to make a visual analysis of the statistical results. In particular, we explain how to convert multidimensional geological data into a single parameter, which is later presented in 2D and 3D space. A discriminant criterion is developed and then used to classifY each of the multivariate observations into one of two groups: producers and nonproducers. The posterior probability of membership in each group for the test data is presented as the production probability. Furthermore, this probability governs the colour and density during the rendering process | discriminant analysis, posterior probability, data science, response variable, regression analysis | source | 6 |
| 192 | SELECT ITEMS FROM PROC.SQL WHERE ITEMS > BASICS | Alan Dickson, Ray Pass |
proc sql, proc step, group by, order by, dataset, select, by group processing, where statement, create table | source | 10 | |
| 193 | Sharing Enterprise Data with ODBC | Andy Barnhart | ODSC provides an interface to many diverse data sources on the back end, and many applications support it. The SAS System for Microsoft Windows exploits this capability to provide enterprise solutions for sharing data from multiple sources | proc step, proc sql | source | 5 |
| 194 | Short-Term versus Long-Term Forecasting | Barbara Ledwith-Crosby | Forecasts can be either short term (under eighteen months) or long term. Forecasts for the near future can be done using relatively simple procedures. Forecasts requiring a further look into the future require more sophisticated techniques. This paper will illustrate making short term and long term predictions using SASIETS software and actual data from the railroad industry | proc step, proc forecast, proc model | source | 5 |
| 195 | Small-Sample Inference in SAS Software: Using Exact Methods | Cyrus R. Mehta | proc freq, null hypothesis, sample, exact test, dataset, likelihood function, chi-square distribution, monte carlo, production run, regression analysis | source | 9 | |
| 196 | So You Want to Present a Paper at SUGI | Judy Loren | source | 4 | ||
| 197 | Some Clever Things to Do with User Defined INFORMATS | Ronald P. Cody | missing value, proc step, proc format, proc print, if-then-else, input statement, proc freq | source | 6 | |
| 198 | Spreadsheet Data Gathering for the SAS System | William C. Murphy, Dennis H. Leverett |
In a variety of epidemiologic studies, data are gathered at many diverse s~es on portable microcomputers. The data are later assembled at a central location for statistical analysis. This data acquis~ion in the field is done in spreadsheets, but the databese is assembled and analyzed in the SAS system. The reliable and speedy translation of the data from the spreadsheet into the SAS data format is therefore of considerable importance to these studies. Since our computers are operating under MS-DOS·, the choices for data translation are those provided by version 6.04 of the SAS system. This limits us to reading text files into a DATA STEP or using PAOC DBF to input dBase files generated by the spreadsheets. However, both of these methods present several problems including variable name construction, data typeambiguily, and missing values treatment. A simple SAS macro routine can provide the assembled database w~h valid variable names |
txt, missing value, macro variable | source | 3 |
| 199 | Strings, Delimiters, and Difficult Data | Lary Jones | SAS is becoming the prime application language for many people. This means handling a wider range of file formats. We need to go beyond the sim ple approaches which worked for regularly spaced columns and numbers. Fortunately, the SAS DATA STEP language offers many aids, though some are not well known. Many problems can be handled through such things as list input options, format modifiers, and built-in functions. These are demon strated through reading a simple order~try file. Other problems may require a bit of ingenuity and jXogramming tricks. The task of converting a CMS Names (e-mail addresses) file to the format used by the em mail program on UNlX systems is used as an example of some techniques which make it possi be to process special format files and delimited string data |
character variable, conditional do loop | source | 6 |
| 200 | Surveillance of Foetal Alcohol Syndrome(FAS) using SAS/FSP and SAS/AF Software with SCL | Philip J. d'Almada, Valborg Kvigne, Michele D. Strachan |
About 8,000 babies are born each year with the characteristic birth defects or developmental disabilities associated with in utero exposure to maternal consumption of alcohol. These characteristics Bre collectively know as Foetal Alcohol Syndrome (FAS). The CDC uses an epidemiological approach to assist states to address public health problems. The first step to help South Dakota address the FAS problem was to develop and establish a surveillance system. SAS software on the PC. featuring SAS/AR: and SAS/FSP@ software. was used to construct a PC-based, menu-driven database management facility: Foetal Alcohol Syndrome Applications Facility (FASAF). FASAF is characterised by the capability for precise and accurate data entry using SAS Screen Control language (Sel). FASAF, therefore, can be easily implemented in the field by nonSAS users for automated medical chart abstraction |
quality control, if-then-else | source | 5 |
| 201 | System Managed Storage: Using SAS Software to Establish a Storage Policy | Samuel Berestizhevsky, Tanya Kolosova |
System Managed Storage plays a growing role in automating the allocation, placement, backup, and migration of datasets on the mainframe. Storage management system (SMS) is a set of IBM software products combined with hardware enhancements and procedures written in a CLiST -like language. Ata computer center of any size, SM3 requires one additional job function. This is a storage administrator whose job is to implement and manage SM5-related concepts. SMS constructs (storage class, data class, management class and storage group) are used to deliver storage resources and services to individual datasets. A storage administrator should be able to define SMS constructs on a regUlar basis to make sure they are still meeting the needs of their data. He may define any number of values for each SMS construct. A dataset can be assigned any combination of values from up to four SMS constructs. This is a very complicated matter to select a right assignment from a great number of possibilities | linear programming, dataset | source | 3 |
| 202 | Table Lookups in the SAS DATA Step | Gary L. Katsanis | lookup, set statement, key=, proc step, proc format | source | 7 | |
| 203 | Tables for Two: An Introduction to the TABULATE Procedure | Kathy McLeod | The SASe System includes many powerful tools for summarizing and displaying data. PROe TABULATE is one of these tools. This tutorial provides an introduction to PROC TABULATE for programmers having little or no experience using the procedure to generate tables. Each statement used with PROC TABULATE will be discussed: the PROC TABULATE statement with its options; BY. CLASS. FORMAT. FREQ. LABEL. VAR and WEIGHT statements; the TABLE statement: and the KEYLABEL statement. Emphasis will be put on the TABLE statement in creating 8 table that satisfies the application's requirements. The presentation will focus on how to cross (both across dimensions and within 8 dimension). Concatenate, and group two variables to produce distinctly different tables. Once 8 basic table has been created, the tutorial will suggest |
proc tabulate, proc step, title statement, dataset, class variable, degrees of freedom, by group processing, format statement, input statement, label statement, proc freq, proc means | source | 10 |
| 204 | Techniques for Efficiently Accessing and Managing Data | Steven A. Wilson | This paper explores a number of SAS System data management and coding techniques for improving efficiency. After efficiency is defined and some basio efficiency techniques are explained, some SAS Version 6.07 + features are discussed from an efficiency viewpoint. These features include PROC SaL, SAS data set compressing, the Stored Program Facility, and SAS Data Views |
proc step, dataset, elapsed time, character variable, sas library, macro definition, macro facility, sas programming | source | 6 |
| 205 | Techniques to Avoid: What Momma Should Have Told You About SAS/GRAPH | Arthur L. Carpenter | Several available graphic options and PROCedures produce graphs and charts that are either misleading or do not convey the information intended by the creator of the graphic. This paper demonstrates a few of these commonly applied SAS/GRAPH graphics and options. and discusses their pitfalls and why they should be avoided. The ability to distinguish values and to interpret graphics depends on our perceptions. and we do not always perceive what we think we do. Research has shown that some types of graphs and some combinations of graphical elements are more easily and accurately interpreted than others. Correct selection of the elements can lead to a strong presentation, while other combinations of these elements can be misleading or even deceptive |
proc step, proc gplot | source | 4 |
| 206 | The 'SKIP' Statement | Paul H. Grant Jr. | macro definition, proc step | source | 2 | |
| 207 | The Annotate Facility: A Quick Start to an Easy Overview | Arthur L. Carpenter | The ANNOTATE fecility i. included within SAS/GRAPH'" and acts as 8 bridge between the procedure selected by the user and the user's desire to customize the graphics output. The ANNOTATE facility can be used to; position text or symbols 8nywh~re on the graph. control text characteristics, draw line segments and polygons. and otherwise enhance the user's graph. Using ANNOTATE need not be difficult and can be easily introduced by presenting the different fundamentals of the specialized ANNOTATE data set. ANNOTATE looks for variables with specific names and attributes, and the values taken on by these variables in turn instruct ANNOTATE as to the user's intentions. Unlike most SAS data sets. the ANNOTATE data set is fairly rigidly defined in terms of the variables that it is to contain and the attributes that these variables must have |
proc step, character variable | source | 6 |
| 208 | The Benefits of Object-Oriented Application Development Using the SAS System | Randy Pierce | catalog entry, sas base | source | ||
| 209 | The Census Reference System | Edward Cary Bean Jr. | This paper describes how the advantages of both SAse and UNIX were combined to create the 'Census Reference Sys· tem' (CRS) a unique on-line database used by the U.S. Bureau of ihe Census for conducting its many household based surveys. This system provides rapid access to over one hundred million data records w~hout the use of a trad~ional relational database. The unique deSign of the CRS signfficantly reduced hardWare and software require ments and their associated costs, ascompared to other more traditional processing approaches | relational database, dataset, group by | source | 5 |
| 210 | The Joys of Merging: Alternative Techniques | Joan Keesey | The SAS System ,. provides the capability of performing one-ta-one and many-to-one data set merges easily and efficienijy via the MERGE statement. Many-to-many merges require alternative techniques but are often very useful, particularly when there are errors and inconsistencies in the merge variables or when there is a 'best" match based on some criteria, i.e., the record with the highest score or the record which best satisfies some formula or reqUirement. Using a many-to-many merge technique provides the user with increased flexibility in searching any number of potential matches for the 'best" match. The implementation of a many-ta-many merge can eliminate repeated merge steps and make more efficient use of the matching information |
proc step, proc transpose, point= option, proc format, proc sql, set statement, macro variable | source | 6 |
| 211 | The Lazy Man's Guide to SAS Software | Ginger Carey, Helen D. Carey |
sas consultant, sample, proc step | source | 6 | |
| 212 | The SAS System - from the Box to Production | Roger L Chenoweth | When a new release of the SAS System is installed it is natural to have concerns about the validity of the new software and its impact on your production applications. To allay these concerns this paper describes verification and validation of the SAS System performed at SAS Institute. how SAS Software sites can contribute to this process, and finally, steps SAS Software users can take to continue the validation process once the new release is installed. This paper also illustrates how the Management Information Systems (MIS) department puts the SAS System into production at the Instrtute | data cleaning, management reporting | source | 5 |
| 213 | The SAS System for the Macintosh | Joanna D'Aquanni, John W. De Boskey |
For several years, the most requested new platform on the SASware Ballot has been the SAS System on the Macintosh. This user interest, coupled with new technology, such as the Macintosh's new System 7 Operating System and the Power Macintosh. have prompted SAS InsliMe to develop tile SAS System for the Macintosh. Production release for this port is scheduled for late 1994. This paper provides an overview of current and future dev.elopment directions | source | 2 | |
| 214 | The SAS System for Windows, Release 6.10 | Carol Williams Rigsbee, John P. Schroedl |
This demonstration focuses on the Graphi· cal User Interface (GUI) enhancements to the SAS System in Release 6.10 for Micro soft Windows. We will show the major en hancements including a description of the improved GUI and increased application in tegration capabilities. Some of the improved GUI capabilities include a conf-'Jrable tool bar, a more robust help system, ,lore meth ODS to configure your GUI, printing im provements and electronic mail (E-mail) support. Application integration enhance ments include support for Object Linking and Embedding (OLE) and Open Data Base Connectivity (ODBC), a method to access extemal Dynamic Link Libraries (DLL's) and the ability to import and export graphics to and from common PC data file fOmlats. For more details on the Release 6.10 GUI en hancements, refer to "Enhancements to the Graphical User Interface for the SAS Sys tem on Personal Computers". For more de tails on ODBC, refer to "Sharing Enterprise Data with ODBC" |
output delivery system, sample | source | 1 |
| 215 | The SAS System in a Client/Server Environment | Bengt Bengtsson | Client/server computing is understood in many different ways, ranging from being the revolu tionary new model for. computing in the 90's, to simply a buzzword to which we all must pay lip service. In this paper we will attempt to describe different kinds of client/server applications, both by examining the current market offerings, and by taking a more abstract view of the way in which clients and servers could interact. This | source | 3 | |
| 216 | The SAS System under ConvexOS, Release 6.09 | Isom Crawford, Leigh A. Ihnen |
This paper addresses issues associated with the mi· gration of production jobs from other SAS platforms to Release 6.09 of the SAS System under ConvexOS. Performance characteristics related to the architec ture olthe Convex C3200, C3400, and C3800 series are explored. Also covered are areas where performance might im prove -or diminish - when migrating to Release 6.09. Specific areas to consider include I/O-intensive processing on large SAS data sets, SAS DATA STEP performance, SORT procedure performance, and nu merically intensive procedures |
missing value, elapsed time | source | 4 |
| 217 | The SAS System: A Complete Client/Server Solution | Cheryl A. Garner | source | 11 | ||
| 218 | The SAS User Group Newsletter - Start the Presses! | Andrew T. Kuligowski | unique key, source of funds | source | 7 | |
| 219 | The SAS/TOOLKIT Integrated Development Environment | Mark V. Schaffer | Writing extensions to the SAS System using SASITOOLKIT Software may appear to be a very difficult task. An integrated development environment, nicknamed TIDE, is currently under development and should ease the burden. TIDE is available in beta-test mode and will become part of SASITOOLK1T Software. INTRODucnON The SASrrOOLKIT Integrated Development Environment. or TIDE, is a program written using FRAME technology to provide the users of SASfTOOLKIT Software with an interface which simplifies the application development process. A user with ~mited knowledge of SASITOOLKIT Software should be able to use TIDE to develop functions, formats, informats, procedures and engines. Among the features provided is the ability to generate source code templates (in C, FORTRAN, PUI or IBM 370 assembler) on the appropriate host TIDE's other capabilities include project management. automated compile correction | dataset, api | source | 2 |
| 220 | The View Review: PROC SQL Views, SAS/ACCESS Views, and DATA Step Views | Andrew A. Norton | proc sql, where statement, sql pass-through, missing value, proc step, dataset, create view, flat file | source | 6 | |
| 221 | The Virginia Higher Education Information System | Dennis B. Catley, James M. Alessio |
Staff of the State Council of Higher Education for Virginia (SCHEY), Virginia's higher education coordinating board, and the Office of Institutional Research at Virginia Tech have developed an enterprise information system in a client/server environment. The system, using SAS, provides access to data and information at the institution, state, and national levels. Data can be accessed from client PC's or mainframe sessions over established state and national networks. The Virginia Educational and Research Network (VERNet) provides the backbone within the state and access to the INTERNET. The model is flexible, providing users the ability to connect to and access data on a variety of computers and operating systems | dataset, management reporting | source | 5 |
| 222 | The WHERE Clause and SCL | Marge Scerbo | where statement, numeric variable | source | 2 | |
| 223 | The. Standalone Program Grows Up: Strategies for System Design | Frank C. DiIorio | macro variable, macro loop, macro put, proc step, macro quoting function, macro conditional, macro facility, put statement, proc print, dataset, sas log, macro definition, proc format, proc report, autocall macro | source | 10 | |
| 224 | This is a Fairy TaleNOT! A Primer on Moving SAS Applications Across Graphical Operating Systems | James D. Hefner | Currently, most SAS Software application developers have on~ one or two graphical operating systems (such as Microsoft WindowsTN, or OSFlMoti~ to support. However, the pending release of the SAS System for the Apple Macintosh I and the introduction of new hardware and software such as the PowerPC and Wabi, means that application developers may have to support two or more graphical operating systems. This paper is intended to assist application developers, both in the teaching of the fundamentals of graphical operating systems, and in Ihe moving of SAS/AF and SAS/EIS applicalions from one operating system to another |
by group processing, independent qc | source | 6 |
| 225 | TQT - Total Quality Training | David E. Beam | Training managers want to deliver the best quality training possible. Customers want to receive the best quality training available. Sounds like a match made in heaven, doesn't it? Unfortunately, too many elements of training may interfere with the ability to give and receive the kind of training needed. We are often forced to balance limited budgets against expensive training needs, juggle schedules to get people together and keep up with the ever changing technology. These problems can easily overpower the best attempts for quality training | quality control, customer satisfaction | source | 6 |
| 226 | Tracking Software for Longitudinal Studies at the National Center for Health Statistics | Sandra T. Rothwell, Aileen D. Bennett |
The mission of the National Center for Bealth Statistics (NCBS) is to provide statistical information that will guide actions and policies to improve the health of the American people. To support this mission NCHS began to field an increasing number of studies which followed the health status of individuals over time. These longitudinal studies can continue for many years and require the constant update of vital status data and information necessary to re-contact living survey subjects in person, by mail, or over the telephone. As the number of followup studies grew, it became clear that this tracing activity was best supported by a single system which would be applicable agency-wide. This system, written using SAS/AF~ software, currently provides support for nine of the most often used methods for collecting changes in addresses, telephone numbers, vital status and dates of death. Information may be obtained from the U.S |
flat file, feature selection | source | 5 |
| 227 | Undocumented Features to Test for Existence of Data Sets | John Beach | filename statement, error message, macro definition | source | 1 | |
| 228 | Usages of the Preview Window under Application Control | Don Stanley | catalog entry, catalog, proc step, sysrc, proc sql, dataset, sas base, batch job | source | 11 | |
| 229 | Use Origin and Length to Pinpoint And Match Up Multiple Graphs | Irene Mendelson | Comparison of two or more related graphical situations is often best done when the graphs are side by side. The example we look at here is two chromatograms or line graphs. These chromatograms can be lined up exactly on one page through precise placement of their respective origins and the identical length for each respective axis. The key here is to think of the layout of the graphical page in terms of percentage of screen area and not cells or inches. PRODUCE THE FIRST GRAPH ON THE LEFf The strategy overall here will be to use the technique of re-displaying graphs into one screen template using the GREPLAY procedure. The first step in doing this is to produce the graph and store it in a temporary graphics catalog. If the graph origin or (0,0) point is placed 15 percent of the screen from the left side and 25 percent up from the bottom, and if the horizontal axis then ends 40 percent from the left side, then this graph can be displayed in the left half of the screen |
proc greplay, proc gplot | source | 2 |
| 230 | Using BY Variable Text Substitution to Add Data Values to SAS/GRAPH Titles and Footnotes | Earl R. Westerlund | sample, by group processing | source | 2 | |
| 231 | Using Fractional Factorial Designs to Improve Product Shelf Life | Andrew G. Stead, Susan B. Wilkins, Karen G. MacDonald |
Nine variables were identified through brainstorming as possibly affecting shelf life of a new, not-yet-marketed, biological product. The FACTEX procedure within the SAS/QCE software module was employed to generate a logistically tractable fractional factorial design with which to screen these variables for their importance in influencing a key performance measure of the product. The design used and the analysis of the results are presented |
main effect, proc genmod, proc step | source | 4 |
| 232 | Using SAS INCLUDE Files and SAS Macro Variables to Develop an Interactive Graphics Application | Rick Guest | Do you generate a hundred or more graphs each day just to ensure that a particular one required by your manager is available? SAS graphics catalogs are excellent for storing a variety of graphics covering all aspects of your business, however, they can use a lot of CPU and DASD to create and hold graphics that may rarely, if ever, be used. This paper describes a simple SAS program for creating graphics interactively when they are needed. Actual program text provides examples that can be executed or modified with very little effort, which will enable you to convert these examples into a working tool for your graphics requirements. With this information, you should be able to use a SAS INCLUDE file, write a simple SAS MACRO, generate a simple SAS graph and output a graph to an ADMGDF file in a CMS environment | macro variable, sample, macro definition, macro call, %if-%then-%else | source | 6 |
| 233 | Using SAS Software for Monte Carlo Simulation | Vi-Cheng Wu, James E. McLean |
Most Monte Carlo simulation studies have used programming languages such as Fortran. SAS~ software is often conceived of by statisticians 8S an analysis package rather than a major programming language. Because of this, SAS is rarely used for Monte Carto simulation. The purpose of this paper is to propose a Monte Carlo simulation process using only SAS code. The | correlation, monte carlo, dataset, anova | source | 3 |
| 234 | Using SAS Software to Analyze Paired Comparisons Preference Data Under Coomb's Unidimensional Unfolding Model | Jeff A. Sloan | Coombs' unidimensional unfolding or ideal point model is a methodology for analyzing paired comparisons preference data. The method has been underutilized due in part to the lack of goodness of fit statistics and model selection criteria. Using a simple multinomial model, related goodness of fit tests of hypothesis are achieved via bootstrapping. An "all possible models" approach via SAS is used to examine whether or not the underlying hypothesized dimension of the construct under study is supported. Suggestions for model selection criteria are given. The approach is demonstrated with an example drawn from clinical research involving cancer patients' role preference regarding treatment decision making | sample, goodness of fit, proc freq | source | 6 |
| 235 | Using SAS Software to Carry Out a More Complete Thurstone Scaling Data Analysis | Jeff A. Sloan | This paper describes SAS algorithms for carrying out a detailed analysis of paired comparisons data via Thurstone scaling. Included in the analysis are a SAS/GRAP~ algorithm for producing a picture of the Thurstone scale, goodness of fit statistics for both the case V and case III models, computation of Kendall's coefficient of consistency and the coefficient of agreement |
chi-square test, proc step, sample, regression analysis | source | 6 |
| 236 | Using SAS Software to Check Assumptions for Analysis of Covariance, Including Repeated Measures Designs | Richard P. Steiner, N. Margaret Wineman |
Analysis of covariance (ANCOVA) is a powerful statistical tool for adjusting an analysis to acoount for the effects of concomitant variables. The technique may be applied to completely randomized designs (CRO) as well as repeated measures designs. In addition to normality assumptions, ANCOVA depends on assumptions about variances and slopes. Although not usually provided directly, most statistical software has the capability of testing the equal slopes assumption in a CRO ANCOVA; however, the slope assumptions of repeated measures ANCOVA are more complex and more difficult to check. The SYSLIN procedure in SAS/ETS software is an elegant tool to assist with checking the slope assumptions of repeated measures ANCOVA. The assumptions of ANCOVA are discussed and SAS programs for checking these assumptions are presented. A method for comparing groups when the equal slopes assumption is violated is also presented |
response variable, regression analysis, covariance, confidence interval, ancova, proc step, repeated measures, null hypothesis, proc glm, proc reg, binary variable, proc genmod, anova, sample | source | 5 |
| 237 | Using SAS Software to Develop a Comprehensive Air Pollutant Emissions Modeling System | Suzanne J. Strasser, Leonard Bruckman |
Emission estimates of photochemically reactive air pollutants are a key input to a photochemical model. These models are used by state and local air quality management programs to help prepare air quality plans that include the control programs required to demonstrate attainment with federal health standards for ozone. For proper photochemical model performance. emission estimates must be spatially located (i.e .* emission estimates by grid cell) within the modeling domain, temporally resolved on an hour-by-hour basis for the specific modeling episodes. and chemically speciated. Most "emission inventories· are compiled on an annual basis for individual counties or planning regions. Radian Corporation has developed the Geocoded Emissions Modeling And Projections (GEMAP) system to process these annual county-wide emission rates into gridded. speciated. hour-by-hour emission estimates required by current photochemical models | macro variable, proc step, sas base, bar chart, density plot, dataset, proc report, proc tabulate, macro definition | source | 10 |
| 238 | Using SAS Software to Simulate Questionnaire Style Data | John F. Walsh | A SAS program permits instructors to provide students with simutated questionnaire style data lor use in courses in sta tistics and experimental design. The program can produce data that approximate the distributions 01 nominal or categorical variables, Likert type rating scale data and normally distributed scores. The data sets provide a Simulated research experience that can be used to incorporate the development 01 research items as well as their statistical analysis and interpretation. In teaching a course in statistics and experimental design, I have found the examples provided in textbooks wanting as a vehicle for teaching the integration 01 statistical analysis with the interpretation of resutts. The textbook material is provided to give the student practice in . mastering the specific concept provided in a section 01 a chapter. Such examples provide drill and practice quite ade quately | cumulative frequency, data science | source | 2 |
| 239 | Using SAS to Develop a "Clinician Friendly "Clinical Summary Report | Marc S. Newman, Jeffrey I. Clyman, William O. Smith, Marc Shifman |
proc step, sas base | source | 6 | |
| 240 | Using SAS/AF for the First Time | Loretta Golby | SASIAF makes it incredibly easy to build a full screen interface for your SAS System. Some of the topics that will be covered are: Basic knowledge to start building SASIAF Screens Menus Programs | proc step, sas base | source | 6 |
| 241 | Using SAS/FSP to Develop an On-line Randomization System for Multicenter Clinical Trials | Margaret Lee, Dorothea Collins |
Multicenter clinical trials research involves the randomization of patients to studies in order to assign treatments in an unbiased manner. An efficient flexible, and accurate randomization system is required. In order to accommodate the number of hospitals involved and the number of patients to be randomized, an on-line randomization system was developed using SAS software. Base SAS was used to generate the random number scheme using the function 'RANUNI'. SAS/FSP software was utilized to develop the on-line interactive randomization screens. Screen Control Language (SCL) was utilized for the interaction between users and screen entries in the PROC FSEDIT applications. This paper describes the techniques for using SAS software to develop the on-line randomization system and how this system can be used to randomize patients from multiple centers simultaneously. The benefits of the system, its operation, and the SAS code will be illustrated |
randomization, proc step, clinical trial | source | 6 |
| 242 | Using SAS/GRAPH Software for Real Work | Gregory S. Barnes Nelson | source | 14 | ||
| 243 | Using SAS/SPECTRAVIEW for Data Visualization | Stuart A. Nisbet, Ali Dogrusoz |
In this paper, we present some different types of data visualization that can be pertormed with SAS/SPECTRAVIEW software. The discussed visualization applications will explore both spatial and non-spatial data anaJysis and can, therefore, be useful examples in a wide variety of industries. This paper is meant to supplement a formal demonstraUon of the SAS/SPECTRAVIEW software |
data visualization, response variable | source | 2 |
| 244 | Using the EXPLAIN Feature to Improve DB2 Query Performance | Frank Soloman | This paper discusses the use of the SOL EXPLAIN feature of DB2 to"assist in the understanding of bow DB2 btuldles an SOL query request and how to look for tuning opportunities for better query perforaenee. This paper will explain how DB2 processes an SOL request. how to use the SOL EXPLAIN statement with the SAS8 SOL PASS-~ Facility. obtain the EXP~N results. and interpret what those results maan. In addition. this paper will present some helpful ideas for optimizing queries to save both time and system overbead. 1I1TROOOCTIOlf To acquire the skills to enhance SOL query performance it is important to understand the underlying component structures that make up the 1m2 DBMS. 1m2 is a Database Management system. comprising of two dimensional tables" and indexes that fora a basic relational structure. SOL provides tbe means for data access and retrieval froa ~ tables. Internally. ~ contains tables that fora a catalog that store information about all DB2 objects | where statement, stage 2, stage 1 | source | 6 |
| 245 | Using the FRAME Entry to Develop Graphical-based Data Review Application | David A. Bright | The FRAME enny provides a user-friendly environment for creating novel applications that take advantage of object-oriented programming techniques. The FRAME enny provides many pre-defined classes that can be used to create objects. The incorporation of Screen Control Language (SCL) into FRAME entries has enabled users to develop custom applications to take advantage of the analytical tools that the SAS System provides. By using several widget classes and by creating additional customized objects, one can easily build an application. In this tutorial, a programmer will learn how to create a prototype graphical review tool for the drilldown and analysis of data. Creation of this graphical review prototype will incorporate the exploration of several unique FRAME enny classes. By using the FRAME enny for development of mission-critical applications, a programmer can provide their company with quality analysis in a timely manner | data review, proc step | source | 8 |
| 246 | Using the SAS System as a Tool for Historical Research | Barbara B. Okerson | Because much of historical research must take place in the field and in the archives. little emphasis has been placed on the use of computer software as a research tool for the historian except in the area of quantitative history. This paper demonstrates the use of the SAS System as a tool for the traditional historian. Using SAS/FSP software to create and index a bibliographic database, SAS/GRAPH software to create both a time line and a reference map. and SASIOR software to develop a lineage chart for a historical research problem. the SAS system is presented as a comprehensive, productive software tool for historical research |
proc step, proc gmap | source | 4 |
| 247 | Using the SAS System to Assess the Effectiveness of An Educational Program | Paul E. Pope | This paper presents SAS code useful in assessing the effectiveness of an educational program. It includes both instrument-level and question-level assessments | proc step, proc freq | source | 6 |
| 248 | Using the SAS System to Score the SF-36 Health Survey | Katherine Newvine | The Veterans Affairs Cooperative Studies Program is using the MOS 36-ltem Short Form Health Survey to measure Quality of Life in the Aneurysm Detection and Management (ADAM) Study. The New England Medical Center Hospitals publishes a coding manual on how to score the 36 items.' Included are instructions for scoring and recoding each item, how to code missing items, and the formula for transforming the raw scores into final scores. This paper shows the SAS code for scoring and recoding the items, an example of a patient's scores and frequencies of the scores. The higher the score, the better the patient feels | if-then-else, proc freq, missing value, standard deviation | source | 6 |
| 249 | Using the Spearman-Karber Method to estimate the ED50 | Art Carter | The Spearman-Karber method is a nonparametric procedure for computing an ED50 estimate (and fiducial limits) that is not currentiy available in the SAS system. This paper reviews the Spearman-Karber method and presents SAS software code that can be used to generate ED50 estimates and fiducial (confidence) limits. The code was written for use with SAS software version 6.07 in VMS. The advantages/disadvantages of the Spearman· Karber vs. probit analysis in computing ED50 estimates will be discussed | dose, sample | source | 6 |
| 250 | Visualization of Scientific Data: Specialty Graphs Without Using Annotate | Arthur L. Carpenter | SAS/GRAPH"'" is flexible enough to create many graphs and charts that would not normally be considered standard SAS/GRAPH output. Although the ANNOTATE Facility is often used to "dress up" 8 graph, there are 8 number of non ANNOTATE techniques which can also be used to create non-standard graphics. The examples illustrated in this presentation use the technique of data manipulation to "trick" SAS/GRAPH into producing graphs and charts that at first glance appear to be outside of its capabilities. This technique uses the incoming data to create additional data points. These data points are then manipulated and used in conjunction with the SYMBOL and PATTERN statement. When created in the proper sequence these additional data points can create error bars on scatter plots, histograms, butterfly plots, box-whisker plots, histograms with broken scales, multiple axes, and special shapes and symbols |
histogram, proc step, box plot, proc calis, scatter plot, proc gplot, cluster analysis, missing value, outlier | source | 9 |
| 251 | Vote-Counting Method to Obtain an Estimate and Confidence Interval for the Population Correlation Coefficient Using SAS/AF | Frank C. Lieble, Morgan C. Wang |
In today's information age, scientific studies are being conducted at an exponential rate in areas such as psychology, pharmaceutics, and education. The meta analyst wants to combine these studies which investigate a common phenomenon into useful information. However, missing values pose a particularly difficult problem in meta-analysis. This paper will provide a solution, vote-counting procedures, to estimate the population correlation coefficient when some of the studies do not provide the information about the sample correlation coefficient. SASI AF was used in the development of an interactive application system for calculating and displaying the confidence interval for the population correlation coefficient | sample, correlation, confidence interval, sample size | source | 6 |
| 252 | Warning: Apparent Macro Invocation Not ResolvedTechniques for Debugging Macro Code | Veronica R. Walgamotte, Jeffrey Phillips, Derek Drummond |
macro variable, call symput, proc print, macro facility, macro quoting function, macro definition, proc step, macro put, sas log, error message, &variable, %if-%then-%else, if-then-else, macro loop | source | 7 | |
| 253 | Working with Arrays: Doing More with Less Code | Ralph W. Leighton | ; Arrays are a SAS Basic Language DATA'step feature useful for organizing, manipulating, and performing calculations on groups of data elements. Arrays have been an important feature of other more traditional procedural "scientific" programming languages, such as FORTRAN, PLf1 and PASCAL. A key point to remember at the outset is that arrays are a processing tool within the DATA STEP: they are not, in and of themselves, data on SAS Datasets. Often one needs to perform the same calculation on a series of SAS variables, as for example the tax calculations below: CBDTAX = TAXRATE CBDINCOM; xBDTAX = TAXRATE XBDINCOM; xASTAx = TAXRATE XASINCOM; etc For each of the original income items we see the same calculation being carried out a fixed quantity (taxrate) multiplied by an income to achieve a tax amount. While repeating the calculation statement is not burdensome when there are just three instances, it does become a chore if there are fifty of them |
calendar year, temporary array, proc step, input statement, dataset, array, insurer, array bounds | source | 11 |
| 254 | Writing an In-House SAS User's Guide | Bruce F. Gilsen | autocall macro, batch job | source | 8 | |
| 255 | Writing SAS Applications That Access Data in a Multiple-Update Environment | Mark Stranieri | A multiple update environment is any situation in which a single SAS data set may be accessed by more than one process at a time and one or more of the processes may be updating the data. This paper serves as a tutorial for SAS/SHARE 'software which facirrtates a multiple update environment. However, some of the ooncepts cov ered may also be applicable to other multiple update environments such as accessing a DBMS database through a SAS/ACCESS view. Situations arise in multiple update environments that cannot occur in single update environments. For example: an observation read once may have different variable values if/when it is read a second time. a record that was read may not be updateable because another process has ~ lOCked, * the nth record that a process reads in one sequential pass of the data, may not be the nth record retrieved in a second sequential pass of the data |
sas log, proc step, dataset, sas library, proc sort, proc print, libname statement, sas programmer, error message, macro definition | source | 7 |
| 256 | You Want to Analyze All of the Oil Production Data for 90% of Canada Using the SAS System for PCs? You Gotta Be Kidding! | Ned Etris, Mark Bercov |
Canadian Hunter Exploration Ltd. has created a graphical evaluation system that characterizes the production performance and reservoir rock quality of al1 of the oil pools in Alberta, based entirely on the SAS System for PCs, release 6.04 for DOS. The system consists of two parts: a set of separate programs that process oil well and oil pool data, combining them into a strictly pool-based database, and a set of integrated programs that create one textual report and forty graphs per pool. Development of this system utilized several SAS System products. Creation of the database involved consolidation of raw data from different sources for over 54,000 wel1s and over 8,000 oil pools, as wel1 as correction of errors and inconsistencies in the data, and calculation of the appropriate statistical swnmary infonnation from the data. Major concerns such as data storage, data integrity and consistency, speed of analysis, rapid data retrieval, and graphical design had to be addressed | proc step, raw data | source | 6 |
| 257 | You Want to Produce 83,000 Graphs Using SAS Software on a PC? You Gotta Be Kidding! | Mark Bercov, Ned Etris |
Canadian Hunter Exploration Ud. has created a database/graphical evaluation system which characterizes the production perfonnance and reservoir rock quality of all of the oil pools in Alberta, based entirely on SAS 6.04 on the PC. The system consists of two parts: a set of separate programs that process oil well and oil pool data, combining them into a strictly pool-based database, and a set of integrated programs which create one textual report and forty graphs per pool. Development of this system was truly an adventure. Creation Qf the database involved consolidation of raw data from different sources for over 54,000 wells and over B,OOO oil pools, as well as correction of errors and inconsistencies in the data, and calculation of the appropriate statistical | missing value, macro definition | source | 6 |
| 258 | ZAP to ZAPS | Jason Moore | dataset, proc step, proc contents, proc copy | source | 7 |
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.