MWSUG 2006 Papers - Index

39 papers. Source: MWSUG (Midwest SAS Users Group) conference proceedings.

#	Title ×	Authors ×	Abstract ×	Keywords ×	Pages
1	A Picture is Worth a Thousand Data Points: Using SAS Arrays, LAG Functions and ODS to Create a Flexible Survey Interviewer Tracking Chart	Joe Murphy	Advances in technology have made available a stagge ring amount of information on the survey data colle ction process for use in tracking field interviewer (FI) behavior. The data can be reviewed to detect ineff iciencies or protocol violations that may reduce data quality. The challenge lies in how to harvest these rich dat a sources to produce valuable tools for those who monitor the da ta. This paper presents a SAS technique developed by RTI International to compile raw record-of-calls data f rom individual field interviewers and display them in an interactive and informative format for data quality reviewers a nd field supervisors. Record-of-calls data contain the date, time, case ID, interviewer ID, and disposition code for e very call made to a household selected for a survey	excel, data cleaning, data step, lag function, proc step	9
2	A SAS Macro for Performing Backward Selection in Proc Surveyreg	Qixuan Chen	This paper describes a macro to do backward selection for survey regression. At each step of backward elimination, p-values are calculated by using `PROC SURVEYREG`. The p-values are sorted, and the maximum is compared to the staying criterion, which is defined by users, to decide if the corresponding variable should be eliminated. Users are required to provide a list of variables that should be included in all models and a list of variables that could be eliminated during the backward elimination procedure. This macro is also capable of handling categorical variables. In the process of explaining the macro code, we will review three ways of creating macro variables and the following SAS macro functions: %scan, %str, %eval, and %unquote	backward selection, regression analysis, proc surveyreg, predictor variable, sample, proc step, macro quoting function, macro definition	5
3	A SAS/AF Utility for Managing Stored SCL Lists	Derek P. Morgan	SCL lists are an important component of SAS System applications development. Unfortunately, there are no tools within SAS for the creation and editing of SCL lists that are stored as SLIST catalog entries. This describes one such application for the creation and management of stored SLIST entries. You can create an SLIST entry from an ASCII file, edit/delete existing SLIST entries, and write an existing SLIST entry to an ASCII file. The utility works on both named and ordered SLIST entries	txt, dataset	8
4	Accuracy or Efficiency in Merging	Cindy Liu	Merge is an often-used statement in SAS programming. Besides one-to-one merging and match-merging, sometimes we need merge datasets with specific conditions. For instance, we want to change the value of variable after merging. These tasks normally involve IF-THEN or SELECT statement. The efficient solution is to apply MERGE, IF-THEN or SELECT statements in one `DATA STEP`. The results would be inaccurate in some situation. In this paper, several error examples are given to show the outcomes when we apply the seemly efficient method described above. Specific care has to be taken when trying to find an efficient algorithm for data merging without losing accuracy	data step, pdv, set statement, select, merge statement	6
5	All Possible Model Selection in Proc Mixed - A SAS macro application	George C. J. Fernandez	A user-friendly SAS macro application to perform all possible model selection of fixed effects including quadratic and cross products in the presence of random and repeated measures effects using SAS `PROC MIXED` is available. This macro application will complement the model selection option currently available in the SAS `PROC REG` for multiple linear regressions and the experimental SAS `PROCEDURE GLMSELECT` that focuses on the standard independently and identically distributed general linear model for univariate responses. Options are also included in this macro to select the best covariance structure associated with the user-specified fully saturated repeated measures model; to graphically explore and to detect statistical significance of user specified linear, quadratic, interaction terms for fixed effects; and to diagnose multicollinearity, via the VIF statistic for each continuous predictors involved in each model selection step	feature selection, fixed effects, covariance, proc mixed, repeated measures, proc step, covariance structure, restricted maximum likelihood, predictor variable, macro definition, correlation, data visualization, spearman correlation, sample, interaction effect, sample size, akaike information criterion, dataset, excel	19
6	An Effective CLEANWORK.SAS for Windows	John M Wildenthal	SAS provides an effective utility for deleting orphaned work directories on Unix boxes. But their offering for Windows merely deletes everything older than a particular time (http://support.sas.com/techsup/unotes/SN/00 8/008786.html). This is unworkable for a server environment. This paper di scusses a short program for Windows that parses the root WORK directory and matches directory names to SAS v9 r unning processes. Directories that are not matched are then deleted		4
7	Association of Computer Operator Errors and Lunar Phases	David J. Corliss		proc reg, proc step, regression analysis	4
8	Avoiding Blind Dates with SAS	Derek P. Morgan	Everybody is familiar with the concept of blind dates. When the date is made, you have visions of what he or she will look like, but the reality doesn't always match that. You can have blind dates in the SAS System, too. This paper will show you how to avoid some of the possible pitfalls with dates (and times and datetimes) in your SAS code. We'll show how SAS handles dates and times through these examples of what can go wrong, and close with a discussion of `EXCEL` conversions	sample, date variable, flat file, sysdate9, excel, proc step, input statement, missing value, proc format, cpu time, error message, time.	14
9	Best Practices for Implementing a BI Strategy with SAS	Mike R Vanderlinden	Implementing a Business Intelligence strategy can be a daunting and challenging task. SAS has introduced many concepts to us by bringing a comprehensive BI solution to the market. While some of those topics are not new, they can certainly make us think more than before, which is a very good thing. Many companies go ahead with the installation and configuration of the SAS BI platform with very little planning, only to ask themselves many questions afterwards, questions that should have been answered early on. This paper describes the best practices for all phases of a Business Intelligence strategy implementation using the SAS platform. It will cover what needs to be considered during the planning phase such as architecture, security and optimization as well as introduce the different tools available for data collection and reporting and what it means in terms of changes to move from SAS Foundation to the SAS BI platform	sas administrator, sas management console, business intelligence, proc step	7
10	Checking Assumptions in the Cox Proportional Hazards Regression Model	Brenda W Gillespie		proc phreg, hazard ratio, proc step, regression analysis, hazard function, time-dependent covariate, outlier	70
11	Creating a Windows Service using SAS 9 and VB.NET	David J. Bosak	This paper describes how to create a Windows service using SAS 9 and VB.NET. VB.NET is used as a wrapper to SAS. The VB.NET executable is registered with the Windows Services Manager. You are then able to call SAS programs from the service	sas 9, exception handling, error message, sas enterprise guide	8
12	Creating and Exploiting Information Maps and Filters on Clinical Data	Brian K. Varney	Utilizing Information Maps with the SAS 9 Business Intelligence platform is vital in taking advantage of the software you have purchased. It is also a new concept in SAS development. This paper will focus on the creation of maps and filters as well as how to leverage these from SAS Enterprise Guide, SAS Add-in for Microsoft Office, Web Report Studio and SAS Web Report Studio on SAS data sets, OLAP cubes, and the information maps engine. Setting up information maps in an effective way can give information consumers an easy way to create reports and analyze data. In the clinical arena, this can give more power to non-programming statisticians, data managers, medical personal and management	sas enterprise guide, business intelligence, proc step	12
13	Data Transposition with Proc Report	Lingqun Liu	Transposition is a very common data manipulation task. W ith SAS, data transposition can b e carried out in more than one way. `DATA STEP` and `PROC TRANSPOSE` are the two most common	proc step, proc transpose, proc report, by group processing, numeric variable, class variable	12
14	Dependent Scores within KAI and MBTI Instruments	Marie Risov	Various psychometric instruments assessing human personality preferences strive to measure divergent aspects, such as career aptitude, creativity style, communication and learning style, to name just a few. Two of such instruments, Myers-Briggs Type Indicator and Kirton Adaptation-Innovation Inventory, were developed to measure personal preferences and creativity style respectively. These aspects were first assumed to be independent variables that contribute to a human character. This work uses a psychometric data set built over a decade by Rolf Smith's School for Innovators and shows that psychometric parameters tend to work in tandem, although more unusual cases exist and may be worth special attention. The assessment has been completed with the General Linear Model (GLM) and Generalized Linear Model (GLIM). The known psychometric scale correlations have been confirmed, and new insights have been discovered in regards to intra- instrument relationships	correlation, proc glm, proc step, proc genmod, link analysis, sample, sas enterprise guide, excel	9
15	Deploying SAS as the Cornerstone of a Stability Monitoring Program	Jeff Gardner	Both US and international regulations require pharmaceutical companies to perform stability testing on all marketed active pharmaceutical ingredients (APIs; also referred to as drug substances) and finished drug products to provide evidence on how the quality of such products varies with time under the influence of a variety of environmental factors such as temperature, humidity, and light. Data obtained during stability testing is used to establish a retest period or shelf life for a product as well as recommended storage conditions for the product. Inherent challenges faced by stability personnel charged with managing the storage and testing of a high volume of products and/or product configurations include (1) difficulty in distinguishing variability in test results from changes in the product over time, and (2) resource constraints on the capacity for statistical analysis and evaluation of stability data in a timely manner	regression analysis, data science, dataset, sample, confidence interval, residual, proc reg, proc step	9
16	Dynamic Titles & Footnotes Tool in a Clinical Study Report	Hangtao Xu		macro variable, excel	3
17	Enhancements to Maps Using the Annotate Data Set	David J. Corliss	The Annotate Dataset in SAS is employed to enhance maps. Records are created for the display of list of landmarks and railroad routes using latitude and longitude coordinate s. Data for Alaska and Hawaii are projected with a separate location for each state and a reduced scale for Alaska, allowing the display of points in the preferred USCOUNTY map format	dataset, proc step	7
18	Exploring DICTIONARY Tables and SASHELP Views	Kirk Paul Lafler	SAS users can quickly and conveniently obtain useful information about their SAS session with a number of read - only SAS data views called DICTIONARY tables or SASHELP views. At any time during a SAS session , information about currently defined system options, libnames, table names, column names and attributes, formats, indexes, and more can be accessed and captured . This paper explores the purpose of DICTIONARY tables and views, how they are accessed, and what information is available to SAS users. Attendees will learn how these important tables and views can be accessed and applied using real-world scenarios	dictionary tables, proc sql, proc step, sas library, options statement, select	6
19	Futrix V5 Integration with the SAS BI Server for OLAP Cubes	Donald L Penix Jr.	The Futrix tool set had already provided extensions to the SAS System that made the building of OLAP Server cubes a painless and quick process. Futrix V5 is the first release that in tegrates with the SAS 9 BI Server architecture in an iterative approach. In additi on to the previous ability to build, query, and optimize OLAP cubes, Futrix users can now integrate the application with the SAS Metadata Server, the SAS Information Delivery Portal, and utilize the SAS 9 security architectu re. This presentati on will demonstrate Futrix V5 and how it efficiently interacts with the SAS 9 BI Server	sas 9, sas data integration studio	8
20	How to Incorporate Old SAS Data into a New DATA Step, or "What is S-M-U?"	Andrew T. Kuligowski	The `SET` statement i s commo nly used to concatenate two or m ore SAS datasets together. Let us look at a basic example: S-M-U. Some people will see these three letters and immediately t hink of the a bbreviation f or a p rivate university and asso ciated football team in Texas. Others might treat them a s a three-letter word, and recall a whi msical ca rtoon cha racter created by Al Capp many years ago. However, in the world of the SAS user, these three letters represent the building blocks for processing SAS datasets through the SAS `DATA STEP`. S, M, and U are first letters in the words SET, MERG E, and UP DATE - the 3 com mands used to introduce SAS data into a `DATA STEP`. DATA newdata; SET olddata1 olddata2; / additional statements /	dataset, libname statement, set statement	9
21	How to use Summary Statistics as raw data to do basic statistical analysis	Dachao Liu	Summary statistics can be N MEAN STD or even CORRELATION MATRIX. We can use them to do the same statistical analysis as we can do with the raw dataset. This will help us to save time and space if we just keep summary statistics in some situation or help us to figure out other test statistics by using summary statistics when we are reading a research paper. This paper will discuss how to use summary statistics as raw data to do basic statistical analysis	proc means, raw data, proc step, correlation, data science, character variable, proc corr, excel, proc freq, regression analysis	6
22	Illustrating generation of MSWord tables via HTML with the %cattable and %contable macros	Matthew T. Karafa	The author presents two macros for use in SAS version 7.0 or higher. The %cattable macro takes a list of any number of categorical factors, and %conttable takes a similar listing of continuous factors. Both macros present the association of the list with a 2-level response variable and provide summary statistics taken from several procs with many options for table appearance and statistic selection including odds ratios and appropriate significance levels from both parametric and non-parametric methods. The author uses these two macros, which generate manuscript- ready descriptive summary tables, to demonstrate how to take Microsoft Word mock-up tables and generate SAS code that produces customizable tables from `ODS` output datasets and `DATA STEP` code. Used in conjunction with Microsoft Word's ability to read and interpret HTML files these allow additional flexibility in formatting and layout often difficult to achieve using the `ODS RTF` destination	odds ratio, exact test, wilcoxon test, p-value, response variable, sample, data step, proc means	6
23	Inline Formatting + Long Character Variables = Wow! That's SAS?	Derek P. Morgan	Version 8 of SAS expanded the maximum size of character variables, and this is a practical use of that capacity. When you combine this with a custom `ODS` template, in-line formatting, and the `REPORT` procedure, you can build a report that will look as if it came from a word processor	character variable, proc report, proc step	4
24	Joining Wide Tables with PROC SQL	John M Wildenthal	SQL is easier to use if one does not need to hand code the SELECT clause. Hand coding is particularly onerous for wide tables. This paper shows how to get SAS to do it for you	proc sql, proc step	4
25	Journeymen's Tools: Data Review Macro FreqAll: Using Proc SQL List Processing with Dictionary.Columns to Eliminate Macro Do Loops	Ronald J. Fehd	The SAS R⃝ macro language is simple, yet powerful. List Processing with `PROC SQL` is also simple, yet powerful. This paper provides a data review macro FreqAll which illustrates using `PROC SQL` reading Dictionary .Columns to replace macro %do loops. Expected audience is advanced users, and macro programmers	proc step, proc sql, macro variable, proc freq, macro loop, do loop, proc append, select, proc univariate, macro call, %if-%then-%else, macro definition, proc print	12
26	Leveraging SAS Portal: An Executive Dashboard with Customizable Data Source	Elibeth R Carpenter	Data is one of the biggest assets of corporations, and the ability to analyze it drives corporate goals, strategies and results. One of the latest trends in business intelligence is the use of Key Performance Indicators (KPI) to measure corporate performance, in an easy to read GUI. SAS provides a great deal of tools to generate this kind of interface; the question is how to create a flexible, attractive and meaningful Dashboard integrated into the SAS Portal. This paper will step through the implementation of an Executive Dashboard as a Portlet Template (or Editable Portlet) that summarizes data and represents it with SAS Critical Success Factor graphs, using the SAS Java Connection Factory and the SAS Rangeview applet. Additionally, this Portlet illustrates the key benefit of SAS Editable Portlets by allowing the users to choose the data they want to diagram. They will be able to run stored processes and generate or modify the source data, all at the tips of their fingertips	connection pool, dataset, sample, raw data	20
27	Matched Case-Control Techniques: A Data Manager's Case Study	Matt P Shevrin	To accurately test outcome differences between retrospectively defined case and control samples, it is advisable to match the samples on characteristics that could otherwise bias the results. Successful application of this method, known as matched case-control, involves the following steps: Collection of descriptive information by treatment groups, means testing and analysis of key attributes, identification of outlying characteristics, and the random exclusion of controls using data-specific criteria. This paper will describe base SAS programming techniques to effectively and impartially normalize a control group to a case group for an epidemiological study	proc step, frequency analysis, proc freq, sample, group by, proc surveyselect, sas base	12
28	Modifying the LogParse PassInfo Macro	Ronald J. Fehd	This paper examines the issues of building a SAS usage database by modifying macros used to read the job and rtrace logs to provide a common key in each log for joining the job times with the products used. Expected audience is advanced users, macro programmers, site and server administrators. Readers are expected to be familiar with issues of configuration and running programs as a batch process. Keywords: altlog log logparse passinfo rtrace rtraceloc . Contents Database Theory 2 The LogParse Suite 2 The Rtrace Suite 2 Accuracy of `DATETIME` 3 Modifying SASv?.cfg 4 Modifying Autoexec.sas 5 Modifying PassInfo 5 Modifying LogParse 6 Modifying RTRACERD 7 A Demonstration Suite 7 Merging Time and Product Usage 10	proc step, macro put, proc print, proc sql, macro variable, cpu time, proc options, %if-%then-%else	11
29	Nonparametric Inference for Ordered Alternatives in a One-Way Layout Using	Paul Juneau	The one-way layout is a commonly used experimental design in scientific research (Juneau, 2004). W ith such a design it is easy to test alternative statistical hypotheses of interest including all pair-wise comparisons of treatment effects or all pair-wise comparisons with a designated (control) group. Sometimes a natural ordering exists among the treatments in an experiment; e.g., the treatment levels in the study may represent increasing doses of a single agent and an investigator may conjecture, a priori, that the response will be decreasing (or increasing) with increasing levels of dose. It could also be the case that an inv estigator might wish to study if the response increases up to a certain treatment level and then begins to decrease over the remaining ordered levels. SAS affords the user the ability to analyze data in both of these settings	sample, proc freq, proc step, sample size, null hypothesis, exact test, phase ii, dataset, clinical trial	15
30	Parsing Variable Lists: A Macro Function for Macros	Jimmy Zou	Variable lists are often used in SAS procedures and DATA steps for referencing groups of variables. However, in many situations variable lists cannot be used directly in macros without enumerating the variables, which limits the macros' capability of working with multiple variables. To make macros work with any variable lists just as SAS procedures do, it is essential for the macros to be able to parse the variable lists. This paper presents a macro function %Parse(dsn, varlist <, nvars>) that can parse any variable list (varlist) for a given data set (dsn). The variable list can be a conventional SAS variable list (like those used in `PROC` steps and DATA steps) or a Perl regular expression. The function returns a complete list of variable names corresponding to the variable list. Optionally, the function saves the number of variables in the list to a global variable (nvars) specified by the user	variable list, macro function, variable, proc step, name range list, macro definition, macro variable	10
31	Pruning the SASLOG - Digging into the Roots of NOTEs, WARNINGs, and ERRORs	Andrew T. Kuligowski	You've sat through constant design meetings. You've endured countless requests for "just one more little change". You even managed to find a creative solution to that nagging technical problem. But, you persevered, and despite all of the obstacles, you've managed to eliminate the final syntax error in your newest SAS routine. Time to sit back and relax -- uh, not quite ... The primary focus of this presentation will be on techniques to ensure comprehension of your input data. We will look at several messages that are often found in the `SASLOG`, such as: NOTE: `MERGE` statement has more than one data set with repeats of BY values. that imply that there may be gaps in your knowledge of your data! Special emphasis will be placed on the use of ad-hoc queries to assist in finding data anomalies that can cause problems with your SAS code	input statement, numeric variable, proc step, merge statement, out=, index, data cleaning, infile statement, proc means, dataset, e., sample, put statement	10
32	SAS Enterprise Guide Custom Tasks	Alex Dmitrienko	SAS Enterprise Guide comes with a large number of built-in tasks for various data access, manipulation and analysis needs. In addition, Enterprise Guide provides a unique framework for creating new tools known as custom tasks. Custom tasks feature attractive graphical user interfaces and can significantly shorten the user's learning curve and greatly increase his/her productivity. This paper will provide a high-level overview of Enterprise Guide custom tasks, installation procedures and other features. It also provides useful information for custom task developers, for exam- ple, describes the underlying data model, how custom tasks interact with the SAS System and how to build custom tasks	sas enterprise guide, macro definition, data cleaning, proc freq	7
33	SAS Macros for Statistical Analysis and Data Management	Brandy R. Sinco		proc step, proc freq, regression analysis, macro definition, call symput, sas log, macro variable	14
34	Some Common and Not So Common Uses of Pipes in a Windows Environment	Brian K. Varney	Utilizing pipes from Windows programs opens up new possibilities and functionalities. This paper will introduce and show examples of some common and not so common uses of pipes in a Windows environment. Pipes can also be a very powerful tool in other operating systems but that is outside the scope of this paper		7
35	That's the Signpost Up Ahead Your Next Stop, SAS IML	Gary Allen		dataset, input statement, sas base, infile statement, flat file, sample, file statement, proc iml, proc step, character variable	10
36	The Metadata Survey Method: Phase II	Derek P. Morgan	The metadata method was developed to bypass obstacles related to staff resources for end-user data capture. It uses SAS datasets to implement program control as well as provide questions and responses. A fixed series of `SAS/AF` frames interact with the user, yielding a consistent user interface. The frame code does not change between surveys-the datasets do. Phase 1 consisted of the development and deployment of a prototype application to administer one specific survey. Since the initial deployment of version 1.0 of the metadata software, the method has been refined, and design and development improvements have been made towards the ultimate goal of turning the metadata method into a system for end- user data capture. In order to utilize version 2 of the metadata software, a series of tools have been created so that semi- technical users may create and modify the control datasets necessary to implement the metadata system	txt, sample	21
37	The Projman Application: Allowing SAS to Manage Your Project	Jon M Patton	`SAS/OR` software has four major procedures that can be used to manage your projects. The CPM and PM procedures can be used for scheduling tasks that make up the project. The `GANTT` procedure displays this schedule, and the `NETDRAW` procedure displays the project network made up of these tasks. These four procedures are integrated into the Projman application which is a friendly graphical user interface which is included as part of the `SAS/OR` software. This tutorial will cover the usage of these four procedures and the Projman application. The early part of the tutorial will cover the definition of terminology that is critical for understanding the output results	data governance, resource allocation	11
38	Time to Failure in UPS Data Collector and UPS Thermal Printer	Rebecca E Dennison	The purpose of this study is to model the effect of equipment age and model on the time to failure in "UPS Data Collector" and "UPS Thermal Printer" units repaired in 2003. The data were analyzed using a generalized linear model. The generalized linear model assumed a Poisson distribution with a log link function and an offset based on the natural log of the population. Life tables were calculated for the time to failure using equipment model and age as strata. Proportional hazards were also calculated using equipment age and model predicted time to failure. The generalized linear model appeared statistically significant overall (p-value <0.001). The effects of model and equipment age also appeared statistically significant (p-value <0.001 for both). However, 17.6% of the units had not been returned for repair by 4/30/2006, the end of the study, undermining the validity of these results	proc phreg, life table, poisson distribution, proc genmod, proc step, sample, box plot	10
39	Using Biweights for Handling Outliers	George W Dombi	Values far from the center of the data are called outliers. These can be highly influential in determining the character of descriptive statistics. M-estimators are a class of central tendency measures than replace the mean and are highly resistant to local misbehavior caused by outlier data. Beaton and Tukey introduced the biweight as an iteratively reweighed measure of central tendency. Huber also introduced a different but complementary M-estimator. SAS will calculate both the biweight and the Huber weight function in `PROC STDIZE`. `PROC NLIN` will allow for biweight and Huber weights to be utilized in user developed equations	proc step, proc nlin, central tendency, outlier, proc stdize, anova, proc means, raw data, inferential statistics, proc anova	9

Back to Conf go 2007 go 2005

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.