Pre-conference Seminars & Statistical Tutorials
Pre-conference activities
There are a number of ways to expand your learning opportunities at SAS Global Forum. Sign up to participate in a Monday seminar or statistical tutorial or one of the pre- or post-conference SAS training classes.
Monday Seminars and Statistical Tutorials
Monday, April 16
Join your fellow conference attendees at one of these educational opportunities.
- Seminars are available in the morning and afternoon. The fee for seminars varies based on the materials provided. In the morning seminars, you will receive appropriate handouts. If the instructor has selected a book, you will also receive a book. In the afternoon seminars, you will receive appropriate handouts. The afternoon seminar sessions will be conducted by SAS Education instructors.
- Statistical Tutorials cost $95 each, and you will receive appropriate handouts. All Statistical Tutorials will be taught by SAS' Research and Development staff.
| Monday Seminars | |||
| Separating the Interface from the Engine: Creating Custom Add-in Tasks for SAS Enterprise Guide® (Fee $125) | Counting the Ways to Excel (Fee $125) |
||
| PROC SQL Programming: Beyond the Basics (Fee $155) | Modernizing Your SAS Code, or How To Avoid Becoming a SAS Dinosaur (Fee $125) |
||
| Exploring Graphical Data Analysis in Model Building and Prediction (Fee $125) | Using the Output Delivery System to Generate PDF and HTML Files (Fee $125) |
||
| Creating and Exploiting SAS Indexes for Better Program Performance (Fee $155) | Understanding Why Your Macros Don't Work (Fee $125) | ||
| Statistical Tutorials | |||
| 8:00 a.m. - 10:00 a.m. (concurrent offerings) |
10:30 a.m. - 12:30 p.m. (concurrent offerings) |
||
| Modern Regression Analysis (Fee $95) |
Statistical Analysis with the GLIMMIX Procedure (Fee $95) | ||
| Structural Equation Modeling Using the CALIS Procedure (Fee $95) | Introduction to Logistic Regression (Fee $95) |
||
Monday Morning Seminars
8:00 a.m. - 11:30 a.m.
- Separating the Interface from the Engine: Creating Custom Add-in Tasks for SAS Enterprise Guide® 4.1
Instructor: Peter Eberhardt, Fernwood Consulting Group
SAS Enterprise Guide 4.1 provides a ton of tasks to tickle travels into the world of data exploration and presentation. However, there are times when our fancy is not tickled just as it should be. Perhaps you need a front end to existing SAS reports, or perhaps you need a dynamic lookup screen. Whatever the need, developing a custom add-in task may be the answer.
This seminar will show you how to create custom tasks for use in SAS Enterprise Guide and the add-in for Microsoft Office using C# .NET. It will guide you through the tools you need to get started and then dive right into the programming. You do not need to know much about SAS Enterprise Guide or the add-in for Microsoft Office; however, you should have at least a rudimentary knowledge of object-oriented languages, preferably Microsoft's C#.
- PROC SQL Programming: Beyond the Basics
Instructor: Kirk Lafler, Software Intelligence Corp.
Expand your PROC SQL skills beyond the basics with this PROC SQL programming techniques seminar. The instructor will present numerous examples of this powerful database language to improve your mastery of the procedure while providing a better understanding of the language details to perform more complicated tasks. Topics include using case expressions, strategies for creating and using views, performing complex queries with joins and set operators, concepts for creating and using indexes, debugging techniques (including documented and undocumented features), implementing table integrity constraints, and query performance tuning strategies.
- Exploring Graphical Data Analysis in Model Building and Prediction
Instructor: George Fernandez, University of Nevada, Reno
Exploratory graphical data analysis methods stress visualization to thoroughly study the structure of data and to check the validity of statistical model fit to the data. This half-day seminar covers fundamental concepts for understanding and successfully applying data visualization and graphical data analysis methods by using the powerful user-friendly SAS macro applications. These concepts will be illustrated via downloadable SAS macro files. The learning outcome of this seminar is to train the participants in data exploration, best candidate model selection based on AICC and SBC, model fitting, model validation, and graphical data analysis methods used in multiple and logistic regression modeling. This seminar is intended for data analysts, predictive modelers, statistical consultants and biostatisticians in advanced training in data exploration and graphical data analysis methods for increasing the effectiveness, efficiency and productivity in predictive modeling. Participants are required to have an understanding of basic statistical methods and an introductory working knowledge of SAS systems.
- Creating and Exploiting SAS Indexes for Better Program Performance
Instructor: Michael Raithel, Westat
If there were a performance tool that could drastically reduce your SAS program's I/O and response time and lower its CPU time, would you use it? Of course you would! SAS indexes are performance tools that can dramatically improve the performance of programs that access small subsets of observations from large SAS data sets. However, many SAS programmers never bother to learn about them or to use them. This is your opportunity to add this powerful performance tool to your SAS programming repertoire.
In this seminar, you will learn how to create simple and composite SAS indexes, determine which variables make good index key variables, discover when creating and using indexes is appropriate, understand the four SAS statements that actually invoke indexes, learn about centiles, find out how to generate index usage messages, and learn how to recover damaged or missing indexes. You will see firsthand how indexes can improve processing when subsetting and/or updating a large SAS data set. To be successful in this seminar, you should have base SAS knowledge, including experience creating and updating permanent SAS data sets. You will leave this seminar with a practical knowledge of how to create and use SAS indexes.
Statistical Tutorials
8:00 a.m. - 10:00 a.m.
- Modern Regression Analysis
Instructor: Robert Cohen SAS
Nonparametric and robust modeling are widely employed in modern regression analysis. Nonparametric analysis is used to model data for which knowledge of the underlying model is limited. Robust parametric or nonparametric methods are appropriate when data contains outliers. This workshop is intended for a broad audience of statisticians and data analysts who are interested in modern regression methods.
This workshop describes these methods and SAS tools for fitting the following:
- Robust local regression models with the LOESS procedure.
- Robust parametric models with the ROBUSTREG procedure.
- Quantile regression models with the new QUANTREG procedure.
- Mixed model smoothing with the new GLIMMIX procedure.
- LASSO/LAR regression models with the new GLMSELECT procedure.
- Structural Equation Modeling Using the CALIS Procedure
Instructor: Yiu-Fai Yung, SAS
Structural equation modeling is a general modeling technique that covers a wide range of statistical applications in many fields. For example, in substance abuse studies, it can determine factors that are responsible for different types of abuse, whereas in Web-behavior research, it can locate the most important determinants for attracting Web-surfing behavior. Starting with the relationships among variables described by simultaneous equations or a path diagram, structural equation modeling offers an integrated analysis of the entire theoretical model. Other advantages of structural equation modeling include the use of latent variables for defining theoretical constructs that have no measurement errors (such as self-esteem) and the ability to handle reciprocal causation (such as a supply and demand relationship). Participants will be introduced to basic models such as path analysis, confirmatory factor analysis, causal models with latent variables, and patterned covariance matrix analysis. Through the use of examples, participants will learn when to use these models and how to apply the CALIS procedure to formulate models, estimate model parameters, and assess and improve model fit.
- Statistical Analysis with the GLIMMIX Procedure
Instructor: Oliver Schabenberger, SAS
This tutorial focuses on the new GLIMMIX procedure for analyzing generalized linear mixed models in SAS. The first part of the tutorial introduces the class of generalized linear mixed models and discusses statistical estimation and inference techniques. The second segment introduces the GLIMMIX procedure through syntax and comparisons to other procedures in SAS/STAT®. Numerous applications are presented to highlight the capabilities of PROC GLIMMIX in estimation and inference for normal or non-normal data with complex variation.
This tutorial requires basic knowledge of linear mixed models and the MIXED procedure in SAS/STAT.
- Introduction to Logistic Regression
Instructor: Bob Derr, SAS
Logistic regression is one of the basic modeling tools for a statistician or data analyst. This tutorial uses real examples to delve into the basic methodology behind logistic regression and discusses parameterization, testing goodness of fit, model evaluation and interpretation of results. The tutorial focus is on binary response; time permitting, direction for handling ordinal response will also be provided. Attendees should have a solid foundation in regression.
Monday Afternoon Seminars
1 - 4 p.m.
- Counting the Ways to Excel
Instructor: Cynthia Zender, SAS
Do you need to output SAS data sets or procedures to Excel? Do you know whether you're using the right technique for your requirements?
This seminar outlines all the ways to get information from Base SAS to Excel. The method you choose depends on whether you're dealing with a SAS data set or SAS procedure output. Topics include using the SAS Excel Libname engine; using PROC EXPORT; and using ODS to create CSV, HTML and XML files that can be opened by Excel. The instructor will provide a brief overview of non-SAS technology, such as DDE and ODBC. She will also provide relevant SAS code for the Base SAS techniques. Selected non-SAS techniques will be discussed, but not demonstrated.
- Modernizing Your SAS Code, or How To Avoid Becoming a SAS Dinosaur
Instructor: Warren Repole, SAS
New features of the SAS programming language often permit the replacement of complex algorithms and clunky workarounds with more elegant code. Some enhancements support the creation of more efficient solutions. Occasionally, optimal techniques have existed for a while, but they have been overlooked or underused.
Whether you are a SAS programmer with many years of experience or a novice user who is responsible for maintaining legacy programs, implementing updated approaches may allow you to streamline your SAS applications, expedite the development and debugging process, and minimize future maintenance of the code.
This seminar covers a wide range of discrete tasks with programming solutions involving the DATA step, Base SAS procedures, formats and functions, SAS macro language, SAS/GRAPH® software, and the SAS/ACCESS® software interface to PC files. While some of the solutions use SAS®9 enhancements, many of them rely on features introduced in earlier SAS releases.
- Using the Output Delivery System to Generate PDF and HTML Files
Instructor: Rick Bell, SAS
This presentation is designed for users who are new to the Output Delivery System (ODS) and want to create RTF, PDF or HTML output from SAS data, enhance reports using options and predefined styles, and customize the appearance of PROC PRINT output. This course focuses on how to use ODS to create RTF, PDF and HTML output from SAS procedures. In addition, students learn the basic terminology of ODS and practice techniques for enhancing output by using predefined styles and special options in the TITLE and FOOTNOTE statements.
- Understanding Why Your Macros Don't Work
Instructor: Michelle Buchecker, SAS
This brain-teasing seminar will discuss the behind-the-scenes workings of the macro facility and explain why macro variables you thought would resolve don't; why you need an extra period or four after a macro variable reference; why you care about the difference between %LET and CALL SYMPUT; and what all those extra ampersands mean. Some macro knowledge is recommended before attending this seminar.