Making Business Decisions Using Linear Models in SAS: A Harvard Case Study

Duration: 2.0 days CEU: 1.2

Presented by F. Michael Speed, Ph.D. and Simon Sheather, PhD, professors at Texas A&M University

This advanced course identifies the benefits and pitfalls of using statistical analyses for making business decisions. It addresses practical applications of regression and analysis of covariance in a business setting using a Harvard Business School Case Study. The primary software used in the course is SAS Enterprise Guide, although some code is also used to run analyses.

Learn how to

make a business decision using linear models in SAS
build complex analysis of covariance models
determine the hypothesis being tested by SAS software
use and understand advance diagnostic techniques.

Who should attend

This course is aimed a business analysts as well as researchers in most disciplines including agricultural sciences, psychology, education, social science, engineering, and medicine. It is also appropriate for professionals conducting organizational or business research.

Prerequisites

Before attending this course, you should

be familiar with the basic structure and concepts of the SAS System, which you can gain from the SAS Programming I: Essentials course
be familiar with the core concepts of descriptive statistics and multiple regression
have completed the Statistics I: Introduction to ANOVA, Regression, and Logistic Regression course or have equivalent knowledge
have some experience using SAS Enterprise Guide, specifically being able to import data, open a data set, and run tasks.

Familiarity with the concepts presented in the Statistics II: ANOVA and Regression course is also helpful.

Course Contents

Business Scenario and Motivation: Harvard Case Study - Store 24

introduction
the main business issue

Introduction to SAS Enterprise Guide

overview of SAS Enterprise Guide
our first regression
interpretation of results

Preliminary Analysis of the Data

scatter plots
descriptive statistics
exploratory plots

Multiple Linear Regression

the model and assumptions
possible problem points, multicollinearity, and additional residual analyses
variable subset selection
making scale independent variables into categorical variables

Analysis of Covariance (ANCOVA)

introduction
the model and assumptions
residual analyses
variable subset selection

ANCOVA - Selected Topics (Self-Study)

pre-post analysis
LSMEANS versus MEANS

Software Addressed

This course addresses the following software product(s): SAS/STAT. This course also addresses Base SAS software, SAS/GRAPH software, and SAS Enterprise Guide.

Course Materials

Students receive a hardcopy of the course notes and, in some courses, can choose to take home a copy of the course data.

U.S. Schedule

29JAN2009 San Francisco, CA

02APR2009 Cary, NC

11JUN2009 Rockville, MD

Check for additional and updated schedule information online at support.sas.com/courses/bmbd.html.

Registration

To register for this course in the US, call 800-333-7660 or visit support.sas.com/training. This course is also available for on-site training, or you can create a custom course by combining material from several courses. For more details, contact SAS Education in Cary, NC at 919-531-7321 or send e-mail to training@sas.com.