Regression Integration
From sasCommunity
Russell Hendel, Ph.d A.S.A, Center for Beneficiary Choices, Baltimore, MD
ABSTRACT
Professor Russell Hendel's presentation of the powerful regression analysis and graphical tools within the SAS System with which to analyze data. It takes time to learn how to write a program to obtain outputs. The purpose of this presentation is to describe the next step AFTER outputs are obtained.
(a) Should you use the output model--how do you decide?
(b) How do you interpret the outputs?
(c) How do you predict using the model and with what confidence can you do so?
(d) If the model is poor can it be fixed?
Topics presented include:
Reading a REGRESS output; Confidence levels for prediction; ranges; using residual-X graphs; graphical tests for linearity-normality-independence; standard remedy transformations; omitted variables; advanced tests.
Click here to see the entire article.
