|
Activity Number:
|
545
|
|
Type:
|
Contributed
|
|
Date/Time:
|
Thursday, August 2, 2007 : 10:30 AM to 12:20 PM
|
|
Sponsor:
|
Section on Statistical Computing
|
| Abstract - #309267 |
|
Title:
|
Purposeful Selection of Variables in Logistic Regression: Macro and Simulation Results
|
|
Author(s):
|
Zoran Bursac*+ and C. Heath Gauss and D. Keith Williams and David Hosmer
|
|
Companies:
|
University of Arkansas for Medical Sciences and University of Arkansas for Medical Sciences and University of Arkansas for Medical Sciences and University of Massachusetts Amherst
|
|
Address:
|
4301 W Markham, Little Rock, AR, 72205,
|
|
Keywords:
|
logistic regression ; SAS PROC LOGISTIC ; variable selection algorithm ; purposeful selection ; confounding
|
|
Abstract:
|
The main problem in any model-building situation is to choose from a large set of covariates those that should be included in the "best" model. A decision to keep a variable in the model might be based on the clinical or statistical significance. There are several variable selection algorithms embedded in SAS PROC LOGISTIC. Those methods are mechanical and carry limitations. Hosmer and Lemeshow (2000) describe a purposeful selection of covariates algorithm within which an analyst makes a variable selection decision at each step of the modeling process. In this paper, we introduce a macro, %PurposefulSelection, which automates this process. We conduct a simulation study to compare the performance of this algorithm with three well-documented variable selection procedures in SAS PROC LOGISTIC: FORWARD, BACKWARD, and STEPWISE. Results and implications are discussed in more detail.
|
