Date:         Tue, 22 Apr 1997 10:21:20 -0400
Reply-To:     MAGOETZ@BICS.BWH.HARVARD.EDU
Sender:       "SAS(r) Discussion" <SAS-L@UGA.CC.UGA.EDU>
From:         Margaret Ann Goetz <MAGOETZ@BICS.BWH.HARVARD.EDU>
Subject:      Bonferroni correction?

Hello:
 
I'm currently working on a linear regression model with four independent
variables and sample size of 77.   The set of regression models can be
described as exploratory.
 
When I perform my final linear regression models, is it necessary to include a
correction for possible Type I error such as the Bonferroni correction? I'd be
particularly interested in arguments, both in favor of and against.
 
And, if YES, how would the Bonferroni correction be correctly applied for each
model conducted? (e.g., 4 regression models at alpha =.05 becomes .05/4 or a
significance level of .0125 for rejecting each indep var as significant?)?
 
Any help is very much appreciated!!  Thanks in advance!
 
Peggy
 
*******************************************************************************
 
MAGOETZ@BICS.BWH.HARVARD.EDU
617-278-0530 / fax 617-738-8703
Division of Psychiatry/Research
Brigham and Women's Hospital
Boston MA 02115