Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.
From | Maarten Buis <maartenlbuis@gmail.com> |
To | statalist@hsphsun2.harvard.edu |
Subject | Re: st: Correcting for bonferroni in logictic regression |
Date | Thu, 24 May 2012 14:48:02 +0200 |
On Thu, May 24, 2012 at 2:36 PM, Amal Khanolkar wrote: > I'm currently running logistic models, where my exposure variable has 20 categories. The model also includes another 4 potential confounders, some with 2-4 categories. Due to the high chance of multiple testing - I would like to know: > > 1. how one may correct for the same in Stata using Bonferroni's correction and You can do so by rejecting the null hypotheses if the p-value is less than a/k instead of a, whereby a is the significance level of your choice --- typically .05 --- and k is the number of tests. > 2. if the same can also be applied for polytomous regression (mlogit). Yes. Hope this helps, Maarten -------------------------- Maarten L. Buis Institut fuer Soziologie Universitaet Tuebingen Wilhelmstrasse 36 72074 Tuebingen Germany http://www.maartenbuis.nl -------------------------- * * For searches and help try: * http://www.stata.com/help.cgi?search * http://www.stata.com/support/statalist/faq * http://www.ats.ucla.edu/stat/stata/