Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.
From | Maarten buis <maartenbuis@yahoo.co.uk> |
To | statalist@hsphsun2.harvard.edu |
Subject | Re: st: Box Tidwell procedure & Wald Chi2 |
Date | Mon, 12 Jul 2010 02:29:00 -0700 (PDT) |
--- On Mon, 12/7/10, Cornelius Nattey wrote: > I know chi2 are used in contingency tables to check whether > there is an association between exposure variable and > outcome of interest ie tab death agegrp,chi2 or exact > What is the Wald X2? Within a model estimated with maximimum likelihood it is a test of a linear constraint on the parameter estimates. it has nothing to do with contingency tables other than it uses the same distribution for the sampling distribution of the test statistic under the null hypothesis. (Actually, I would not be surprised if you could reformulate the chi2 test for independence in a cross tabulation as a Wald test, but that would not help you here.) In Stata it is what you get when you use the -test- command after a model estimated with maximum likelihood, and it is the test reported in the output of that estimation command that appears after each coefficient. After -regress- you will get F-tests and t-tests respectively instead of Wald tests. -- 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/