Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.
From | Edward Lorenz <ned.lorenz@gmail.com> |
To | statalist@hsphsun2.harvard.edu |
Subject | Re: st: Nested hypothesis testing with multiply imputed data using xtmelogit |
Date | Sat, 30 Nov 2013 18:16:31 +0100 |
Hello, I had looked at mi post-estimation and the mi test command. mi estimate performs the joint test that all coefficients are equal to zero (F statistic) and mi test performs joint tests that coefficients are 0. However I am interested in the empty two-level logistic model without covariates which explains why there is no F statistic in the results. The standard way to test the null hypothesis that the random variance component is 0 is a likelihood ratio test comparing the empty single level model with the empty two-level model. However there is no log likelihood statistic in the saved results e(b) e(V) after mi estimate with meqrlogit. Perhaps I am missing something but I do not see a way forward with mi test. If I don't respond right away it's because I am boarding an 11 hour flight. Thanks for any help On Sat, Nov 30, 2013 at 3:32 PM, Steve Samuels <sjsamuels@gmail.com> wrote: > > See the manual entry for - mi test-. > > Steve > > Steven J. Samuels > 18 Cantine's Island > Saugerties, NY 12477 > USA > > On Nov 29, 2013, at 4:03 AM, Edward Lorenz wrote: > > Hello, > > I am new to Statlist and I am hoping that someone familiar with > multiple imputation estimation knows whether it is possible to perform > nested hypothesis testing after using xtmelogit (now meqrlogit) on > multiply imputed data. I am doing a two-level logistic random > intercepts model. I would like to test the null hypothesis that the > estimate for the random parameter is zero. Without multiply imputed > data I would do this with a likelihood ratio test comparing the empty > single-level model with the empty two-level model. But I have learnt > that the log likelihood statistictic is not defined in the case of > multiply imputed data. Is there another way to do this test after mi > estimate: meqrlogit. Any help would be much appreciated. > > Edward Lorenz > * > * For searches and help try: > * http://www.stata.com/help.cgi?search > * http://www.stata.com/support/faqs/resources/statalist-faq/ > * http://www.ats.ucla.edu/stat/stata/ > > * > * For searches and help try: > * http://www.stata.com/help.cgi?search > * http://www.stata.com/support/faqs/resources/statalist-faq/ > * http://www.ats.ucla.edu/stat/stata/ * * For searches and help try: * http://www.stata.com/help.cgi?search * http://www.stata.com/support/faqs/resources/statalist-faq/ * http://www.ats.ucla.edu/stat/stata/