Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.
From | Maria Fleischmann <maria.s.fleischmann@gmail.com> |
To | statalist@hsphsun2.harvard.edu |
Subject | Re: st: increasing variance when adding covariates (xtmelogit) |
Date | Thu, 19 May 2011 09:55:03 +0200 |
Thanks, Garry! On 19 May 2011 09:36, Garry Anderson <g.anderson@unimelb.edu.au> wrote: > Hello Rob and Maria, > > This situation can occur and is explained on pages 217 and 229 of Snijders and Bosker (1999) > > Snijders T and Bosker R (1999) Multilevel Analysis: An introduction to basic and advanced multilevel modeling. Sage Publications. > > Kind regards, Garry > > > -----Original Message----- > From: owner-statalist@hsphsun2.harvard.edu [mailto:owner-statalist@hsphsun2.harvard.edu] On Behalf Of Maria Fleischmann > Sent: Thursday, 19 May 2011 5:07 PM > To: statalist@hsphsun2.harvard.edu > Subject: Re: st: increasing variance when adding covariates (xtmelogit) > > Hello Rob, > > did you yet get any answer on your question? perhaps on another way than statalist? > I would also be very interested the explanation because I had the same problem in one of my analyses. Back then, my supervisor told me that this was a rather frequent problem when modelling a multilevel logistic model. He however could not provide any explanations for this. > So if you get any more insight, I would be happy if you'd let me know too. > > Maria > > On 18 May 2011 13:44, de Vries, Robert <r.de-vries08@imperial.ac.uk> wrote: >> Hello all, >> >> I am getting some strange results from some multilevel logistic >> regression models (persons nested within geographical areas, random >> intercepts) run with xtmlogit. >> >> I am using xtmelogit to fit models predicting a binary outcome at the >> person level from some person-level and area level predictors. In the >> empty model (with no predictors) I get a certain estimate for the >> standard deviation of the constant. However, when adding person and >> country-level predictors to the model, the estimate of this property >> actually INCREASES quite substantially (by about 15-20%). >> >> As I take the standard deviation of the constant to be an indicator of >> (the square root of) the variance at the area level. It seems very >> strange that this would go up when adding predictors to the model. I >> would be grateful if anyone could shed any light on this situation. >> >> Rob >> * >> * 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/ >> > > * > * 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/ > > > > * > * 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/ > * * 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/