Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.
| From | "Eike Mark Rinke" <emrinke@web.de> |
| To | statalist@hsphsun2.harvard.edu |
| Subject | st: comparing mixed-effects regression coefficients between models |
| Date | Tue, 24 Jul 2012 16:24:44 +0200 (CEST) |
Dear statalisters, I would like to compare two coefficients for the same regressor between two multilevel mixed-effects linear models with different outcomes (but otherwise identical specification, and estimated on the same sample, with only minor differences between models due to missing values). However, I do not seem to find a way to accomplish this task, so I am turning to the list for advice. The situation looks something like this in Stata: xtmixed y1 a b || id: // model a xtmixed y2 a b || id: // model b Is there a way to test for the difference between the coefficients/partial correlations a --> y1 and a --> y2? In other words, is there a way to test if a is significantly more strongly/weakly associated with y1 than with y2? (Using -suest- with subsequent Wald testing does not seem to work in a mixed-effects setting; suest produces the following error upon an attempt to combine estimates for models a and b: >>unable to generate scores for model M19 suest requires that predict allow the score option<<) I'll be grateful for any thoughts, suggestions, pointers or immediate solutions for this problem. Eike -- Ihr WEB.DE Postfach immer dabei: die kostenlose WEB.DE Mail App für iPhone und Android. https://produkte.web.de/freemail_mobile_startseite/ * * 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/