Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.
From | Amy Hale <aehale38@gmail.com> |
To | statalist@hsphsun2.harvard.edu |
Subject | st: re: moderated mediation with multiple mediators |
Date | Sun, 16 Mar 2014 16:27:28 -0400 |
Hello, I am trying to measure moderated mediation in a 2-mediator model with bootstrapping estimates, but the usually-helpful UCLA tutorials cover mediation with multiple mediators and moderated mediation separately, using different commands for both the base commands and bootstrapping (-sureg- vs. -sem-, -bootmm- vs. -boot2m-). Can someone tell me how to combine these into a single model, or point me to a tutorial that does? The model I need to run is: - iv predicts med1 & med2 separately (exactly as in the UCLA example -www.ats.ucla.edu/stat/stata/faq/mulmediation.htm). - mod1 moderates both iv-->med1 and iv-->med2 (similar to Model 2 in the UCLA example, but in my case for two mediators - http://www.ats.ucla.edu/stat/stata/faq/modmed.htm#model2). There are no moderators for the med1-->dv or med2-->dv relationships. Any help on code (including bootstrapping estimates) would be much appreciated. All variables are continuous and I'm using Stata 12.0. Thanks, Amy -- Amy E. Hale, M.A. Department of Psychology University of Connecticut 406 Babbidge Road, Unit 1020 Storrs, CT 06269 * * 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/