Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.
From | Jorge Eduardo Pérez Pérez <perez.jorge@ur.edu.co> |
To | "statalist@hsphsun2.harvard.edu" <statalist@hsphsun2.harvard.edu> |
Subject | Re: st: robust estimation SUREG |
Date | Fri, 27 May 2011 12:47:38 -0400 |
You could use the -genwt- option in -rreg- to generate the weights used in the robust regression, then use those weights in -sureg-. You will have three sets of weights from your first three regressions, and -sureg- will only allow a set of weights, so you would have to combine them somehow. _______________________ Jorge Eduardo Pérez Pérez On Fri, May 27, 2011 at 12:11 PM, pierrick.jan@art.admin.ch <pierrick.jan@art.admin.ch> wrote: > Dear Stata-List Members, > > I am investigating the determinants of three indicators of corporate performance for a cross-section made of 480 firms. Due to the presence of outliers I performed in a first step a robust regression using the rreg command of Stata (rreg combines two types of robust weighting: iteratively reweighted least squares and biweight estimator). In a second step, for each of the three regressions performed, I predicted the residuals and investigated the correlation between the residuals of each of the three equations. It turned out that the residuals were correlated, which advocates for the use of a SUR model. Unfortunately I could not find any information on how to perform in Stata a robust estimation of the SUR model (i.e. on how to combine the robust approach underlying the rreg command and the SUR approach underlying the sureg command). > > Any suggestion will be greatly appreciated! > > Thanks in advance! > > Kind regards, > > Pierrick Jan > > * > * 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/