svypois ...., subpop(cesdage1) predict predicted if e(sample) sum predicted if cesdage1==1 I hope this helps, Scott ----- Original Message ----- From: "Laurel A Copeland" <lacop@umich.edu> To: <statalist@hsphsun2.harvard.edu> Sent: Thursday, December 19, 2002 11:14 AM Subject: st: Sample restriction in -predict- following regression with -subpop- > Could someone point me to information on what restriction, if any, is > placed on the population for which -predict- produces values, after a > regression for which a subpopulation is specified? I do not find -predict- > and -subpop- together using -findit-. Here is an example of what we are > running. > > svypois cesd_2 pred1 pred2 pred3, subpop (cesdage1) > predict predicted > sum predicted cesd_2 > > The above seems to produce values for the whole sample, not just the > subsample. Is that right? > > Will this give us the subsample specified by "subpop (cesdage1)" ? > > svypois cesd_2 pred1 pred2 pred3, subpop (cesdage1) > predict predicted > sum predicted cesd_2 if cesdage1==1 > > Thank you, > Laurel & Liz > * * For searches and help try: * http://www.stata.com/support/faqs/res/findit.html * http://www.stata.com/support/statalist/faq * http://www.ats.ucla.edu/stat/stata/