Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.
From | SAM MCCAW <sam2stata@gmail.com> |
To | statalist@hsphsun2.harvard.edu |
Subject | st: Trouble with mixlogit (error) with binary dependent variable |
Date | Tue, 29 Jan 2013 19:55:52 -0500 |
Dear STATA gurus, I am having trouble running a mixed logit model. Please help! - The dependent variable is binary (0,1) (innovation). - My independent variables (var1 var2 var3) are continuous variables (they are logs of a count, excluding 0). -The group variable just takes a value of 1 or 2, because I only have two choice occasions, using: egen group = group(innov_1) - Code: mixlogit innov, group(group) rand(var1 var2 var3) id(id) or mixlogit innov var4, group(group) rand(var1 var2 var3 var5) id(id) I am getting the following errors: [P] error . . . . . . . . . . . . . . . . . . . . . . . . Return code 2000 no observations; You have requested some statistical calculation and there are no observations on which to perform it. Perhaps you specified if exp or in range and inadvertently filtered all the data. (end of search) I have over 30,000 for all the variables specified in the simplest model I ran and I still get the same error. Here are the sumamry statistics for my variables: Variable | Obs Mean Std. Dev. Min Max -------------+-------------------------------------------------------- innov_1 | 32523 .4774467 .4994988 0 1 var1 | 33065 2.104231 1.589854 0 4.859812 var2 | 33065 1.669999 1.0031 0 4.060443 var3 | 33065 .6736071 .9022467 0 3.78419 var4 | 33065 2.141496 2.795201 0 9.953027 -------------+-------------------------------------------------------- var5 | 28893 1.506202 .9606917 0 3.295837 var6 | 5953 -2.335463 1.106637 -4.60517 1.96611 I am completely lost about what to do next. Thanks for your help. SAM * * 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/