Bookmark and Share

Notice: On March 31, it was announced that Statalist is moving from an email list to a forum. The old list will shut down on April 23, and its replacement, statalist.org is already up and running.


[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

st: Question about felsdvregdm/felsdvreg


From   "O'Brien, Rachel H" <rhobrien@stanford.edu>
To   "statalist@hsphsun2.harvard.edu" <statalist@hsphsun2.harvard.edu>
Subject   st: Question about felsdvregdm/felsdvreg
Date   Tue, 21 Jun 2011 11:14:23 -0700

Hi.  I am trying to use felsdvregdm to estimate teacher fixed effects and have run into an issue.  After I ran the program, I discovered that there was a mass of teachers with a FE estimate of 0.  Upon further investigation, I determined that all of these teachers have group==.  I am confused because I don't know what it means for group to be missing (although my guess is that these teachers' students never appear in other classes).  More importantly, I am running a one-level model, so my understanding is that group should be irrelevant, and I don't know why it would cause all of the estimates to be 0.  

In case it matters, in the model I am centering the estimates by the teacher's grade.  In my first run of the program, I inadvertently omitted one grade dummy.  I tried to fix this in a second run, but then I got the error message:

             decompreg():  3498  Firm effects are collinear with explanatory variables - cannot proceed
                 <istmt>:     -  function returned error

This confused me because the help file for the command indicates that you should include all indicators (there is no constant).  Now I am running the program without the dummies explicitly included which should force the program to include them for me.

Any help would be appreciated!

Rachel 

*
*   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/


© Copyright 1996–2014 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   Site index