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: multiple imputation


From   <als59@georgetown.edu>
To   statalist@hsphsun2.harvard.edu
Subject   st: multiple imputation
Date   Wed, 15 Sep 2010 12:24:02 -0400 (EDT)

To start, I should let you know that I'm new to both Stata and this listserv, and in addition to just learning the basic stata syntax, I'm probably not as computationally sophisticated as most members here.

I have two questions. 

1)When running regressions in Stata, R-sq and Adj R-sq are provided in the output.  However, when I run mi estimate: regress (for multiple imputation), no R-sq is provided.  Does anyone know how to get the R-sq and Adj R-sq in the output while using mi?  (As a related issue, I tried using the beta option to get the standardized coefficients, but it didn't seem to work when using mi. Any way to do this?)

2) I want to use multiple imputation on sequential regression to see the change in R-sq with each block of variables.  I figured out that nestreg is the way to do run sequential regression, but it is not compatible with the mi command.  The manual says that one can use the cmdok option to force imputation of missing variables when the command is not compatible with mi, if it is a legitimate thing to do in general.  So my questions are: a) is it legitimate to use mi on missing data with nested regressions, and b) what would be the correct syntax (I can't seem to get it to work).

Thanks in advance to anyone who can help!

-Amy
*
*   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