Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.
[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
Re: st: R squared after mi estimate: svy: regress?
From
[email protected] (Wes Eddings, StataCorp LP)
To
[email protected]
Subject
Re: st: R squared after mi estimate: svy: regress?
Date
Thu, 05 Jul 2012 17:19:35 -0500
Jennifer Braga ([email protected]) asked about obtaining R-squared and
contingency tables from multiply-imputed survey data:
> Thus, for my regression equation I use mi estimate: svy: regress. How do I
> generate R squared? I tried mibeta and noisily and wasn't able to generate the
> statistic.
> Also, I find I cannot use mi estimate: svy: tab for my nominal and ordinal
> level variables. I want to create a table of descriptive statistics that uses
> the multiply imputed data so that it is aligned with the following regression
> analysis that uses imputed data.
The -mi estimate- command does not support contingency tables or R-squared.
(-mibeta- is an unofficial command that reports R-squared but doesn't support
survey data.) Jennifer may, however, combine the R-squared values manually. A
method is outlined in the section on "Combining point estimates only" in the
following FAQ:
http://www.stata.com/support/faqs/statistics/combine-results-with-multiply-imputed-data/
--Wes
[email protected]
*
* 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/