Statalist


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

st: specifiy a multiple imputed dataset for "mim"


From   Thomas Lux <tholux2000@yahoo.de>
To   statalist@hsphsun2.harvard.edu
Subject   st: specifiy a multiple imputed dataset for "mim"
Date   Wed, 7 Oct 2009 15:10:12 +0000 (GMT)

Dear statalisters,

I have a dataset without imputed income and wealth. I want to combine it with multiple imputed wealth (5 imputations) generated by researcher A and multiple imputed income (5 imputations) generated by researcher B, because I want to do “mim: logistic”-analysis with the imputed income and wealth as independent variables.
Is it correct to store the combinations of main-data + imputed wealth + imputed income in 25 seperate datasets (5*5) before using mimstack?

Main data + wealth imputation A + income imputation A
Main data + wealth imputation A + income imputation B
Main data + wealth imputation A + income imputation C
...
Main data + wealth imputation B + income imputation A
Main data + wealth imputation B + income imputation B
Main data + wealth imputation B + income imputation C
And so on...


(I use stata 9.2)

regards,
Thomas



      

*
*   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   |   What's new   |   Site index