Statalist


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

Re: AW: RE: st: RE: mim: reg command


From   Maarten buis <maartenbuis@yahoo.co.uk>
To   statalist@hsphsun2.harvard.edu
Subject   Re: AW: RE: st: RE: mim: reg command
Date   Tue, 20 Oct 2009 07:57:25 +0000 (GMT)


--------------------------
Maarten L. Buis
Institut fuer Soziologie
Universitaet Tuebingen
Wilhelmstrasse 36
72074 Tuebingen
Germany

http://www.maartenbuis.nl
--------------------------


--- On Tue, 20/10/09, Martin Weiss wrote:
> " Can I ask, what does the code "local m= r(max)" and
> "forvalues j = 1/`m' "
> mean in that command?"
> 
> 
> 
> Yes, you can. The first one stores the maximum calculated
> by the line -sum _mj, meanonly- in a -local- macro so as
> to make it accessible after other commands have
> overwritten the returned values of the -summarize- command.
> The second one lets Stata loop from a fixed starting point
> of "1" to this very maximum stored by the -local- in "m",
> in increments of 1...

That is correct. To expand a bit on that in the context of 
-ice-: _mj identifies each imputed dataset, where _mj=0 
represents the original dataset with missing values, _mj=1
the first imputed dataset, _mj=2 the second, etc. So, the 
maximum of _mj represents the total number of imputed 
datasets. In the loop I loop over the imputed datasets,
calculate the regression in each of them, and add up the 
log(r2). After the loop I divide by the number of imputed
datasets (still stored in the local `m') and exponentiate
it again.

-- Maarten


      

*
*   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