Statalist


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

Re: st: table & chi-square from multiply imputed survey data (-ice-, -mim-) [repost]


From   Maarten buis <maartenbuis@yahoo.co.uk>
To   statalist@hsphsun2.harvard.edu
Subject   Re: st: table & chi-square from multiply imputed survey data (-ice-, -mim-) [repost]
Date   Wed, 4 Feb 2009 21:50:29 +0000 (GMT)

--- On Wed, 4/2/09, Michael I. Lichter wrote:
> I want to know how to generate a survey-adjusted chi-square
> like that available from -svy: tab- using data multiply
> imputed using -ice- (net sj 8-1 st0139).

Even ignoring the survey adjustments this is a surprisingly 
difficult task. The reason is as follows: Multiple Imputation
is designed for making inference on coefficients separately, 
not for making inference on multiple coefficients 
simultaneously. The chi-square test is such a simultaneous 
test: it tests whether all odds ratios that define the 
association within the table are simultaneously equal to
one another. However, stuff has been done in this area, and 
some of it has been implemented in Stata as was discussed by 
Rose Medeiros at the 2008 Fall North American Stata Users' 
meeting:
http://ideas.repec.org/p/boc/fsug08/11.html
 
> I'd also be interested in suggestions about how to
> tabulate these data. (E.g., would anybody complain if I
> computed a mean imputed value for each variable for each
> case, rounded them off, and reported that?)

I wouldn't complain.
 
<snip> 
> As far as I can tell, -mim- doesn't support -tab- or
> -svy: tab-, and -svy: tab- itself doesn't support prefix
> commands. I can try predicting A from B using -mlogit-, but
> that seems silly. 

Actually, because this is such a surprisingly complicated 
problem you'll probably end up doing something like that.
Alternatively, if that chi square statistic isn't crucial
for your paper, I would probably just not bother with trying
to compute such a statistic at all, and just report a table 
with the averaged counts.

> I can manually do a tabulation for each
> imputation and, I guess, average the chi-square statistics,
> and, I dunno, subtract one degree of freedom, perhaps? 

This will not give you the correct coverage, as Rose discussed
in her presentation.

Hope this helps,
Maarten

-----------------------------------------
Maarten L. Buis
Department of Social Research Methodology
Vrije Universiteit Amsterdam
Boelelaan 1081
1081 HV Amsterdam
The Netherlands

visiting address:
Buitenveldertselaan 3 (Metropolitan), room N515

+31 20 5986715

http://home.fsw.vu.nl/m.buis/
-----------------------------------------





      

*
*   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