Statalist


[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]

RE: st: treatment of missing values in a matrix dissimilarity score


From   "Elkins, Zachary S" <zelkins@austin.utexas.edu>
To   "statalist@hsphsun2.harvard.edu" <statalist@hsphsun2.harvard.edu>
Subject   RE: st: treatment of missing values in a matrix dissimilarity score
Date   Mon, 15 Sep 2008 17:34:13 -0500

Thanks to Nick, Eva, and Jay for very helpful responses to the below.

Best,
Zach
________________________________________
From: owner-statalist@hsphsun2.harvard.edu [owner-statalist@hsphsun2.harvard.edu] On Behalf Of Eva Poen [eva.poen@gmail.com]
Sent: Monday, September 15, 2008 2:49 PM
To: statalist@hsphsun2.harvard.edu
Subject: Re: st: treatment of missing values in a matrix dissimilarity score

Zach,

Stata seems to do listwise deletion, which appears fair in this
situation; it is not clear to me how comparable similarity measures
would be between observations when they are calculated based on
different sets of variables.

You want to calculate similarities only across non-missing elements. I
don't think there is an easy way to do this. One approach is to enlist
the help of -mvpatterns- which you can locate using -findit-.
-mvpatterns x1 x2 x3 x4- will tell you which patterns of missing
values exist in your data. You can then run the -matrix dissimilarity-
command separately for each pattern:

matrix dissimilarity m1=x1 x3 if x2 >=. & x4 >=., match proportion

for example, for all those observations that have x1 and x3
non-missing but x2 and x4 missing.

Eva


2008/9/15 Elkins, Zachary S <zelkins@austin.utexas.edu>:
> I'd like to calculate the matches between observations across a set of binary variables.  I suspect that there are multiple ways to do this.  I've specified:
>
> matrix dissimilarity m=x1 x2 x3 x4, match proportion
>
> However, some values in x1-x4 are missing.  Based on the results, it appears that Stata treats missing values as if they were 1 and I don't see how to modify that.  I'd like to calculate to calculate similarities across only non-missing elements (the number of which will be different for each pair, of course).
>
> Thanks for any help.
>
> Zach Elkins
>
>
> ______________________________
> Zachary Elkins
> Assistant Professor
> Department of Government
> University of Texas at Austin
> 1 University Station A1800
> Austin, TX  78712-0119
>
> p: (512) 232-7250
> f: (512) 471-1061
>
> *
> *   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/
>
*
*   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/

*
*   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