Re: st: Number of Obs with svy , suppop()

[Phil Schumm <pschumm@uchicago.edu>]

On Mar 18, 2010, at 6:20 PM, Michael Mitchell wrote:
> Here is the tabulation of race and sex by race.

<snip>

> . tab sex race, missing
>
>    1=male, |          1=white, 2=black, 3=other
>   2=female |     White      Black      Other          . |     Total
> -----------+--------------------------------------------+----------
>       male |     1,676        193         35         34 |     1,938
>     female |     1,824        238         34         37 |     2,133
> -----------+--------------------------------------------+----------
>      Total |     3,500        431         69         71 |     4,071

<snip>

> But now I want to analyze just the sub-population of males (sex==1)  
> and it shows that the number of obs is now 4037 (see below). How can  
> the number of observations increase when adding a -subpop()-  
> option?  There are suddenly 37 extra observations. Note this  
> corresponds to the number of females with a missing race.
>
> . svy , subpop(if sex==1): tab race, count format(%13.2fc)
> (running tabulate on estimation sample)
>
> Number of strata   =         1                  Number of obs       
> =      4037
> Number of PSUs     =      4037                  Population size    =  
> 7932333.9
>                                                 Subpop. no. of obs  
> =      1904
>                                                 Subpop. size       =  
> 3780355.3
>                                                 Design df           
> =      4036


This is as it should be, since information about race is not required  
on those observations outside of the subpopulation.  Remember,  
observations outside the subpopulation are relevant only insofar as  
they reflect the variability in the proportion(s) of sampled PSUs with  
at least one observation in the subpopulation.

In fact, at one point Stata did not behave properly in this regard;  
this was fixed in an update to Stata 10 on 02apr2008 (see -help  
whatsnew10- and search for "02apr2008").


-- Phil

*
*   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/