Bookmark and Share

Notice: On March 31, it was announced that Statalist is moving from an email list to a forum. The old list will shut down on April 23, and its replacement, statalist.org is already up and running.


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

RE: st: create new variable from weighted counts?


From   "Rossen, Lauren M. (CDC/OSELS/NCHS)" <vyz5@cdc.gov>
To   "statalist@hsphsun2.harvard.edu" <statalist@hsphsun2.harvard.edu>
Subject   RE: st: create new variable from weighted counts?
Date   Wed, 17 Apr 2013 13:12:46 +0000

Thank you so much, Nick, for pointing me in the right direction.
There will be plenty of jumping up and down in appreciation.

Lauren

------------------------------

Date: Tue, 16 Apr 2013 19:09:30 +0100
From: Nick Cox <njcoxstata@gmail.com>
Subject: Re: st: create new variable from weighted counts?

You could always go something like

bysort county: egen dths_white=total(wtvar * (race==1))

In a strong sense this is documented, as the -egen- -total()- function
can take an arbitrary expression as argument. However, quite how
general this is may deserve more shouting and jumping up and down than
it gets.

Nick
njcoxstata@gmail.com


On 16 April 2013 18:57, Rossen, Lauren M. (CDC/OSELS/NCHS) <vyz5@cdc.gov> wrote:
> Hello Stata-listers,
>
> I have a data set on all infant deaths in the US, and I am
> trying to create county-level summaries of several variables.
> For example, counts of deaths by county for white infants,
> black infants, etc.  Normally, this would be straightforward
> to do with something like:
>
> bysort county: egen dths_white=total(race==1)
> bysort county: egen dths_black=total(race==2)
>
> However, the data are weighted because a small # of
> deaths are not included in the file, so there are something
> like importance weights to make sure that the totals sum
> up to the actual total # of reported deaths in the US.
> I say importance weights because there is no sampling,
> and the weights are not integers, they range from 1 to 1.2.
>
> My question is: is there a way to generate new variables
> representing county-level totals incorporating the
> weights? I apologize for the rudimentary question,
> but I have tried searching through the archives and
> documentation and had no luck finding a solution.
*
*   For searches and help try:
*   http://www.stata.com/help.cgi?search
*   http://www.stata.com/support/faqs/resources/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/faqs/resources/statalist-faq/
*   http://www.ats.ucla.edu/stat/stata/


© Copyright 1996–2014 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   Site index