Bookmark and Share

Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.


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

Re: st: subpop() and over() with survey mean estimation using SDR weights


From   jpitblado@stata.com (Jeff Pitblado, StataCorp LP)
To   statalist@hsphsun2.harvard.edu
Subject   Re: st: subpop() and over() with survey mean estimation using SDR weights
Date   Tue, 31 Jan 2012 09:52:55 -0600

Sam Schulhofer-Wohl <sschulh1.work@gmail.com> had a follow-up question:

> Is -svy bootstrap- with -bsn(4)- equivalent to SDR weights in all cases?
> For example, if I am using the IPUMS version of the Current Population
> Survey with
> 
> svyset [iw=wtsupp], sdrweight(repwtp1-repwtp160) vce(sdr)
> 
> can I instead do
> 
> svyset [iw=wtsupp], bsrweight(repwtp1-repwtp160) bsn(4) vce(bootstrap)
> 
> (Comparing the formulas on pages 186 and 190 of [SVY] suggests that the two
> settings are indeed always equivalent, but official confirmation would be
> nice.)

While the replicate weights are different between the two methods, the formula
used to compute the VCE from the replicated parameter estimates is equivalent
between the SDR method and the bootstrap with a multiplier of 4.

--Jeff
jpitblado@stata.com
*
*   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 1996–2018 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   Site index