Statalist


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

Re: st: Survey variance estimates - large software differences


From   sjsamuels@gmail.com
To   statalist@hsphsun2.harvard.edu
Subject   Re: st: Survey variance estimates - large software differences
Date   Tue, 30 Jun 2009 13:52:12 -0400

==
Arnold,

Since you do not show the Stata -svyset- output, nor the Stata
estimation commands and output, nor the equivalent SAS commands and
output.  Please do so.  If there are so many variables as to make
scanning the output difficult, please run the commands with as few
variables as needed to demonstrate the issue. Best would be to use one
of the downloadable example data sets from the Stata survey manual.

-Steve


On Tue, Jun 30, 2009 at 12:41 PM, Levinson,
Arnold<Arnold.Levinson@ucdenver.edu> wrote:
> Survey analysis experts:
> I have data from a stratified two-stage school survey. The first stage sampled schools within strata, the second sampled classrooms within selected schools.
>
> When estimating variables of interest at the school level, I get hugely different variance estimates running Stata vs. SAS or SUDAAN. Stata's estimates are generally a lot smaller than SAS's or SUDAAN's, and the latter to are similar or identical to each other.
>
> My Stata svyset statement is:
>
> svyset skulid [pw=skulwt], strata(strat) fpc(fpc) || classid
>
> My SAS/SUDAAN design statements are the equivalent.
>
Steven Samuels
sjsamuels@gmail.com
18 Cantine's Island
Saugerties NY 12477
USA
845-246-0774

*
*   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