Re: st: Estimating variable median from svy data

[Steven Samuels <ssamuels@albany.edu>]

Redundant Line
On Jun 14, 2007, at 8:27 AM, Ashwin Ananthakrishnan wrote:
> Hi,
>
> I am a current user of Stata 9.0.
>
> I'm working on analysis of a complex stratified survey
> dataset. I know commands such as the 'svy: mean
> (varname)' command estimate the mean for a particular
> variable. Can someone please tell me if there is a
> corresponding command to estimate the median of a
> variable that is not normally distributed?

-summarize- and -pctile- will take weights.  Unfortunately there is  
no easy way to obtain a CI for the percentiles.  Request to Stata:  
Please implement a method such as that in Sarndal,Swensson, & Wretman  
(1992) Model Assisted Survey Sampling, Springer, pp 197-206.

 -Steve-


. webuse nhanes2
. svydes

Survey: Describing stage 1 sampling units

      pweight: finalwgt
          VCE: linearized
     Strata 1: strata
         SU 1: psu
        FPC 1: <zero>
[output skipped]

. sum height [weight=finalwgt], det
(analytic weights assumed)
[output skipped]
*
*   For searches and help try:
*   http://www.stata.com/support/faqs/res/findit.html
*   http://www.stata.com/support/statalist/faq
*   http://www.ats.ucla.edu/stat/stata/