Prev: wiki page: update SASv9.cfg for Sudaan
Next: advice about SAS coding level displayed on the video
From: Pakcha Sharma on 4 Mar 2010 20:43
Hi all,

I am trying to do quantile regression with data from a survey. Each record
has sampling weight to represent the whole population. I am just wondering
if PROC QUANTREG can be used for the survey data. Does it compute the
correct standard error for the estimates if I specify sampling weights
through the WEIGHT statement ? Or is there a problem like in PROC
LOGISTIC, which does not compute the proper variance when using with the
survey data and specifying sampling weights through the WEIGHT statement,
and we need to use PROC SURVEYLOGISTIC instead of PROC LOGISTIC.

Is there any other PROC that can be used for quantile regression for
survey data ? Any help would be much appreciated.

Thanks.

Packha.
 | 
Pages: 1
Prev: wiki page: update SASv9.cfg for Sudaan
Next: advice about SAS coding level displayed on the video