Stata does not have survey versions of survival models. SUDAAN version 8
does. Or in Stata you can specify PSU as the cluster, along with weights
and ignore the stratification. This will yield conservative results with
larger than necessary variances. Which might be sufficient, depending on
the amount of stratification in the data.
Bryan Sayer
Statistician, SSS Inc.
-----Original Message-----
From: Sarah A. Mustillo
To: [email protected]
Sent: 11/25/02 11:33 AM
Subject: st: survival analysis with strata and PSU
Hi -
I would like to run a cox model on survey data that has PSU, strata and
pweights. I need to model time to death (continuous) using depressive
symptoms as an independent variable. -stcox- will allow the weights,
but
not psu or strata. There is no cox command in the -svy- suite. Can
the
cox model be adjusted for sampling design, or is there an alternative
analytic approach?
Thanks!
Sarah
Sarah A. Mustillo, Ph.D
Center for Developmental Epidemiology
Department of Psychiatry and Behavioral Sciences
Duke University School of Medicine
Box 3454
Durham NC 27710
919 687-4686 x234
*
* 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/
*
* 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/
