Statalist


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

st: analysing a case-cohort using Stcascoh and Stselpre


From   <A.A.M.Vaarhorst@lumc.nl>
To   <statalist@hsphsun2.harvard.edu>
Subject   st: analysing a case-cohort using Stcascoh and Stselpre
Date   Mon, 8 Feb 2010 10:07:31 +0100

Dear Stata users,

I'm trying to analyse a case-cohort dataset, using Stata/SE 11.0 for
windows. For this I have downloaded the Stcascoh module version 1.2.1
for preparing the dataset and Stselpre (version 1.1.0) for analysing the
dataset.

I splitted my dataset into the subcohort and additional cases (they were
already sampled). Then both datasets were prepared for survival analysis
using "stset lftcens, failure(failurevar==1) time0(timevar) id (IDvar)".
Next I used "stcascoh, alpha(0.99999999999)" for the subcohort and
"stcascoh, alpha(0)" for the remaining cases. I saved both files and
appended them. Next I addapted the Barlow weights using "replace
_wBarlow=ln(number of subjects/number of samples) if _wBarlow>0"

However when I'm using stselpre for analysing, I get the following error
message: "Data were corrupted from previous stcascoh something that
should be true of your data is not r(459)."

Thanks for your consideration,
 
Anika Vaarhorst
 


*
*   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