[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]

Re: st: stset command

From   Maarten buis <>
Subject   Re: st: stset command
Date   Tue, 22 Apr 2008 17:34:15 +0100 (BST)

--- "Martiarena, Griselda" <> wrote:
> Why I do not have to stset the data for a estimation when I use the
> command cloglog?

-stset- prepares your data for a survival analysis, it collects
information on the durations, which observations are censored, etc, and
makes this information easily accessible for programs especially writen
for survival analysis. This is convenient because almost all survival
analysis commands need that information, so during this your analysis
you only have to specify that once during -stset- and afterwards you
are always ok. These survival analysis commands can be recognized
because they are often preceded by st, e.g. -stcox-, -streg-, -sts-,
etc. -cloglog- can be used for survival analysis, but was not
specifically designed for that. You can also see it as a model for a
dichotomous dependent variable with a rather weird non-symetric link
function. So, as it was not designed for survival analysis, it won't
use the information collected by -stset-, and -stset-ing your data will
make no difference for -cloglog-. 

Hope this helps,

Maarten L. Buis
Department of Social Research Methodology
Vrije Universiteit Amsterdam
Boelelaan 1081
1081 HV Amsterdam
The Netherlands

visiting address:
Buitenveldertselaan 3 (Metropolitan), room Z434

+31 20 5986715

Sent from Yahoo! Mail.
A Smarter Email
*   For searches and help try:

© Copyright 1996–2017 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index