--- Moleps wrote:
> 1) Reading the medical literature most retrospective survival
> analysis is done with Kaplan Meier curves. Is it not more appropriate
> to use Cox graphs where other covariates have been adjusted for?
> 2) Some report both univariate and then multivariate data on their
> variables. What is the correct thing to do?
Depends on the aim. A Kaplan Meier curve is an excelent way of
describing the data. Such a describtion is crucial, as any modeling
later on (e.g. Cox regression) is only a manipulation of this raw
material. Also controling for a covariate is not necesarily a good
thing: a very common mistake is that people don't distinguish between
intervening and confounding variables.
-- Maarten
-----------------------------------------
Maarten L. Buis
Department of Social Research Methodology
Vrije Universiteit Amsterdam
Boelelaan 1081
1081 HV Amsterdam
The Netherlands
visiting address:
Buitenveldertselaan 3 (Metropolitan), room N515
+31 20 5986715
http://home.fsw.vu.nl/m.buis/
-----------------------------------------
*
* 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/
