Stata The Stata listserver
[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]

Re: st: competing risk models


From   Enzo Coviello <enzo.coviello@tin.it>
To   statalist@hsphsun2.harvard.edu
Subject   Re: st: competing risk models
Date   Sat, 15 May 2004 10:42:04 +0200

At 16.50 14/05/04 -0400, you wrote:
Hi,

I am trying to run a competing risks event history model using stata. Once firms enter the sample, they are at risk for three possible outcomes (technology adoption). I want to see if a list of various independent variables affect the rate for these outcomes in different ways, maybe in the same direction, but differential impact. So in the output I should get a set of coefficients (which I think decomposes to the probability of the destination state * the overall rate) for each potential outcome. In TDA, the command is rate and then specify the outcome and independent variables for each potential outcome (in my case 3 outcomes). I would appreciate it if someone could tell me how to do this with stcox?


I ignore TDA, but in epidemiology a quite simple approach is described in:

Lunn, M and D. McNeil. 1995 Applying Cox Regression to Competing Risks. Biometrics 51: 524-532.

The Lunn's method needs an augmented (expanded) data set. When data are suitably adapted, you can estimate one Cox model for all competing events and independent variables at once.

If you are interested I can send a do file where Lunn's example is replicated.
It is not so much, but I could be useful.


Enzo






Thanks!

WS

*
*   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/



© Copyright 1996–2014 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index