re: st: Individual risks scores using competing risks

["Ariel Linden, DrPH" <ariel.linden@gmail.com>]

Have you looked at - stcompet -  (http://fmwww.bc.edu/RePEc/bocode/s/), or
in Stata v13 (perhaps earlier versions as well) using "predict , basecif"
after -stcrreg- ?


Date: Wed, 11 Sep 2013 15:41:58 +0100
From: Lucy Riley <lucy.riley89@googlemail.com>
Subject: st: Individual risks scores using competing risks

Hello,

I am currently trying to build a model using competing risks which will 
give individual risk scores to patients.

I am trying to use the Fine and Gray approach to build the model, using 
the Stata command STCRREG I am able to get the sub-distribution hazard 
ratios and beta coefficients for the score but I'm having trouble 
converting these into individual scores.

As far as I can see the best method is to calculate an individuals 
cumulative incidence function (CIF) which can be done using the formula;

CIF(t|X) = 1 - exp( - exp(X * beta^t. H0(t) ) where H0(t) is the 
cumulative sub-distribution hazard for the event at time t.

My main problem is that I haven't come across any methods for finding 
H0(t).

If anyone knows a way to calculate this value or has any references that 
might be useful, please would you send them on to me?

Thank you!!
Lucy

*
*   For searches and help try:
*   http://www.stata.com/help.cgi?search
*   http://www.stata.com/support/faqs/resources/statalist-faq/
*   http://www.ats.ucla.edu/stat/stata/