st: RE: predicting survival with a semiparameteric model

["Martin Weiss" <martin.weiss1@gmx.de>]

<>

So your problem is pretty much the inverse of
http://www.stata.com/statalist/archive/2009-11/msg00132.html ?


HTH
Martin


-----Original Message-----
From: owner-statalist@hsphsun2.harvard.edu
[mailto:owner-statalist@hsphsun2.harvard.edu] On Behalf Of Feiveson, Alan H.
(JSC-SK311)
Sent: Dienstag, 24. August 2010 19:24
To: statalist@hsphsun2.harvard.edu
Subject: st: predicting survival with a semiparameteric model

Hi - I am estimating  a semi-parametric survival model using -stcox-. In the
process, I can get estimates of the cumulated baseline hazard (say H0(t))
evaluated at values of time, t, in my data. Then I can use this to predict
the survival at time t for given values of the explanatory variables, say x,
using


S(t) = exp(-exp(xb)H0(t))

where xb is the linear predictor.

However, I don't see how to get a standard error of this prediction. For
example, -nlcom- only considers the estimation error in xb and treats H0(t)
as a known constant.

So is there a way to incorporate the uncertainty in estimating H0(t) into
the standard error of S(t)?

Of course, I can always get a standard error of S(t) with a fully parametric
model using -streg-, but if possible, I'd like to use a PH model without
having to specify a distribution.

Thanks

Al Feiveson

*
*   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/

*
*   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/