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

st: RE: Breslow baseline hazard estimator of Cox.

From   "Stephen P Jenkins" <>
To   <>
Subject   st: RE: Breslow baseline hazard estimator of Cox.
Date   Tue, 13 Apr 2004 09:35:48 +0100

> -----Original Message-----
> From: 
> [] On Behalf Of 
> gong shizhuo
> Sent: 13 April 2004 03:09
> To:
> Subject: st: Breslow baseline hazard estimator of Cox.
> Dear Stata Users:
> Does anyone know how to estimate the Breslow baseline hazard 
> estimators of 
> Cox model using Stata? Or SAS, R?

In Stata, you can estimate a Cox proportional hazard model for
continuous survival time data with -stcox- using any of 4 methods of
handling ties (breslow, efron, exactm, exactp). Using the appropriate
options, you can have -stcox- calculate the baseline cumulative hazard
function, the baseline survivor function, and the baseline hazard
contribution.  Note that the last of these refers to the hazard
/contribution/. You can't estimate a hazard function per se.  [Recall
that the continuous time hazard rate h(t) is equal to [-dS(t)/dt]/S(t)
for survivor function S(t), or the derivative of the cumulative hazard
function H(t). But the estimates of S(t) and H(t) are step functions of
observed survival times, and so slopes -- and hence hazards -- are not
well-defined.]  You can calculate a /smoothed/ hazard function, however.
See also -stcurve-.

For further details, have a look at Manual [ST], and Cleves et al. /An
Introduction to Survival Analysis using Stata/.

Professor Stephen P. Jenkins <>
Institute for Social and Economic Research
University of Essex, Colchester CO4 3SQ, U.K.
Tel: +44 1206 873374.  Fax: +44 1206 873151.   

*   For searches and help try:

© Copyright 1996–2015 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index