[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

Re: st: SE's on survival estimates from parametric models

From   Maarten buis <>
Subject   Re: st: SE's on survival estimates from parametric models
Date   Fri, 24 Apr 2009 16:57:30 +0000 (GMT)

--- On Fri, 24/4/09, Mark Hebblewhite wrote:
> My question is how to calculate the SE/95% CI for the
> predicted survival estimate from a parametric model in
> STATA. I know STATA is doing this with stcurve commands, but
> I haven't been able to figure out how to solve for a
> point estimate of survival and its SE for time t.  

In the example below I predict the hazard rate and it's CI at 
t=15. The se can also be predicted by specifying the -se()-
option in the -predictnl- command.

*--------------- begin example -----------------
sysuse cancer, clear
stset studytime, failure(died)
xi: streg i.drug age, dist(weibull)

local t = 15
local p "exp([ln_p]_b[_cons])"
local h0 "`p' *`t' ^(`p' -1)"

predictnl hazard = `h0' * exp(xb()), ci(lb ub)

twoway rarea lb ub age, sort || ///
       line hazard age, sort by(drug)
---------------- end example -------------------

Hope this helps,

Maarten L. Buis
Institut fuer Soziologie
Universitaet Tuebingen
Wilhelmstrasse 36
72074 Tuebingen


*   For searches and help try:

© Copyright 1996–2017 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index