[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]

Re: st: stcurve and multiple strata

From   Maarten buis <>
Subject   Re: st: stcurve and multiple strata
Date   Thu, 11 Sep 2008 13:06:24 +0100 (BST)

--- moleps islon <> wrote:
> Right now my cox model looks like this:
> xi:stcox a b d i.c, basesurv(e)
> I need to make survival graphs adjusted for the other variables for
> the individual i.c categories. I tried
> stcurve, survival at1(_Ic_2=1) at2(_Ic_3=1) etc, etc but somehow I 
> can't find my first expansion term anywhere. Ideas?

That will not work: -xi- creates a set of dummies, -stcurve- set
variables not mentioned in -at#()- at the mean, so just saying _Ic_2=1
will not properly identify the second group, as _Ic_3 is set at the
mean, but should be set at 0. The reference category is identified by
both variables set equal to 0. 

*----------- begin example ------------
sysuse cancer, clear
stset studytim, failure(died)
xi: stcox i.drug age, basesurv(e)
stcurve, surv ///
     at1(_Idrug_2=0 _Idrug_3=0) ///
     at2(_Idrug_2=1 _Idrug_3=0) ///
     at3(_Idrug_2=0 _Idrug_3=1) 	
*----------- end example --------------
(For more on how to use examples I sent to the Statalist, see )

Also see:

-- Maarten

Maarten L. Buis
Department of Social Research Methodology
Vrije Universiteit Amsterdam
Boelelaan 1081
1081 HV Amsterdam
The Netherlands

visiting address:
Buitenveldertselaan 3 (Metropolitan), room N515

+31 20 5986715

*   For searches and help try:

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