Re: st: Two baselines in stpiece

[Maarten Buis <maartenlbuis@gmail.com>]

On Wed, Oct 5, 2011 at 11:34 AM, Marika Jalovaara wrote:
> I'm using stpiece (or streg) to fit piecewise constant models. I'm wondering
> whether it is possible to have separate baseline risks for two groups of
> observations (say, dummy Group).
>
> Fitting separate models for the two groups doesn't work because I should
> perform tests of statistical significance for interactions between Group and
> other covariates.

-stpiece- is user written. The Statalist FAQ asks you to specify where
you got user written software from. The reason for that is that there
are often multiple versions of the same user written program floating
around cyber space, and we obviously cannot answer questions about
unknown pieces of software. Typically, we will guess which version you
are using, but often that just leads to more confusion when we guess
wrong. So for all involved it is better to just read the FAQ and
follow the advise given in it, a link can be found at the bottom of
every post on statalist (including this one). Below I will assume you
have downloaded -stpiece- from SSC by typing in Stata -ssc install
stpiece-.

With the -tv()- option you can enter interaction terms between the
baseline hazard and some variable. This is typically interpreted as
allowing the effect of that variable to change over time, but since
interaction terms are symetric you can also interpret this as allowing
the baseline hazard to be different for different values of that
variable.

Hope this helps,
Maarten

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


http://www.maartenbuis.nl
--------------------------
*
*   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/