Bookmark and Share

Notice: On March 31, it was announced that Statalist is moving from an email list to a forum. The old list will shut down on April 23, and its replacement, is already up and running.

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

Re: st: New command: stpm2illd - flexible parametric illness death models

From   Adam Olszewski <>
Subject   Re: st: New command: stpm2illd - flexible parametric illness death models
Date   Fri, 7 Sep 2012 14:59:57 -0400

This is wonderful! I have a question though - is this the general
direction that the -stpm2- team is taking with regards to implementing
the "competing risk" framework? In the book by Royston/Lambert
there was a suggestion that a subhazard/CIF-based model, perhaps
analogous to Fine-Gray model might be "a subject of research". Is that
still considered?
The illness-death model seems to be rich in possibilities though
CIF-based models are now widespread in applied literature and I was
hoping to see the related FPM extension some time in the future..
Best regards,
Adam Olszewski

On Fri, Sep 7, 2012 at 3:35 AM, Hinchliffe, Sally R.
<> wrote:
> Thanks to Kit Baum a new command, stpm2illd, is now available to download from the SSC.
> It is usual in time-to-event data to have more than one event of interest, for example time to death from different causes. Competing risks models can be applied in these situations where events are considered as mutually exclusive absorbing states. That is we have some initial state, for example alive with a diagnosis of cancer, and we are interested in several different endpoints all of which are final. However, usually a disease process will consist of one or more intermediary events that may alter the progression to an endpoint. These events are neither initial states or absorbing states. Here we consider one of the simplest multi-state models known as an illness-death model.
> stpm2illd is a postestimation command used after fitting a flexible parametric survival model using stpm2 to estimate the probability of being in each of four states. There is also the option to generate con dence intervals and transition hazard functions.
> Kind Regards
> Sally Hinchliffe
> *
> *   For searches and help try:
> *
> *
> *

*   For searches and help try:

© Copyright 1996–2016 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   Site index