|
[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]
Re: st: Split Population Survival (Cure) Model with discrete timedata
From |
"E. Paul Wileyto" <[email protected]> |
To |
[email protected] |
Subject |
Re: st: Split Population Survival (Cure) Model with discrete timedata |
Date |
Thu, 20 Dec 2007 12:07:38 -0500 |
When you say discrete time, do you mean that you have (long) time
intervals with a beginning and end, and the event happens some time in
between? If so, we can write something simple for that using ml.
Paul
Javier Ses� wrote:
Thanks Paul for your suggestions.
I couldn't have access to this article, although my guess is that
these routines are for continuous time data (I searched for them from
the Stata help).
In my case, I have discrete time data.
Any suggestions to solve it with this kind of data?
Thank you in advance
At 13:12 19/12/2007, you wrote:
Look in The Stata Journal (2007), Vol. 7, Number 3, pp. 351-375 for
an article on cure models by Paul Lambert.
You can retrieve Lambert's set of routines by searching for -strsmix-
from Stata Help. It's a very flexible set of parametric cure models.
EPW
Javier Sesé wrote:
Dear all,
I am trying to estimate a Split Population Survival Model (also called
Cure Model) with discrete time duration data in Stata 9.0. This model
relaxes the assumption that all subjects will eventually experience
the event of interest by supposing that a proportion of the population
never fail.
The -spsurv- Stata module developed by Stephen P. Jenkins estimates
this model, but it assumes that the cure probability (the probability
of a subject never failing) is common to all individuals. The code can
be found at:
http://fmwww.bc.edu/repec/bocode/s/spsur_ll.ado
http://fmwww.bc.edu/repec/bocode/s/spsurv.ado
However, I am interested in running a Split Population Survival Model
that allows for differences between individuals in this probability,
for instance, by using a logistic relationship between some
explanatory variables and the cure probability. But I have no clue
about how to do this in Stata, or how to modify the original code of
the -spsurv- module to incorporate this heterogeneity in the cure
probability.
If it helps, Forster, M. and Jones, A.M. (2001) ("The
role of tobacco taxes in starting and quitting smoking: duration
analysis of British data" Journal of the Royal Statistical Society A,
164(3), pp.517-547) have developed a Stata code to estimate this model
for continuous time data (the code can be found at
http://www.york.ac.uk/res/herc/software/Jrsscode.pdf).
Any help would be much appreciated.
Thank you in advance
*
* For searches and help try:
* http://www.stata.com/support/faqs/res/findit.html
* http://www.stata.com/support/statalist/faq
* http://www.ats.ucla.edu/stat/stata/
--
E. Paul Wileyto, Ph.D.
Assistant Professor of Biostatistics
Tobacco Use Research Center
School of Medicine, U. of Pennsylvania
3535 Market Street, Suite 4100
Philadelphia, PA 19104-3309
215-746-7147
Fax: 215-746-7140
[email protected]
http://mail.med.upenn.edu/~epw/
*
* For searches and help try:
* http://www.stata.com/support/faqs/res/findit.html
* http://www.stata.com/support/statalist/faq
* http://www.ats.ucla.edu/stat/stata/
*
* For searches and help try:
* http://www.stata.com/support/faqs/res/findit.html
* http://www.stata.com/support/statalist/faq
* http://www.ats.ucla.edu/stat/stata/
--
E. Paul Wileyto, Ph.D.
Assistant Professor of Biostatistics
Tobacco Use Research Center
School of Medicine, U. of Pennsylvania
3535 Market Street, Suite 4100
Philadelphia, PA 19104-3309
215-746-7147
Fax: 215-746-7140
[email protected]
http://mail.med.upenn.edu/~epw/
*
* For searches and help try:
* http://www.stata.com/support/faqs/res/findit.html
* http://www.stata.com/support/statalist/faq
* http://www.ats.ucla.edu/stat/stata/