s-news
[Top] [All Lists]

Re: split-population model (cure model)

To: Shige Song <sgsong@ucla.edu>
Subject: Re: split-population model (cure model)
From: ripley@stats.ox.ac.uk
Date: Thu, 30 May 2002 07:26:24 +0100 (BST)
Cc: <s-news@lists.biostat.wustl.edu>
In-reply-to: <20020529210202.0120.SGSONG@ucla.edu>
On Wed, 29 May 2002, Shige Song wrote:

> Dear All,
>
> Has anyone implemented S/R code for what economists called
> "split-population model" and what biostatisticians called "cure model"?
> Here are some references:
> ----------------------------------------------------------------------------------------------------
> Maller, R.A. and Zhou, X. Survival Analysis with Long Term Survivors,
>         Wiley series in probability and statistics, John Wiley,
>         Chichester.
>
> Schmidt, P. and Witte, A. (1989), "Predicting criminal recidivism
>         using 'split population' survival time models",
>         Journal of Econometrics 40: 141-159.
> ----------------------------------------------------------------------------------------------------
> Thanks!

survReg allows user-specified distributions which should allow you to fit
some accelerated-life distributions with mass at infinity.  Otherwise,
just write down a log-likelihood and maximize it, which would only need a
few lines of S code.

-- 
Brian D. Ripley,                  ripley@stats.ox.ac.uk
Professor of Applied Statistics,  http://www.stats.ox.ac.uk/~ripley/
University of Oxford,             Tel:  +44 1865 272861 (self)
1 South Parks Road,                     +44 1865 272860 (secr)
Oxford OX1 3TG, UK                Fax:  +44 1865 272595


<Prev in Thread] Current Thread [Next in Thread>