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, statalist.org is already up and running.


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

st: Han and Hausman (1990) Nonparametric Baseline Hazard


From   "Stephen P. Jenkins" <stephenj@essex.ac.uk>
To   <statalist@hsphsun2.harvard.edu>
Subject   st: Han and Hausman (1990) Nonparametric Baseline Hazard
Date   Wed, 8 Dec 2010 09:55:31 -0000

===============================
Date: Tue, 7 Dec 2010 08:00:03 -0500
On Dec 6, 2010, at 8:56 PM, Irwin T.S. Wang wrote:

Dear All,

Has anyone tried estimating the nonparametric baseline hazard
discussed in Han and Hausman (1990) in Stata? I browsed through the
archive but did not find relevant discussion. Any thoughts will be
much appreciated.

Han, A. and J.A. Hausman. 1990. Flexible Parametric Estimation of
Duration and Competing Risk Models. Journal of Applied Econometrics
5(1):1-28.

Thanks,

T.S. Wang
================================

My understanding is that H & H provided a way of estimating the
discrete time proportional hazard regression model using an 'ordered
logit' type regression applied to reorganised data. They also extend
that approach to fit a model with Gamma distributed frailty. 

However you can estimate the same model in other ways. Without
frailty, the model can be estimated using -cloglog-, and the Gamma
frailty version of the model can be fitted using -pgmhaz8- (on SSC).
See the 'unobserved heterogeneity' material in the MS and Lessons at
the URL below.

I conjecture that the H&H approach is not commonly used is because
they never explicitly provide the expression for the likelihood
contribution for right-censored spells in their article.  So, work by
e.g. Meyer (Econometrica 1990) has become more commonly followed.  See
the references cited in the previous paragraph.

My discussion in the previous paragraphs refers to the single
destination case -- not competing risks. For some discussion of
competing risk models in the discrete time (grouped survival time)
case, see the materials cited in para 2

Stephen
-------------------------------------------------------------
Professor Stephen P. Jenkins <stephenj@essex.ac.uk>
Institute for Social and Economic Research
University of Essex, Colchester CO4 3SQ, U.K.
Tel: +44 1206 873374.  Fax: +44 1206 873151.
http://www.iser.essex.ac.uk ; 
Survival Analysis using Stata:
http://www.iser.essex.ac.uk/survival-analysis
Downloadable papers and software: http://ideas.repec.org/e/pje7.html 



*
*   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/


© Copyright 1996–2014 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   Site index