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.

# st: Discrete time hazard model - Interval width

 From "Stephen P. Jenkins" To Subject st: Discrete time hazard model - Interval width Date Wed, 19 May 2010 09:30:24 +0100

```------------------------------

Date: Tue, 18 May 2010 14:51:22 +0200
From: gideluca@unical.it
Subject: st: Discrete time hazard model - Interval width

Dear Stata Users,

We are assessing the transition from university to the first real
job,
taking into account individual characteristics and the family
background. We use survey data including graduates from the
summer
sessions in the year 2004 who were interviewed at one, three and
five
years from graduation.  In order to carry out the analysis we
estimate
a discrete time hazard model. We have organised the data in such
a way
that for each student there are as many data rows as there are
time
intervals over which the student is at risk of finding the first
job.
Is it correct to use intervals of different width (0-1; 1-3; 3-5)

given that we do not have yearly interviews?

+-----------------------+
-----------------------
279.	182          2      0
280.	182          2      1
281.	183          3      0
282.	183          3      0
283.	183          3      1
-----------------------
284.	184          1      1
285.	185          3      0
286.	185          3      0
287.	185          3      1
288.	186          3      0
-----------------------
289.	186          3      0
290.	186          3      0
+-----------------------+

Thank you very much.
Giuliana
========================

Thanks to Steve Samuels for the mention of my Survival Analysis
website materials in connection with this topic. FYI The webpages
now have a new 'permanent' URL, as given in my signature. The URL
Steve mentioned will continue to work, but might not in future.

Giuliana: if the intervals of equal width, there is no problem.
If you have unequal-width intervals, then ideally you should take
account of this. It may be complicated to do so. However, do have
a look at -intcens- on SSC for some models that do allow for
unequal-width intervals.

Stephen
-------------------------------------
Professor Stephen P. Jenkins <stephenj@essex.ac.uk>
Institute for Social and Economic Research (ISER)
University of Essex, Colchester CO4 3SQ, UK
Tel: +44(0)1206 873374. Fax: +44(0)1206 873151
http://www.iser.essex.ac.uk
Survival Analysis using Stata:
http://www.iser.essex.ac.uk/survival-analysis