Dear Stata users,
Thank you for the answers to my last question concerning stratified
estimation. I have another question about survival analysis. The data that
I use is interval censored.
The founding dates of firms are known to belong to one of the groups:
1) before 1970
2) 1970-1980
3) 1981-1985
4) 1986-1990
5) 1991
6) 1992
7) 1993
8) 1994
9) 1995
The exit dates are given precisely, by month/day/year starting
from 1995. This means the intervals are not disjoint. For example, a firm
with
founding date in group 3 and an exit year 1996 could have a survival time
in the interval [11,15] whereas a firm with founding date in group 4 and an
exit year 1999 could have survived for any time in the interval [9,13].
There appear to be ways to solve the problem expanding the dataset and
using binary regression methods. Moreover, I heard that SAS has some option
for interval censored data. Which would be the best way to solve this
problem with STATA? Maybe someone has already written a program?
Thank you in advance
Christian
*
* 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/
