At 09:54 AM 9/15/2003 -0500, you wrote:
Thank you very much, Ben. But I also noticed that Prof. Stephen Jenkins
mentioned in that subject, that we simply need to split episode and create
dummy variables, and then include them in the exponential model estimated
using -streg-. As I said in the previous thread that the episodes were
already split into annual spells in the data set, so I wonder if stset and
streg commands are enough to solve the problem.
yes -- stpiece is just a wrapper that a) splits the spells if necessary
(not in your case); b) creates the dummy variables for the time pieces; and
c) estimates an exponential model without a constant (streg ..., d(exp)
noconst). This can all be done manually of course, stpiece just cuts down
on the typing and potential for mistakes.
//Jesper
Thanks.
tapes
----- Original Message -----
From: "Jann, Ben" <[email protected]>
To: <[email protected]>
Sent: Friday, September 12, 2003 2:40 PM
Subject: st: RE: piece-wise constant exponential survival model
> Hi Tapes
>
> No, -streg ..., d(exp)- will estimate a "regular" exponential model.
> Check out -stpiece- by Jesper B. Sorensen.
>
> ben
*
* 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/
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
Jesper B. S�rensen
Richard S. Leghorn (1939) Associate Professor of Strategic Management
Sloan School of Management
Massachusetts Institute of Technology
E52-581
Cambridge, MA 02142
http://web.mit.edu/sorensen/www/
(617) 253 7945 -- voice
(617) 253 2660 -- fax
*
* 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/
