Look in the
brand new issue of STATISTICS IN MEDICINE. (Published by Wiley).
This is
the main theme of the entire issue.
Sincerely,
Uri
-----Original Message-----
From: owner-[email protected]
[mailto:owner-[email protected]]
On Behalf Of Ismail Ait Saadi
Sent: Monday, December 31, 2007 8:55 AM
To: [email protected]
Subject: st: LOGIT MODEL
Dear All,
I know most of you are on holiday but I really
appreciate your help and time.
I am running a logit model to predict currency crises.
I have 14 variables. I run MODEL1 with all 14 variables, then run MODEL2 with
only 7 variables which are mostly used by researchers. I wanted to compare the
two models and see which one is superior.
1-Can you please give me
the list of indicators that can be used for such comparison?
2-I know that ROC and
PSEUDO R2 can be used but I get confused when some indicators are in favor of
MODEL1 and others are in favor of MODEL2. What should I do.
3- What are the general
rules in comparing two logit models.
Many thanks.
Enjoy your Holidays,
Ismail
*
* 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/
