I suggest that you check the mean(y) after you've put the data in stata.
maybe something went wrong. it should certainly be the case that the mean
of the data should be around the mean of the predicted values, and those
should be pretty close to (but not necessarily the same as) the expected
value of Y given the mean of x.
Gary King
On Sat, 1 Feb 2003, Karl DeRouen wrote:
Prof King: greetings.
i am trying to run clarify in conjnction with weibull regression.
everything sees fine til i do 'simqi' then it generates an expected
value of .11 (with setx mean).
my duration variable is months of civil war and it average is 73 so an
expected value of .11 doesnt seem to make sense. am i interpreting the
E(Y) wrong? is there some sort of transformatin that must be done on the
E(Y) so it can be interpreted in months?
thanks in advance,
--
Clarify mailing list served by Harvard-MIT Data Center
[Un]Subscribe/View Archive:
http://lists.hmdc.harvard.edu/?info=clarify