Hi, everyone,
I am estimating an random effects generalized ordered
probit model, and though I get the coefficients fine,
I cannot get marginal effects by using the mfx command
since I am getting the "Warning: ... rescaling"
messages. It seems to me that all of my continuous
variables are in trouble and though I have rescaled
all the continuous variables to make them within
comparable range (eg. 0-1). I have read previous FAQ
and postings on the rescaling thing; but when there
are, say, four variables in trouble it is extremely
frustrating to get to the right answer. -tracelvl- or
-diagnostics- command doesn't seem to offer a lot of
help.
I am wondering (1) does -margeff- command obtain the
marginal effects differentaly? Since for -gologit- I
can get the marginal effects using -margeff- quite
fast and fine. Unfortunately, -margeff- doesn't work
with -regoprob-. (2) In my case, does it imply
something is wrong with the regression itself or it is
just the rescaling problem? (3) What can I do to
solve this issue? Since I am feeling that I am on this
wild goose chase right now for the suspect.
Any information is highly appreciated, and I am very
frustrated right now.
Thanks a lot,
Carol
__________________________________________________
Do You Yahoo!?
Tired of spam? Yahoo! Mail has the best spam protection around
http://mail.yahoo.com
*
* 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/
