[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]
Re: st: -mfx-: can I just keep the interaction variable?
At 07:07 PM 9/10/2006, Scott Cunningham wrote:
I just tried something similar without problem. And, when I added a
var to mfx that was not legitimate, it gave me a warning message
about the variable not being found and went ahead and did the effects.
I'm assuming that the problem is with the name of the race dummy - it
must not be recognizing "_Irace_2" in the varlist. Yet I've not seen
anywhere in mfx as to how to call for a dummy variable's marginal
effect. Is it not the same name that is reported in the raw output?
So, I suspect you are on the wrong track. Are you sure there isn't
some intermediate step that could be zapping the estimates? Do you
still get the error if you don't include the race term? Perhaps you
should give your entire commands so we can better see what is going
on. Better yet, see if the problem is replicable using a publicly
available data set.
Richard Williams, Notre Dame Dept of Sociology
OFFICE: (574)631-6668, (574)631-6463
WWW (personal): http://www.nd.edu/~rwilliam
WWW (department): http://www.nd.edu/~soc
* For searches and help try: