|
|  |
[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]
Re: st: interaction term in probit (inteff problem)
At 10:24 AM 6/23/2006, Kai-Wen Cheng wrote:
By the way, I have another question about inteff commands...
I am using 10 years data and I have to figure out the interaction effects
between college(a dummy variable) and every year. That is, I need to
figure out the interaction effects of year2*college, year3*college,
year4*college,.......,year10*college.
In Norton, Wang, Ai's paper, it said put dummy1 in the second position and
dummy 2 in the third and then dummy1*dummy2 in the fourth...But how about
getting more than one interaction terms? how to apply the commands to my
question?
It doesn't sound to me like you can do it. The help file says it is
for "when two variables have been interacted." In your setup, you've
got 9 vars (year2 through year10) interacted with college. I guess
you could include those terms beginning with variable 5, but they'll
be treated as continuous vars and the program won't know they are
interaction terms.
If it seemed legit to treat year as a continuous var, then you would
just have year and college and you could use the program.
I suspect this would not be legitimate, but I suppose you could keep
on rerunning the program rotating which vars are in positions 2, 3 and 4.
-------------------------------------------
Richard Williams, Notre Dame Dept of Sociology
OFFICE: (574)631-6668, (574)631-6463
FAX: (574)288-4373
HOME: (574)289-5227
EMAIL: [email protected]
WWW (personal): http://www.nd.edu/~rwilliam
WWW (department): http://www.nd.edu/~soc
*
* 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/
