Yes, the problem really is the number of characters. Unfortunately in
my original model, the number of characters is doomed to exceed 244.
Of course, I could easily rename all the variables, and run the
-regoprobit models again (I have more than one to re-run).. However,
that would take a couple of days...Maybe Manos is right and a
modification of the ado file of mfx or mfx2 would do it. Is that
feasible?
Mirko
On 7/20/07, Richard Williams <[email protected]> wrote:
At 02:52 PM 7/20/2007, Richard Williams wrote:
>There might also be some sort of problem if a string containing all
>the var names gets longer than 244 characters. In his regoprob
>command, Mirko might just try putting the z vars first, so that
>their names will fall within the first 244 characters of all the var names.
I think this is closer to what the problem is. I changed Manos
example mfx2 command to
mfx2, m varlist(thisistomakethenamebiga)
at(thisistomakethenamebigk=0, thisistomakethenamebigl=0) stub(mfx);
and I still got the error "warning: variables thisistomakethenamebigk
thisistomakethenamebigl in at() list not found in model". So, I'm
thinking mfx has problems when the list of varnames gets bigger than
244 characters and the at option includes vars outside the first 244
characters.
-------------------------------------------
Richard Williams, Notre Dame Dept of Sociology
OFFICE: (574)631-6668, (574)631-6463
HOME: (574)289-5227
EMAIL: [email protected]
WWW: http://www.nd.edu/~rwilliam
*
* 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/
*
* 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/
