[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]
Re: st: dtobit and tobcm in Stata 9
At 07:14 AM 6/8/2005 -0700, Alejandro Lopez-Feldman wrote:
This little tidbit from the online help for -version- clarifies what the
problem is. If you set version to earlier than 9, then
I have tried to use dtobit and tobcm in Stata 9 but I get back the warning
[_se] not found
I guess something changed from 8 to 9 in the way in which standard errors
are saved after tobit... I can get it to work if I set the version to 8.2
but I was wondering if the authors of these ado files are on the list and
if they are aware of the problem.
"Commands tobit and cnreg revert to pre-Stata 9 logic in how e(b) and e(V)
are stored. Results were stored in a single equation containing both
coefficients and the ancillary variance parameter."
Similarly, the help says
"Commands ologit and oprobit revert to pre-Stata 9 logic in how e(b) and
e(V) are stored. Results were stored in two equations, with all cut points
stored in the second."
Ergo, user-written post-estimation commands for -tobit-, -cnreg-, -ologit-
and -oprobit- may be broken now. You either need to use version control
when running -tobit-, etc., or else the user-written commands have to be
updated. Or, you could maybe write a utility to rewrite e(b) and e(V) back
into Stata 8 format.
Again, I wonder what was gained by reformatting e(b) and e(V) in Stata 9,
but I suppose there was a reason for it.
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: