<>
You do not have to rely on -dtobit- in Stata 10.1, though:
*************
sysuse auto, clear
generate wgt=weight/1000
vers 8.2
qui tobit mpg wgt, ll(17)
dtobit
vers 10.1
qui{
loc lb 17
tobit mpg wgt, ll(`lb')
}
mfx
mfx, predict(ystar(`lb',.))
mfx, predict(e(`lb',.))
mfx, predict(pr(`lb',.))
*************
Does anybody know why the standard errors are different?
HTH
Martin
-----Ursprüngliche Nachricht-----
Von: [email protected]
[mailto:[email protected]] Im Auftrag von 21443017
Gesendet: Mittwoch, 8. Juli 2009 12:23
An: [email protected]
Betreff: st: dtobit
Dear All,
I have a problem of using dtobit. I am trying to estimate the marginal
effects after a tobit model by using dtobit. However, stata reports "[_se]
not found". What would be the problem?
The code I used is
tobit y x1 x2 x3 ll(0)
dtobit
Thanks for your help
Best
Wen
*
* For searches and help try:
* http://www.stata.com/help.cgi?search
* http://www.stata.com/support/statalist/faq
* http://www.ats.ucla.edu/stat/stata/
*
* For searches and help try:
* http://www.stata.com/help.cgi?search
* http://www.stata.com/support/statalist/faq
* http://www.ats.ucla.edu/stat/stata/
