<>
If you are in picky mode, you can take a cue from
http://www.stata.com/support/faqs/res/history.html
and find out when -dtobit- stopped working...
*************
sysuse auto, clear
local versions /*
*/"5.0 6.0 7.0 8.0 8.1 8.2 9.0 9.1 9.2 10.0 10.1"
foreach ver of local versions{
version `ver'
di in red "Now at version: " /*
*/ %2.1fc `ver'
tobit mpg trunk weight, ll(17)
dtobit
}
**************
HTH
Martin
-----Ursprüngliche Nachricht-----
Von: [email protected]
[mailto:[email protected]] Im Auftrag von Martin Weiss
Gesendet: Samstag, 30. Mai 2009 11:58
An: [email protected]
Betreff: AW: st: Re: Marginal Effects in Tobit
<>
John,
you can render -dtobit- operational by typing -version 8.2- interactively/in
your do-file. Note when the command stops in the following example...
*************
sysuse auto, clear
forv i=6/10{
version `i'
di in red "Now at version: " `i'
tobit mpg trunk weight, ll(17)
dtobit
}
*************
HTH
Martin
-----Ursprüngliche Nachricht-----
Von: [email protected]
[mailto:[email protected]] Im Auftrag von John Bunge
Gesendet: Samstag, 30. Mai 2009 11:45
An: [email protected]
Betreff: Re: st: Re: Marginal Effects in Tobit
sorry, of course I do mean DTOBIT and DTOBIT2
thanks
> -----Ursprüngliche Nachricht-----
> Von: "Martin Weiss" <[email protected]>
> Gesendet: 30.05.09 11:22:03
> An: <[email protected]>
> Betreff: st: Re: Marginal Effects in Tobit
> <>
>
> You keep talking about "dprobit" which is a little weird. I assume you
mean
> "dtobit" and "dtobit2"?
>
>
>
> HTH
> Martin
> _______________________
> ----- Original Message -----
> From: "John Bunge" <[email protected]>
> To: <[email protected]>
> Sent: Saturday, May 30, 2009 11:17 AM
> Subject: st: Marginal Effects in Tobit
>
>
> > Dear All
> >
> > I'd like to compute the marg. effects and its standard errors for the
> > unconditional expect value in the tobit model.
> >
> > (1) the standard command "tobit" in combination with "mfx" does not
offer
> > the option to compute marginal effects for the UNCONDITIONAL expected
> > value (in contrast to the marg eff on the expected value conditional on
> > being uncensored and the marginal effect on the probability to be
> > uncensored).
> > (2) the command "dprobit" is constantly reporting me an error: "[_se]
not
> > found"
> > (3) the command "dprobit2" computes the marginal effects but does not
> > provide the standard errors (or at least its help file does not describe
> > how to obtain them)
> >
> > Best,
> >
> > John.
> > *
> > * 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/
>
*
* 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/
*
* 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/