Eric,
the solution is the one you expected:
try to run tobit y x, ll(0) and it would have to work.
Paolo
Paolo Canino
Istituto per la ricerca sociale
Via XX settembre, 24
20123 Milano
Italy
tel. +39.02.4676.4272
fax.+39.02.4676.4227
----- Original Message -----
From: "Neumayer,E" <[email protected]>
To: <[email protected]>
Sent: Tuesday, September 30, 2003 5:37 PM
Subject: st: Left-censoring in Tobit
> Hi,
>
> I have a dependent variable that is left-censored in the following sense.
Any values equal to 1 or above are recorded with their actual value. Any
values less than 1 are coded as zero. I thought I had to run the estimation
as
>
> tobit y x, ll(1)
>
> However, if I do this, then Stata also counts all observations with value
of 1 as censored. Should I therefore run
>
> tobit y x, ll(0) or something like tobit y x, ll(0.99)?
>
> Any help greatly appreciated. Best, Eric Neumayer
>
> *
> * 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/
