Statalist


[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]

st: Re: threshold tobit command


From   Kit Baum <baum@bc.edu>
To   statalist@hsphsun2.harvard.edu
Subject   st: Re: threshold tobit command
Date   Sat, 28 Jul 2007 07:18:11 -0400

I am not familiar with that article. Is the parameter 'a' global, applying to all individuals, or is it individual-specific? A model with a censoring point differing among individuals is estimated with - cnreg-. You might want to look at the manual's description of that command.


Kit Baum, Boston College Economics and DIW Berlin
http://ideas.repec.org/e/pba1.html
An Introduction to Modern Econometrics Using Stata:
http://www.stata-press.com/books/imeus.html


On Jul 28, 2007, at 2:33 AM, Mahabir wrote:


Does anyone know the command to estimate Eaton's and Tamura's (1994)
threshold tobit model?

This is a variant of the standard tobit model where the dependent
variable is specified as ln(a+V) and 'a' is a threshold parameter, which
is estimated in addition to the constant term among the right hand side
variables. The threshold parameter 'a' is assumed to be the amount of
trade that is lost in transit or the amount that 'melts away'. If 'a'=0
, we are back to the standard tobit. If 'a'>0, then explanatory
variables for V must achieve a minimum threshold value before strictly
positive values of V occur (Eaton and Tamura, pp 490)

The commands 'tobit' and 'dtobit' in stata only give the standard tobit
estimates. Is there any command or options that one needs to add to
obtain the threshold tobit estimates?
*
*   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/



© Copyright 1996–2014 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index