Have you checked the tobit model?
See Ch. 20 in Greene's textbook (I am referring to the 4th edition).
A simple introduction to tobit models can also be found in Wooldridge's
"Introductory Econometrics", ch. 17 (2nd edition).
Hope it helps.
Giovanni
-----------------------------------------------
Giovanni VECCHI
Dipartimento di Economia e Istituzioni
Universit� di Roma "Tor Vergata"
Via Columbia, 2
00133 Roma
Italy
voice + 39 (06) 7259 5730
fax + 39 (06) 2020 500
email [email protected]
-----------------------------------------------
-----Original Message-----
From: [email protected]
[mailto:[email protected]] On Behalf Of julio estevez
Sent: gioved� 28 novembre 2002 19.25
To: [email protected]
Subject: st: continuous dependent variable with lots of zeros
Dear Stata listers:
I am running a regression in which my dependent
variable is continuous but it has big chunk of zeros.
I know that the variable is not truncated or censored
in any way so OLS should be the correct estimator.
However this type of estimation will run into problems
because the resulting residuals will typically not be
"well-baheved" (there are grossly non-normal)
Any Idea on how to proceed? When the dependent
variable is 0/1 or ordinal there are some procedures
available (zero-inflated estimators) but I have not
found anything when the dependent variable is
continuous.
thanks for the help!
Julio
__________________________________________________
Do you Yahoo!?
Yahoo! Mail Plus - Powerful. Affordable. Sign up now.
http://mailplus.yahoo.com
*
* 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/
