Stata The Stata listserver
[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]

st: Re: xtclad?


From   "Scott Merryman" <smerryman@kc.rr.com>
To   <statalist@hsphsun2.harvard.edu>
Subject   st: Re: xtclad?
Date   Fri, 2 May 2003 21:34:41 -0500

----- Original Message -----
From: "tom blade" <tomblade@eudoramail.com>
To: <statalist@hsphsun2.harvard.edu>
Sent: Thursday, May 01, 2003 6:39 AM
Subject: st: xtclad?


> Dear statalist
>
> I am working with the command xttobit but I have a problem of
> heteroskedasticity. I have read that clad is robust to
> heteroscedasticity and is consistent and asymptotically
> normal for a wide class of error distributions. I would like to do
> something like that with panel data.
>
> As far as I know there is no "xtclad" command. Has someone a
> solution?
>
> Thank you very much in advance to all.
>
> Tom
>

At least for fixed effects, CLAD is not consistent.   Honore (1992, "Trimmed
LAD and Least Squares Estimation of Truncated and Censored Regression Models
with Fixed Effects." Econometrica) proposed ICLAD (identically censored
least absolute deviations) for censored panel data with fixed effects.  To
my knowledge, there are no ICLAD routines available in Stata.

You might want to take a look at Kenneth Chay and James Powell's
"Semiparametric Censored Regression Models" available at:

http://elsa.berkeley.edu/users/kenchay/ftp/binresp/jepfinal.pdf

and published in the Journal of Economic Perspectives, 2001

Hope this helps,
Scott


*
*   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