Re: st: fixed and random effects for longitudinal censored continuous data

[Maarten Buis <maartenlbuis@gmail.com>]

On Fri, Oct 14, 2011 at 4:10 PM, House Wang wrote:
> The data is proportional data, lasting from 0 to 1, without either 0
> or 1. And the data is longitudinal across 30 years. In the model, I
> want to address the fixed and random effects of years OR congresses
> (every two years).
>
> I have found: xttobit can address random effects for longitudinal
> censored continuous data, but I do not know how to address fixed
> effects.
>
> My questions:
> 1, what are the correct command of STATA to address fixed effects for
> longitudinal censored continuous data. Any good examples?
>
> 2, xttobit can address random effects, but can you recommend any good
> examples?

I don't think a tobit model particularly useful for modeling
proportions as the logic of that model does not correspond well with
proportions. You are probably better of with some models for
fractional logit models for panel data proposed by Jeffrey Wooldridge
at the 2008 North American Stata Users' meeting:

http://ideas.repec.org/p/boc/nsug08/17.html

Hope this helps,
Maarten

--------------------------
Maarten L. Buis
Institut fuer Soziologie
Universitaet Tuebingen
Wilhelmstrasse 36
72074 Tuebingen
Germany


http://www.maartenbuis.nl
--------------------------
*
*   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/