Statalist


[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

Re: st: marg effects & s.e. in tobit


From   Austin Nichols <austinnichols@gmail.com>
To   statalist@hsphsun2.harvard.edu
Subject   Re: st: marg effects & s.e. in tobit
Date   Mon, 1 Jun 2009 07:42:31 -0400

John Bunge--
Presumably the ref is to http://www.stata.com/bookstore/ea.html, or an
earlier edition of that book.  I am guessing that -tobit- is
inappropriate for your empirical application; what are the outcome and
explanatory variables?  My guess is that a -glm- model is preferable.

On Mon, Jun 1, 2009 at 7:28 AM, Maarten buis <maartenbuis@yahoo.co.uk> wrote:
>
> --- On Sun, 31/5/09, John Bunge wrote:
>> in tobit with censoring at 0 you have
>> 4 marginal effects:
>>
>> (1) dE[y*|x]/dx
>> (2) dE[y|x,y>0]/dx
>> (3) dE[y|x]/dx
>> (4) dP[y>0|x]/dx
>
> I am guessing that this is one of the predicted values possible
> with -tobit- and are thus possible to obtain via -mfx-, but I
> would need to look at the paper documentation of -tobit- to say
> more, and I am away from home right now. Maybe somebody else
> can help.
>
>> possible reference: greene (2003), pp.764-766
>
> Remember that this is an interdisciplinary list, so any
> name-year references that are completely obvious within your
> discipline are completely meaningless here. So please give
> complete references.
>
> -- Maarten
*
*   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/



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