Statalist


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

Re: st: dtobit Interpretation


From   nicola.baldini2@unibo.it
To   statalist@hsphsun2.harvard.edu
Subject   Re: st: dtobit Interpretation
Date   Sun, 25 May 2008 09:56:40 +0200

I don't have a direct answer for your question. But since the command has been released as STB-56: sg144; SJ4-3: sg144_1, you may find such an answer by consulting the related papers, which you can now freely (!) download from http://econpapers.repec.org/article/tsjstataj/ and http://econpapers.repec.org/article/tsjstbull/.

Nicola
At 02.33 22/05/2008 -0400, Abra Marie Jeffers wrote:
>Hello,
>
>I am trying to interpret the output of -dtobit- for a continuous, level 
>variable.
>
>For example: 
>If -dtobit- returns that the marginal effect at the mean of the 
>probability of being uncensored is 0.002 for x1, can I say that "if x1 
>increases by 10 from the mean, then the probability of being uncensored 
>increases by 0.02 other things equal"?
>Similarly, if -dtobit- returns that the marginal effects at the mean of 
>the conditional expectation is -1.45 for x2, do I say that "if x2 
>increases by 100 from the mean, then the conditional expectation 
>decreases by $145"?
>
>This seems too simple given the nonlinearities involved in the calculations.
>
>I would really appreciate any suggestions on giving the decomposed 
>marginal effects an economic interpretation.
>
>Thanks,
>Abra
>* 

*
*   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