Bookmark and Share

Notice: On March 31, it was announced that Statalist is moving from an email list to a forum. The old list will shut down at the end of May, and its replacement, statalist.org is already up and running.


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

RE: st: Normally distributed error term & testing normality of


From   Ebru Ozturk <ebru_0512@hotmail.com>
To   <statalist@hsphsun2.harvard.edu>
Subject   RE: st: Normally distributed error term & testing normality of
Date   Sun, 14 Oct 2012 18:06:22 +0300

Thank you very much for your response.

But, the issue is not for me whether to use -glm- or -tobit-. I want to learn how I can test Tobit specifications graphically. 

For instance, in linear regression they generate residuals and check it by -qnorm- or -pnorm- (qnorm e). Also, to check heteroscedasticity they make a graph of the residuals of the model against the predicted values. 

So, if the residuals will not be normal because of censoring, what should I look at? What should I use instead of residuals in Tobit? 

Ebru

----------------------------------------
> From: kit.baum@bc.edu
> To: statalist@hsphsun2.harvard.edu
> Subject: re: st: Normally distributed error term & testing normality of
> Date: Sun, 14 Oct 2012 13:06:41 +0000
>
> <>
> Justina said
>
> Maybe this was already said, but there is also the command -hettest-
>
> That command, as -help hettest- will show, is deprecated in favor of -estat hettest- which accesses the same suite of tests. But
> -help tobit postestimation- does not offer -estat hettest- as an option, for all of the good reasons that have been discussed earlier
> in this thread. Unlike standard regression, normality of the error is a maintained hypothesis in the Tobit framework, as its
> likelihood combines a probit and a regression. Per earlier postings, it would be much more sensible in many cases to use -glm-
> for this sort of model.
>
> Along those lines, the command -linktest- allows you to consider whether the 'link' explicit or implicit in
> the model you estimate is supported by the data. In my own work, I have found that after estimation of -tobit- and -glm- on the same sample
> of data with a mass point at zero, -linktest- often clearly rejects the Tobit specification, and does not reject the -glm- form of the model.
> That might be something for Ebru to consider, rather than fruitless enquiries about the appropriateness of tests designed for a linear regression context to the Tobit.
>
> Kit
>
>
> Kit Baum | Boston College Economics & DIW Berlin | http://ideas.repec.org/e/pba1.html
> An Introduction to Stata Programming | http://www.stata-press.com/books/isp.html
> An Introduction to Modern Econometrics Using Stata | http://www.stata-press.com/books/imeus.html
>
>
> *
> * For searches and help try:
> * http://www.stata.com/help.cgi?search
> * http://www.stata.com/support/faqs/resources/statalist-faq/
> * http://www.ats.ucla.edu/stat/stata/ 		 	   		  
*
*   For searches and help try:
*   http://www.stata.com/help.cgi?search
*   http://www.stata.com/support/faqs/resources/statalist-faq/
*   http://www.ats.ucla.edu/stat/stata/


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