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: censored regression - testing for normal and homoscedastic residuals


From   Maarten Buis <maartenlbuis@gmail.com>
To   statalist@hsphsun2.harvard.edu
Subject   Re: st: censored regression - testing for normal and homoscedastic residuals
Date   Tue, 31 May 2011 17:59:03 +0200

On Tue, May 31, 2011 at 5:37 PM, Anders, Christoph
<C.Anders@dshs-koeln.de> wrote:
> I conducted a regression with right-censored variables using the cnreg command.
> Since I suppose the residuals to be both heteroscedastic and not normally distributed, I would like to conduct some tests to proof it.
> But the commands I usually use - estat hettest and estat imtest - seem not to work here.
>
> Anybody who knows how to test for normally distributed and heteroscedastic residuals when having used cnreg?

You could sample datasets from your model, estimate a new model in
each of these datasets and store the residuals. These will give you an
idea of how the distribution of residuals should look like when the
model is correct. Graphically comparing these with the actual
residuals (e.g. using Nick Cox's -qplot- which you can find by typing
in Stata -findit qplot-) would be a good way of making your suspicions
plausible.

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/


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