Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.
[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
Re: st: I) plot the probability (instead of the dummy) on the residuals // II) cluster test
From
Maarten Buis <[email protected]>
To
[email protected]
Subject
Re: st: I) plot the probability (instead of the dummy) on the residuals // II) cluster test
Date
Mon, 12 Dec 2011 13:30:52 +0100
On Sat, Dec 10, 2011 at 11:26 AM, Luca Fumarco wrote:
> I) I have a probit regression, where the dep. var. is a dummy.
> I want to graphically see whether my model is affected by heteroskedasticity.Is there a way to plot the probability (instead of the dummy) on the residuals instead?
The problem is that the residual you care about is the difference
between the predicted and the latent (i.e. unobserved) variable. To
make things worse the latent variable is identified by the assumption
of homoskedasticity (or alternatively functional form for the
heteroskedasticity in -oglm-, see -ssc d oglm- and
<http://www.nd.edu/~rwilliam/oglm/>). So there is no way to
empirically check that assumption.
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/