Bookmark and Share

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]

st: RE: RE: Test for Heteroskedasticity


From   Nick Cox <n.j.cox@durham.ac.uk>
To   "'statalist@hsphsun2.harvard.edu'" <statalist@hsphsun2.harvard.edu>
Subject   st: RE: RE: Test for Heteroskedasticity
Date   Tue, 24 Jan 2012 16:39:38 +0000

I'm with Tony here in the bemused corner of the stand. 

Quite what would the test be? Can you point to literature on an appropriate test? Even the idea of a residual seems problematic for a tobit model. 

Also, I am down as an author of -whitetst- (STB/SSC): the help says explicitly "-whitetst- is for use after -regress- or -cnsreg-", so invoking it is pointless and comment that it "does not work" is inappropriate. 

Nick 
n.j.cox@durham.ac.uk 

Lachenbruch, Peter [Tony] 

A couple of comments:
1.   Since Tobit seems to be working with truncated normals, doesn't this guarantee unequal variance?
2.   Can you interpret a regression model with 35 predictors?  I can't even in multiple regression.  

Pattarawan Watcharaanantapong

        I need to test for Heteroskedasticity after I run Tobit model,
do anyone know about stata command to test for heteroskedaticity for
tobit model? I tried whitetst, hettest, and clad but they did not work
after running Tobit.

For example: I ran this regression below

tobit  y x1 x2 x3 x4 x5 x6 x7 x8 x9 x10 x11....x35 [pweight], ll(0)
whitetst
last estimates not found

Therefore, I am not sure I use the right command to test for
Heteroskedasticity or not. Thank you so much.

*
*   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 1996–2018 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   Site index