More back to basics: Why is plotting the residuals almost never mentioned in these threads as a way of checking for heteroscedasticity?
Can't economists -- for it appears to be mostly economists who ask these questions, even though heteroscedasticity might appear in anyone's analysis -- draw graphs? Or they are paranoid about any indication that doesn't come with P-value attached?
"Not rigorous!" "Subjective!". So is choosing model form and variable mix....
Nick
[email protected]
Maarten buis
--- Gaul� Patrick <[email protected]> wrote:
> I would not worry about testing for heteroskedasticity. In practice,
> it just makes more sense to always use robust standard errors.
David Freedman (2006) has exactly the opposite view. He basically
distinguishes two scenarios: 1) the model is very wrong in which case
robustifying the standard errors makes a difference, but it also means
that all the coefficients are also wrong. So in this case you are
correctly testing meaningless hypotheses. 2) The model is almost right,
in which case robustifying makes virtually no difference.
In other words -robust- either makes no difference or when -robust-
does make a difference, the model is so much beyond repair that you'll
do the wrong thing anyhow. So, all -robust- does is add a false sense
of security.
A final note, though you will probably already know it as it is (or
should be) in any intro stats book: Do not test for heteroskedasticity
before you have looked at the functional form of the effects of your
predictors.
*
* 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/
