Hi,
My hedonic model for a housing price index is a pooled cross sections
(independents) with 13 dummy time entries (each one for a quarter year).
Stata 10 allow for the use of robust standard errors after weighted least
squares (analitycal weight).
So I applied the robust option (HC3) after WLS. I think that´s correct, but
I couldn´t find any support in the literature.
Does anyone know of any academic articles that support that form?
Statistically thinking, is the use of robust option after WLS correct?
Thanks,
Sergio
*
* For searches and help try:
* http://www.stata.com/support/faqs/res/findit.html
* http://www.stata.com/support/statalist/faq
* http://www.ats.ucla.edu/stat/stata/
