> 1. Looks like there is quite a bit of arbitrary tune up: why 24
> months? why 10 portfolios?
Yes, this is arbitrary....
Actually, I was a bit sloppy in decription...
The estimation period is normally "24 to 60 months depending on
availability".
(60 months is not a big deal given that detailed US stock data is available
since January of 1926).
10 portfolios and 24 to 60 months of estimation period depending on
availability is commonly adopted because of "sentimental reasons" (looking
for the right words here), because Fama-MacBeth (1974) and Fama-French
(1992, 1993, 1996) adopted this criteria.
> 2. Are the standard errors corrected for the multi-stage estimation?
> You can still cast this problem in terms of linear filtering of the
> original data, as all of the testable coefficients should be linear
> functions of the original prices. Hence you can come up with correct
> standard errors just by the virtue of this linearity. (Am I missing
> something?) The standard errors that come out of the last regression
> may be wrong by a factor of 5 or so.
You are right. The standard errors are not corrected.
This is one of many issues I am focussing on while checking for the
robustness of Fama-Macbeth tests.
*
* 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/
