Re: st: within estimator as "phyrric-victory" in corporate finance?

[Christopher Baum <kit.baum@bc.edu>]

<>
On Jan 21, 2011, at 2:33 AM, Erasmo wrote:

> This is problematic because firms change very
> little and very slowly and with fixed-effects many independent
> variables could "appeear" statistically and/or economically
> insignificant, while they might still be very powerful in explaining
> cross-sectional variation.

If by cross-sectional variation you mean that firm A has a higher average ROE than firm B, then no. That is what the between estimator does for a living. It ignores the within-firm variation. The within estimator ignores the between variation. The random effects estimator takes both within and between into account, optimally weighting them, but under stringent assumptions about the orithogonality of regressors and error, unlikely to be satisfied in empirical finance applications.

Kit



Kit Baum   |   Boston College Economics & DIW Berlin   |   http://ideas.repec.org/e/pba1.html
                              An Introduction to Stata Programming  |   http://www.stata-press.com/books/isp.html
   An Introduction to Modern Econometrics Using Stata  |   http://www.stata-press.com/books/imeus.html


*
*   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/