re: Antwort: re: st: xtreg xtregar

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

<>
"the size of the Nickell-bias depends on both T and N. There are cases where
the bias is negligeably small."

There may be such cases, but a panel with 3-5 years of data per unit is about the worst case imaginable. My class notes include

 "Nickell demonstrates that the inconsistency of \hat{\rho} as n → ∞ is of order 1/T,
which may be quite sizable in a “small T” context. "  

If I received a paper to review in which the author ignored Nickell bias without a convincing argument that it was indeed negligible in his/her context, I would be inclined to reject the paper.

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/