Statalist The Stata Listserver


[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]

st: Re: 2 way FE and serial correlation


From   Kit Baum <baum@bc.edu>
To   statalist@hsphsun2.harvard.edu
Subject   st: Re: 2 way FE and serial correlation
Date   Sat, 14 Oct 2006 03:39:50 -0400

1) To use two-way fixed effects, use explicit dummies for the time dimension.

2) ivreg2 contains a superset of the capabilities of newey2, and xtivreg2 is a wrapper to provide one-way fixed effects (and first differences). xtivreg2 will let you calculate HAC ("Newey-West") errors in a fixed effects context. It estimates OLS with HAC standard errors as well as IV.

ssc install ivreg2
ssc install xtivreg2

and read the help files for those two programs.

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


On Oct 14, 2006, at 2:33 AM, Ferhat wrote:


2-)I want to correct for serial correlation with one way fixed effect and I
have seen the David Roodman's user-written -newey2 code but I dont know how
to install it to my STATA9 or at east how to use that code.I will be happy
if anyone can help me about that issue.
*
*   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/



© Copyright 1996–2014 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index