Stata The Stata listserver
[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]

Re: st: Newey West errors with panel data


From   skhemani@worldbank.org
To   statalist@hsphsun2.harvard.edu
Subject   Re: st: Newey West errors with panel data
Date   Thu, 26 Sep 2002 14:33:40 -0400

Hi John, and fellow Stata users,
Thank you for your quick response. Yes, I am familiar with the GLS option and
have used that, but prefer to do simple OLS with "robust" standard errors that
are consistently estimated in the presence of both heteroskedasticity and serial
correlation. I have also used the "xtpcse" command in STATA 7, that the HELP
menu reports as using the Prais-Winsten regression. I am not familiar with this
estimation method, and would appreciate help in this regard as well.

Best,
Stuti



                                                                                                        
                    "John A Karikari"                                                                   
                    <KarikariJ@GAO.GOV>               To:     <Statalist@Hsphsun2.Harvard.Edu>,         
                    Sent by:                          <Skhemani@Worldbank.Org>                          
                    owner-statalist@hsphsun2.h        cc:                                               
                    arvard.edu                        Subject:     Re: st: Newey West errors with panel 
                                                      data                                              
                                                                                                        
                    09/26/2002 02:18 PM                                                                 
                    Please respond to                                                                   
                    statalist                                                                           
                                                                                                        
                                                                                                        
                                                                                                        
                                                                                                        




As an alternative to Newey West, if you do not have lagged dependent
variables in your model, you could use the XTGLS, which estimates
cross-sectional time-series models using the FGLS technique--it allows
estimation with AR(1) within panels and heteroscedasticity across
panels.

For the IV estimation, you could use a 2SLS approach with the XTGLS

>>> skhemani@worldbank.org 09/26/02 01:58PM >>>
I would very much appreciate receiving advice on how to estimate
Newey-West
standard errors in a panel data setting in Stata, and with
instrumental
variables (Stata command: IVREG) and three stage least squares (Stata
command:
REG3)

Thank you,
Stuti Khemani

*
*   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/
*
*   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/





*
*   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