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

st: Autocorrelation in FE and pantest2 problems

From   John Bunge <>
Subject   st: Autocorrelation in FE and pantest2 problems
Date   Thu, 09 Aug 2007 20:39:59 +0200

Dear Users.

I want to implement a panel data regression on a T=20 and N=24 Macro Panel.

First I run FE. Then I want to check for autocorrelation in the residuals in order to have a criterion if dynamic methods (anderson/hsiao, arellano/bond, blundell/bond) should be applied due to a lagged dependent variable.

Related to this are two questions:

1) As a serial correlation test for the residuals of a FE regression I only know the command pantest2. Are there any other commands? I read about the LM test for 1st order serial correlation in a FE model in Baltagi's panel book (3rd ed., 2005), pp. 97-98. Is there a command for it in Stata?

2) If I apply the command pantest2 the order in my dataset was changed sometimes (the order of observation units remains but the time order within those units change in a apparently random fashion), so pantest2 does not run. Thats really strange since I always have tsset my data! Is this a general problem with this command or may it be caused by my Stata Version?

Best regards,


Der WEB.DE SmartSurfer hilft bis zu 70% Ihrer Onlinekosten zu sparen!

*   For searches and help try:

© Copyright 1996–2017 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index