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

st: Pesaran test for cross section dependence in panels [was: Help in Programing]


From   "Scott Merryman" <[email protected]>
To   <[email protected]>
Subject   st: Pesaran test for cross section dependence in panels [was: Help in Programing]
Date   Sat, 5 Mar 2005 09:23:05 -0600

The error statement is telling you need to change the line "estimates
hold..." to "_estimates hold..."

But there is a much more fundamental problem.  -bpagen- is the Breusch-Pagan
(1979) Lagrange multiplier test for heteroskedasticity, not the
Breusch-Pagan (1980) LM test for cross-sectional correlation in fixed
effects model

You should take a look at -xttest2-.

Hope this helps,
Scott


Breusch, T. & Pagan, A. (1979), "A simple test of heteroskedasticity
and random coefficient variation", Econometrica 47.

Breusch T. & Pagan, A. (1980), "The LM test and its Applications to Model
Specification in Econometrics", Review of Economic Studies, 47.


> -----Original Message-----
> From: [email protected] [mailto:owner-
> [email protected]] On Behalf Of Ricardo Gon�alves Silva
> Sent: Friday, March 04, 2005 1:08 PM
> To: Stata
> Subject: st: Help in Programing
> 
> Dear Users,
> 
> The folowing code is to implement a test for comtemporaneous correlation
> in
> panel data, after xtreg ..., fe.
> The statistic to be computed is: CD=sqrt(T/(N*(N-1))*pwc, where
> T is the number of periods, N the panel dimension and pwc is the estimated
> pair-wise residual correlation.
> However, when I run it, I receive the error
> 
> . cdpesaran yr
> the subcommand hold has been moved from estimates to  _estimates
> r(198);
> 
> 
> Any hint?
> 
> * cdpesaran V1.0 cloned from bpagan.ado %Ricardo Gon�alves Silva
> 



*
*   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 1996–2024 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index