Statalist The Stata Listserver


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

Re: st: to check the significance of the coefficient


From   "Keynes M. Smith" <[email protected]>
To   [email protected]
Subject   Re: st: to check the significance of the coefficient
Date   Fri, 20 Apr 2007 21:48:33 +0100

Hi,

Thanks for your reply.

I already run the fixed effect model and F-test accept the null hypothesis.

So I have to work on pooled OLS.

I also check for the heteroskedastic, here is the result

Breusch-Pagan / Cook-Weisberg test for heteroskedasticity
        Ho: Constant variance
        Variables: fitted values of gdppercapita

        chi2(1)      =     2.58
        Prob > chi2  =   0.1085

which, if I'm not misunderstand, mean that there's no heteroskedastic problem.

For the P-value, is that mean I have to divide by 2 before check the
significance of the

coeffiicent?

Could you please suggest me how to test autocorrelation and how to
correct it if I found the

problem.

Regards,

A. Sura

On 4/20/07, Kit Baum <[email protected]> wrote:
Keynes said

I run pooled OLS by using stata and I want to check the significance
of the coefficient.

I'm confuse about the P-value appear in the result.

Do I have to divide that P-value by 2 before I check the significance
of the coefficient?

Moreover, how can I check for autocorrelation in this pooled OLS model?


The p-value given is for the null hypothesis that the coefficient
equals zero, i.e. that of a two-tailed t-test.

If this 'pooled OLS' indicates that you are using panel data, I would
first of all worry about the possibility of unobserved heterogeneity.
Have you tried estimating the model with fixed effects (xtreg, fe)?
If the F-test for individual effects is significant then these pooled
OLS results are not consistent.

In the case of fixed effects, you could use xtgls and allow for
various forms of AR(1). You could also estimate the model with Mark
Schaffer's xtivreg2 (sic; it estimates OLS fixed effects, not just
IV) and use HAC ("Newey-West")  standard errors, which would correct
for heteroskedasticity and autocorrelation of unknown form.

Kit

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


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