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

st: re: Durbin alternative test

From   Kit Baum <[email protected]>
To   [email protected]
Subject   st: re: Durbin alternative test
Date   Tue, 18 Dec 2007 19:23:14 -0500

Josiane said

This is my first time running this test and I am not sure how to
interpret the results.

. estat durbinalt

Durbin's alternative test for autocorrelation
lags(p) | chi2 df Prob >
1 | 0.998 1 0.3179
H0: no serial correlation

Does this mean the regression model I just created contains a serial

No, the null is "no serial correlation", and you have a p-value far in excess of 0.05 or 0.10, which would imply a rejection at the 95% or 90% level, respectively.

Note that this test is a special case of the Breusch-Godfrey test, which considers more than 1 lag, and is thus more general in determining whether there is any evidence of serial correlation. See -estat bgodfrey-

Kit Baum, Boston College Economics and DIW Berlin
An Introduction to Modern Econometrics Using Stata:

* For searches and help try:

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