The Limiting Power of Point Optimal Autocorrelation Tests

This paper considers the point optimal tests for AR(l) errors in the linear regression model. It is shown that these tests have the same limiting power characteristics as the Durbin-Watson test. The limiting power is zero or one when the regression has no intercept, but lies strictly between these values when an intercept is included.


Issue Date:
Jul 07 1991
Publication Type:
Working or Discussion Paper
Language:
English
Total Pages:
14
Series Statement:
9110




 Record created 2017-09-13, last modified 2017-09-13

Fulltext:
Download fulltext
PDF

Rate this document:

Rate this document:
1
2
3
 
(Not yet reviewed)