A heteroscedasticity-consistent covariance matrix estimator for time series regressions
Journal Article
This paper provides a covariance matrix estimator for the ordinary least squares coefficients of a linear time series model which is consistent even when the disturbances are heteroscedastic. This estimator does not require a formal model of the heteroscedasticity. One can also obtain a direct test of heteroscedasticity, although Monte Carlo experiments show that it may have low power. © 1983.
Full Text
Duke Authors
Cited Authors
- Hsieh, DA
Published Date
- January 1, 1983
Published In
Volume / Issue
- 22 / 3
Start / End Page
- 281 - 290
International Standard Serial Number (ISSN)
- 0304-4076
Digital Object Identifier (DOI)
- 10.1016/0304-4076(83)90104-5
Citation Source
- Scopus