A heteroscedasticity-consistent covariance matrix estimator for time series regressions

Published

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