A heteroscedasticity-consistent covariance matrix estimator for time series regressions
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.
Volume / Issue
Start / End Page
International Standard Serial Number (ISSN)
Digital Object Identifier (DOI)