On the performance of biased estimators in the linear regression model with correlated or heteroscedastic errors (Q2266321): Difference between revisions
From MaRDI portal
Latest revision as of 17:10, 14 June 2024
scientific article
| Language | Label | Description | Also known as |
|---|---|---|---|
| English | On the performance of biased estimators in the linear regression model with correlated or heteroscedastic errors |
scientific article |
Statements
On the performance of biased estimators in the linear regression model with correlated or heteroscedastic errors (English)
0 references
1984
0 references
This paper investigates the performance of biased estimators in the linear regression model when the assumption of homoscedasticity is not satisfied. Conditions are derived which show when OLS and GLS are dominated by shrinkage estimators with respect to various mean square error criteria. Specific attention is paid to the case when the covariance matrix of the disturbances is not completely known.
0 references
correlated errors
0 references
generalized least squares estimator
0 references
ordinary least squares estimator
0 references
heteroscedastic errors
0 references
biased estimators
0 references
shrinkage estimators
0 references
mean square error criteria
0 references
0 references
0 references
0 references
