|
Estimation in Linear Regression Models with Disparate Data Points
William S. Krasker
Abstract
This paper addresses the problem of estimating unknown regression coefficients when erroneous data and other violations of the standard assumptions are possible. An estimator which has a limited sensitivity to these departures from the assumptions is presented, and some of its properties are derived. This estimator is shown to have a certain efficiency property relative to other estimators with the same sensitivity to erroneous data.
|
