Article ID | Journal | Published Year | Pages | File Type |
---|---|---|---|---|
5097303 | Journal of Econometrics | 2008 | 15 Pages |
Abstract
Under normality, least squares is efficient. However, if the errors are not normal, we can gain efficiency from the assertion that higher moments do not depend on the regressors. In this paper, we show how the assumption that higher moments do not depend on the regressors can be exploited in a GMM framework, and we provide simple estimators that are asymptotically equivalent to the GMM estimators. These estimators can be calculated by linear regressions which have been augmented with functions of the least squares residuals.
Keywords
Related Topics
Physical Sciences and Engineering
Mathematics
Statistics and Probability
Authors
Kyung So Im, Peter Schmidt,