Abstract
Estimating higher-order moments, particularly fourth-order moments in linear mixed models is an important, but difficult issue. In this article, an orthogonality-based estimation of moments is proposed. Under only moment conditions, this method can easily be used to estimate the model parameters and moments, particularly those of higher order than the second order, and in the estimators the random effects and errors do not affect each other. The asymptotic normality of all the estimators is provided. Moreover, the method is readily extended to handle non-linear, semiparametric and non-linear models. A simulation study is carried out to examine the performance of the new method.
Original language | English |
---|---|
Pages (from-to) | 253-263 |
Number of pages | 11 |
Journal | Scandinavian Journal of Statistics |
Volume | 37 |
Issue number | 2 |
DOIs | |
Publication status | Published - Jun 2010 |
Scopus Subject Areas
- Statistics and Probability
- Statistics, Probability and Uncertainty
User-Defined Keywords
- Asymptotic normality
- Linear mixed models
- Moment estimator
- QR decomposition