TY - JOUR
T1 - An Orthogonality-Based Estimation of Moments for Linear Mixed Models
AU - Wu, Ping
AU - ZHU, Lixing
N1 - This research was supported by a grant (HKBU 2030/07P) from the Research Grants Council of Hong Kong, Hong Kong, China.
PY - 2010/6
Y1 - 2010/6
N2 - 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.
AB - 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.
KW - Asymptotic normality
KW - Linear mixed models
KW - Moment estimator
KW - QR decomposition
UR - http://www.scopus.com/inward/record.url?scp=77954002805&partnerID=8YFLogxK
U2 - 10.1111/j.1467-9469.2009.00673.x
DO - 10.1111/j.1467-9469.2009.00673.x
M3 - Journal article
AN - SCOPUS:77954002805
SN - 0303-6898
VL - 37
SP - 253
EP - 263
JO - Scandinavian Journal of Statistics
JF - Scandinavian Journal of Statistics
IS - 2
ER -