Bayes and empirical Bayes iteration estimators in two seemingly unrelated regression equations

doi:10.1360/03ys0173

CSpace

	Bayes and empirical Bayes iteration estimators in two seemingly unrelated regression equations
	Wang, LC
	2005-09-01
发表期刊	SCIENCE IN CHINA SERIES A-MATHEMATICS
ISSN	1006-9283
卷号	48 期号:9 页码:1153-1168
摘要	For a system of two seemingly unrelated regression equations given by {y1 = X(1)beta + epsilon(1), y2 = X(2)gamma + epsilon(2), (y(1) is an m x 1 vector and y(2) is an n x 1 vector, m not equal n), employing the covariance adjusted technique, we propose the parametric Bayes and empirical Bayes iteration estimator sequences for regression coefficients. We prove that both the covariance matrices converge monotonically and the Bayes iteration estimator squence is consistent as well. Based on the mean square error (MSE) criterion, we elaborate the superiority of empirical Bayes iteration estimator over the Bayes estimator of single equation when the covariance matrix of errors is unknown. The results obtained in this paper further show the power of the covariance adjusted approach.
关键词	seemingly unrelated regressions covariance adjusted approach empirical Bayes estimation mean square error criterion
DOI	10.1360/03ys0173
语种	英语
WOS研究方向	Mathematics
WOS类目	Mathematics, Applied ; Mathematics
WOS记录号	WOS:000233073200001
出版者	SCIENCE PRESS
引用统计
文献类型	期刊论文
条目标识符	http://ir.amss.ac.cn/handle/2S8OKBNM/1078
专题	中国科学院数学与系统科学研究院
通讯作者	Wang, LC
作者单位	Chinese Acad Sci, Inst Appl Math, Beijing 100080, Peoples R China
推荐引用方式 GB/T 7714	Wang, LC. Bayes and empirical Bayes iteration estimators in two seemingly unrelated regression equations[J]. SCIENCE IN CHINA SERIES A-MATHEMATICS,2005,48(9):1153-1168.
APA	Wang, LC.(2005).Bayes and empirical Bayes iteration estimators in two seemingly unrelated regression equations.SCIENCE IN CHINA SERIES A-MATHEMATICS,48(9),1153-1168.
MLA	Wang, LC."Bayes and empirical Bayes iteration estimators in two seemingly unrelated regression equations".SCIENCE IN CHINA SERIES A-MATHEMATICS 48.9(2005):1153-1168.