摘要
本文考虑单向分类的方差分析模型，构造了Ｐ′α的线性Ｂａｙｅｓ估计和经验Ｂａｙｅｓ（ＥＢ）估计，此处αａ×１是效应参数向量，Ｐａ×ｋ是常数矩阵．在较一般的条件下，基于均方误差矩阵准则和ＰｉｔｍａｎＣｌｏｓｅｎｅｓｓ准则。
In the one way ANOVA model, we construct the linear Bayes and empirical Bayes (EB) estimators of P′α, where α is an a×1 vector of effect parameters and P is an a×k matrix with constant elements. Under general conditions, we prove that the EB estimator is better than Least Square (LS) estimator in terms of the mean square error matrix (MSE M) criterion and Pitman closeness (PC) criterion respectively.
出处
《高校应用数学学报（A辑）》
CSCD
北大核心
1997年第2期163-174,共12页
Applied Mathematics A Journal of Chinese Universities(Ser.A)
基金
国家自然科学基金
国家教委博士点基金
关键词
方差分析模型
均方误差
经验贝叶斯估计
优良性
One way ANOVA Model, Bayes and Empirical Bayes Estimation, Least Square Estimation, Mean Square Error Matrix Criterion, Pitman Closeness Criterion.
