相依回归系统参数的Bayes估计  

Bayes Estimation of Parameters in Seemingly Unrelated Regression Model

作　　者：李胜宏[1] 周占功[2] 

机构地区：[1]江苏科技大学数理学院,江苏镇江212003 [2]嘉兴学院信息工程系,浙江嘉兴314001

出　　处：《江苏科技大学学报（自然科学版）》2006年第5期32-36,共5页Journal of Jiangsu University of Science and Technology:Natural Science Edition

摘　　要：在指定的先验信息下获得了相依回归系统参数的Bayes估计,并在均方误差阵准则下对与最小二乘估计和最优线性无偏估计进行了比较,讨论了在后验PC准则下相对于最小二乘估计的优良性。Under the specified prior assumption the Bayes estimation of the parameters in seemingly unrelated regression model is obtained. Based on the mean square error matrix criterion, the result is compared with the least square estimation and the optimal linear unbiased estimation. The superiority of Bayes estimation over the least square estimation is discussed on the posterior Pitman closeness criterion.

关 键 词：相依回归系统 BAYES估计 最优线性无偏估计 最小二乘估计 

分 类 号：O212.1[理学—概率论与数理统计]