生长曲线模型中参数的Bayes线性无偏估计

The Superiority of Bayes Linear Unbiased Estimation in the Growth Curve Model

摘要: 本文在平方损失下导出了生长曲线模型中参数的Bayes线性无偏估计(LUE), 并在均方误差矩阵(MSEM)准则下研究了Bayes LUE相对于广义最小二乘估计(GLSE)的优良性. 对于非满秩情形, 获得了可估函数的Bayes LUE并讨论了其优良性问题.

Abstract: Under quadratic loss function, the Bayes linear unbiased estimator (LUE) is derived for the growth curve model. The superiority of Bayes LUE over the generalized least square estimator (GLSE) is studied in terms of the mean square error matrix (MSEM) criterion. Finally, the superiority of the Bayes LUE of estimable functions for non-full rank case is considered further.