增长曲线模型(一般协方差结构)的Bayes影响分析(英文)

Bayesian Influence Assessments in a Growth Curve Model with General Covariance Structure

本文讨论具有一般协方差结构的增长曲线模型中未知参数矩阵的Ｂａｙｅｓ影响分析问题．在无信息先验分布假设下，Ｋ－Ｌ距离被用来评估指定响应阵对参数矩阵的后验分布的影响程度．

The problem considered here is to assess the Bayesian influence on the unknown param- eter matrices in a grwoth curve model with the general covariance structure. Under the non- information prior distribution assumption, the Kullback-Leibler divergence is employed to eval- uate the effect of a designated response matrix on the posterior distribution of the parameter matrix