����һ��Э����ṹ����������ģ�͵�reference����

Reference分析最早由Bernardo(1979)提出的,Berger和Bernardo(1992a)做了进一步的发展.而Berger 等(2001)提出了一个获得精确reference先验的方法,它已经成为获取无信息先验的最成功的方法之一.本文基于Berger等(2001)所提出的的算法,研究了具有一般协方差结构的增长曲线模型的reference先验.同时, 给出了相应结果的一些应用.

Reference Priors for the Growth Curve Model with General Covariance Structures

Reference analysis was first introduced byBernardo (1979) and further developed by Berger and Bernardo (1992a).Berger et al.(2001) proposed a new method to obtain exact referencepriors, which is proved to be one of the most successful methods toderive noninformative prior distributions. In this paper, the algorithmproposed in Berger et al.(2001) is used to obtain reference priorsfor the growth curve model with general covariance structures.Simultaneously, some applications of the corresponding results arepresented.