数学物理学报 ›› 1997, Vol. 17 ›› Issue (1): 47-54.

• 论文 • 上一篇    下一篇

贝叶斯对数线性估计

陈拥君, 张尧庭   

  1. 武汉大学管理学院 430072
  • 收稿日期:1995-01-20 修回日期:1995-11-06 出版日期:1997-02-26 发布日期:1997-02-26

Bayesian log Linear Estimates for High-Way Contingency Tables

Chen Yongjun, Zhang Yaoting   

  1. Management School, Wuhan University Wuhan, P. R. China 430072
  • Received:1995-01-20 Revised:1995-11-06 Online:1997-02-26 Published:1997-02-26

摘要: 用Logits变换方法来讨论列联表的贝叶期估计,这时的估计称为贝叶斯对数线性估计,最早是由Lconard (1973,1975)提出的.Leonard讨论了二维表的对数线性贝叶斯估计;其后,Nazerat (1987)给出了三维表的贝叶斯对数线性估计.该文采用矩阵求微商方法,立足于高维表贝叶斯线性估计的较一般的表达形式;具体对四维表讨论员叶斯对数线性估计的表达和计算.

关键词: Logits变换, 列联表, 贝叶斯估计, 统计计算

Abstract: This paper presents a Bayes method to estimate the expected proportions for high-way contingency tables appropriate when prior knowledge about the interaction effects can be described by a particular kind of exchangeability assumption.We give the expressions of estimates for four-way contingency tables based on general expressions equations.It extends the work of Leonard (1975) and Nazaret(1987) and useful algorithm also discussed.

Key words: Logits transformation, contingency tables, Bayes estimates, statistical computation