摘要
本文对非线性随机效应模型 ,建立了微分几何框架 ,推广了 Bates &Wates关于非线性模型几何结构 .在此基础上 ,我们导出了关于固定效应参数和子集参数的置信域的曲率表示 ,这些结果是 Bates and Wates( 1 980 ) ,Hamilton( 1 986 )与 Wei( 1 994)等的推广 .
In this paper, we propose a differential geometric framework for nonlinear models with random effects. Our framework may be regarded as an extension of that presented by Bates & watts for nonlinear regression models. As an application, we use this geometric framework to derive three kinds of improved approximate confidence regions for parameter and parameter subset of fixed effect in terms of curvatures.
出处
《应用数学》
CSCD
2000年第4期100-105,共6页
Mathematica Applicata
基金
The Project supported by NSFC( 196 310 40 )
the grant of YZU
关键词
非线性随机效应模型
置信域
几何结构
Confidence regions
Curvature array
Fisher information
Score function
Nonlinear models with random effects
