ESTIMATION, LARGE-SAMPLE PARAMETRIC TESTS AND DIAGNOSTICS FOR NONEXPONENTIAL FAMILY NONLINEAR MODELS

被引:6
|
作者
CORDEIRO, GM
PAULA, GA
机构
[1] INST MATEMATICA PURA & APLICADA,CNPQ,BR-22460 RIO DE JANEIRO,BRAZIL
[2] UNIV SAO PAULO,IME,BR-01498 SAO PAULO,BRAZIL
关键词
ADDED VARIABLE; BARTLETT CORRECTION; DEVIANCE; DISPERSION PARAMETER; EXPONENTIAL FAMILY; GLIM; INFLUENCE; INFORMATION MATRIX; NONEXPONENTIAL MODEL; OFFSET; RESIDUAL; SCORE STATISTIC; WALD STATISTIC;
D O I
10.1080/03610919208813012
中图分类号
O21 [概率论与数理统计]; C8 [统计学];
学科分类号
020208 ; 070103 ; 0714 ;
摘要
We study large sample inference for the non-exponential family nonlinear models and show a simple procedure to fit these models in the GLIM regression package. We derive general expressions of three statistics (Wald, likelihood ratio and score) for testing a subset of parameters of interest, which may be implemented in GLIM. We review various diagnostics for generalized linear models and extend to more general models. Some examples of analysis of real data are provided.
引用
收藏
页码:149 / 172
页数:24
相关论文
共 50 条