学术
离散型广义非线性纵向数据模型中偏离名义离差的检验及其功效模拟
林金官[1,2] 韦博成[1] 傅珏生[3]
[1]东南大学数学系,江苏南京210096 [2]江苏教育学院数学系,江苏南京210013 [3]苏州大学数学科学学院,江苏苏州215006
摘 要:
离散型广义非线性模型包括Poisson，二项，负二项模型．本文讨论离敞型广义非线性纵向数据模型中偏离名义离差的检验问题，得到了检验的score统计量，并利用Monte Carlo方法研究了检验统计靖的性质．最后，利用杀虫剂数据说明了检验方法的应用．[著者文摘]
文章出处:
《应用数学》-2006年19卷2期 -342-347页
分 类 号:
文献标识码:
A
文章编号:
1001-9847（2006）02-0342-06
Testing for Departures from Nominal Dispersion and Power Simulations in Discrete Generalized Nonlinear Models with Longitudinal Data
LIN Jin-guan, WEI Bo-cheng, FU Jue-sheng （1. Dept. of Math. , Southeast University, Nanjing 210096, China; 2. Dept. of Math. , Jiangsu Institute of Education , Nanjing 210013 , China ; 3. Dept. of Math. , Suzhou University , Suzhou 215006 , China ）
Abstract:
Discrete exponential family nonlinear models include Poisson, binomial, and negative binomial models. This paper discusses the test for departures from nominal dispersion in the framework of discrete generalized nonlinear models with random effects for longitudinal data. The score test statistic is constructed, The properties of test statistic are investigated through Monte Carlo simulations. We illustrate our test method by the insecticide data.[著者文摘]
Key words:
Longitudinal data; Generalized nonlinear models; Nominal dispersion; Score test;Simulated power;Random effects
基金资助:
Supported by NSFC （ 10371016）, SSFC （ 04BTJ002）, NSSPFC （ LXZ0415 ） and the Post-Doctorial Grant in Southeast University
更多>>免费文章
cqvip.com