观察值驱动的广义INAR(1)过程的经验似然推断  

Empirical Likelihood Inference for Observation-driven GINAR(1)Processes

作　　者：许晶 于梅菊 李淑文[1] Xu Jing;Yu Meiju;Li Shuwen(School of Mathematics and Statistics,Northeast Normal University,Changchun 130000,China;School of Mathematics,Tonghua Normal University,Tonghua Jilin 134000,China)

机构地区：[1]东北师范大学数学与统计学院,长春130000 [2]通化师范学院数学学院,吉林通化134000

出　　处：《统计与决策》2020年第14期10-14,共5页Statistics & Decision

基　　金：北京师范大学中国基础教育质量监测协同创新中心自主课题(2016-03-004-BZK01)。

摘　　要：整值时间序列分析作为时间序列分析的重要组成部分,被广泛地应用于社会生活的各个领域。文章提出了一类观察值驱动的广义INAR(l)过程,推导了该模型的概率统计性质,并利用经验似然的方法研究了该模型的参数估计问题,给出了模型参数的极大经验似然估计量及其渐近分布。通过一系列的仿真实验,验证了经验似然方法的有效性。最后利用所提出的模型拟合了一组犯罪数据。As an important part of time series analysis,the analysis of integer-valued time series is widely used in various fields of social life.This paper proposes a class of generalized INAR(1)processes driven by observation value,derives the probabilistic properties of the model,and also uses the empirical likelihood method to study the parameter estimation of the model,presenting the maximum empirical likelihood estimator and its asymptotic distribution of model parameters.And the effectiveness of the empirical likelihood method is verified by a series of simulation experiments.Finally,the proposed model is used to fit a set of crime data.

关 键 词：整值时间序列模型 观察值驱动的广义INAR(1)过程 条件最小二乘估计 经验似然估计 

分 类 号：O212.7[理学—概率论与数理统计]