偏正态单向分类随机效应模型中方差分量函数的Bootstrap推断  

Boot strap Inference of Variance Component Function in Skew-normal One-way Classification Random Effect Model

作　　者：叶仁道[1] 戚戬 YE Ren-dao;QI Jian(School of Economics,Hangzhou Dianzi University,Hangzhou 310018,China)

机构地区：[1]杭州电子科技大学经济学院,浙江杭州310018

出　　处：《数理统计与管理》2022年第2期309-321,共13页Journal of Applied Statistics and Management

基　　金：国家社会科学基金(21BTJ068);教育部人文社会科学研究项目(19YJA910006);浙江省自然科学基金(LY20A010019).

摘　　要：本文利用Bootstrap方法和广义方法,研究了偏正态单侖分类随机效应模型中方差分量函数的单边假设检验和区间估计问题。首先,分别基于Bootstrap方法和广义方法构造单个方差分量的检验统计量和置信区间。进而,探讨方差分量之和以及方差分量之比的单边假设检验和区间估计问题。Monte Carlo模拟结果表明,Bootstrap方法在大多数样本量和参数设置下优于广义方法。最后,将上述方法应用于中国人口出生率的案例分析,以验证本文所给方法的合理性与有效性。In this paper,the Bootstrap method and generalized method are used to study the one-sided hypo thesis testing and interval estimation,problems of the variance component function in the skewnormal one-way classification random effect model.Firstly,the test statistics and confidence intervals for a single variance component based on the Eootstrap method and generalized method respectively are constructed.Furthermore,the one-sided hypothesis testing and interval estimation problems of the sum of variance components and ratio of variance components are discussed.Monte Carlo simulation results show that the Bootstrap method is superior to the generalized method under most sample sizes and parameter settings.Finally,the above approaches are applied to the example of China's population birth rate to verify the rationality and validity of the proposed ones.

关 键 词：偏正态单向分类随机效应模型 方差分量函数 BOOTSTRAP 广义方法 

分 类 号：O212[理学—概率论与数理统计] O212.1[理学—数学]