Panel数据模型的参数bootstrap推断  

A parametric bootstrap inference for panel data model

作　　者：叶仁道[1] 姜玲 YE Ren-dao;JIANG Ling(College of Economics,Hangzhou Dianzi University,Zhejiang 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：《高校应用数学学报（A辑）》2018年第4期379-386,共8页Applied Mathematics A Journal of Chinese Universities(Ser.A)

基　　金：浙江省哲学社科规划"之江青年课题"(16ZJQN017YB);国家统计局重点项目(2015LZ14);国家自然科学基金(11401148);国家社会科学基金(12CJY012)

摘　　要：利用广义p值和参数bootstrap方法,研究了Panel数据模型中未知参数的假设检验问题.对于回归系数,基于最小二乘估计和两步估计方法,考虑了非齐次线性假设检验问题.对于方差分量,研究了单边假设检验问题.进而利用Monte Carlo方法进行模拟研究.模拟结果表明,参数bootstrap检验方法既能较好控制犯第一类错误的概率,又具有较高的功效,且大多数情况下优于广义p值检验方法.Using the approaches of generalized p-value and parametric bootstrap,the hypothesis testing problems of unknown parameters in panel data model are studied.For the regression coefficients,the non-homogeneous linear hypothesis testing problem is considered based on the least squares estimator and two-stage estimator.For the variance components,the one-sided hypothesis testing problem is studied.Then,the simulation studies are carried out by using the Monte Carlo method.The simulation results show that the parametric bootstrap approach not only can control the type I error probability e±ciently,but also has higher power,which is better than the generalized p-value approach in most cases.

关 键 词：最小二乘估计 两步估计 广义P值 参数bootstrap方法 

分 类 号：O212[理学—概率论与数理统计]