双因素效应的动态二值logit模型的参数估计及应用  

Parameter Estimation and Application of Dynamic Binary Logit Model With Two-way Effect

作　　者：刘常彪 何庆光[1] 王新军 Liu Changbiao;He Qingguang;Wang Xinjun(China-ASEAN School of Statistics,Guangxi University of Finance and Economics,Nanning 530007,China)

机构地区：[1]广西财经学院中国-东盟统计学院,南宁530007

出　　处：《统计与决策》2023年第13期40-44,共5页Statistics & Decision

基　　金：统计学广西一流学科建设项目(X1211900408009);内蒙古自治区自然科学基金面上项目(2022MS01007);广西财经学院高层次人才项目(X2221610009);内蒙古师范大学高层次人才项目(2020YJRC055)。

摘　　要：文章考虑了带有个体效应和时间效应的双因素面板数据动态二值logit模型,在周期T固定的条件下,提出了一种新的方法估计模型参数。从理论层面指出了该估计量满足一致性和渐近正态性;数值模拟研究了估计量的小样本性质,模拟结果表明,该估计方法在有限样本下具有良好的统计性质。最后,将该方法应用于洗涤剂的购买数据进行实证分析。This paper considers a dynamic binary Logit model for two-way panel data with individual effect and time effect,and proposes a new method for estimating model parameters under the condition that the period T is fixed.Then from the theoretical point of view,the paper points out that the estimator satisfies consistency and asymptotic normality,studying the small sample property of the estimator by numerical simulation.The simulation results show that the estimation method has good statistical properties under limited samples.Finally,the proposed method is applied to detergent purchase data for empirical analysis.

关 键 词：个体效应 面板数据 动态logit模型 双因素模型 

分 类 号：O212.1[理学—概率论与数理统计]