摘要
面板数据政策评价方法(HCW)是一种常用的政策效果估计方法,然而其关于变量之间线性关系的基本设定与社会经济的复杂现实不符。为解决非线性情况下HCW的适用性问题,文章将HCW中关于变量之间关系的设定从线性形式扩展为非线性形式,构造非线性面板数据政策评价模型(NLHCW)。进一步地,构建相关检验方法,并将LASSO引入NLHCW,以提升NLHCW使用的便利性以及政策影响估计量的有效性。数学证明和模拟研究显示,运用NLHCW得到的政策影响估计量在非线性情况下具有无偏性、一致性和渐近正态性;通过实证分析,进一步验证了NLHCW模型的适用性和有效性。
The panel data policy evaluation method(HCW)is a commonly used method for estimating policy effects.However,its basic setting regarding the linear relationship between variables does not conform to the complex reality of the social economy.To solve the applicability of HCW in nonlinear cases,this paper expands the relationship settings among variables in HCW from a linear form to a nonlinear form,and constructs a nonlinear panel data policy evaluation model(NLHCW).Furthermore,the paper develops relevant testing methods and introduces LASSO into NLHCW,thereby enhancing the usability of NLHCW and the validity of policy affecting estimators.Mathematical proofs and simulation studies show that the policy impact estimator estimated by the NLHCW remains unbiased,consistent,and asymptotically normal under nonlinear conditions.The empirical analysis further validates the applicability and effectiveness of the NLHCW model.
作者
陈翔
孙乐
刘亚楠
Chen Xiang;Sun Le;Liu Yanan(School of Statistics and Data Science,Xi’an University of Finance and Economics,Xi’an 710100,China;Center of Journal Management,Xi’an University of Finance and Economics,Xi’an 710100,China)
出处
《统计与决策》
北大核心
2025年第15期24-28,共5页
Statistics & Decision
基金
国家社会科学基金青年项目(22CTJ002)。
