| 1,415 | 10 | 259 |
| 下载次数 | 被引频次 | 阅读次数 |
现有文献在利用处理效应模型评估政策时,模型中的假设条件局限性大多较强,在实际应用中很难验证,且一旦这些假设错误,就会引起参数估计的不一致。本文首先在非参数框架下提出了一种关于处理效应模型的半参数估计方法,其既不对模型中的函数形式做任何假定,也允许误差项的联合分布是广义异方差形式,从而大大减少因模型误设而引起的估计偏误。考虑到处理效应的内生性问题,提出了一个两步估计量。第一步关于选择方程进行非参数估计;第二步在结果方程中,利用工具变量法估计平均处理效应。其次,对估计量的大样本性质进行分析,表明了估计量的一致性和渐近正态性质。再次,通过蒙特卡罗模拟与已有估计方法进行比较,结果表明本文的方法具有较强的稳健性。最后,本文将该方法应用于研究高新技术企业认证政策对企业盈利能力影响,研究发现该政策提升了高新技术企业的盈利能力,并且相比于国有企业,该政策对民营企业促进效应更大。
Abstract：The assumptions are quite restrictive in the treatment effect model used by current literature on policy evaluation but difficult to verify in practice. Once the assumptions are mistaken,parameter estimation will be inconsistent. Firstly,this paper proposes a semi-parametric estimation method for treatment effect model under a non-parametric framework. In our model,we don't assume functional forms,and also allow the joint distribution of the error terms to be a general form of heteroscedasticity,which greatly reduces the risk of model misspecification.This paper considers treatment effect under endogeneity,and proposes a two-step approach. The first step uses a non-parametric estimator in the selection equation,and the second step uses an instrumental variables approach to estimate average treatment effect in the outcome equation. Secondly,the proposed estimator is shown to be consistent and asymptotically normally distributed. Furthermore,compared with the existing methods,the Monte Carlo simulation result shows our method is more robust. Finally,we apply our method to empirically estimate the impact of certification policy for high-tech enterprises on their profitability,and find this policy can help promote the profitability,and has a greater impact on private enterprises than state-owned enterprises.
[1]卢君生，张顺明，朱艳阳．高新技术企业认证能缓解融资约束吗?[J]．金融论坛，2018(1):52-65.
[2]黎文靖，郑曼妮．实质性创新还是策略性创新—宏观产业政策对微观企业创新的影响[J]．经济研究，2016(4):60-73.
[3]任曙明，张静．补贴、寻租成本与加成率—基于中国装备制造企业的实证研究[J]．管理世界，2013(10):118-129.
[4]孙早，席建成．中国式产业政策的实施效果:产业升级还是短期经济增长[J]．中国工业经济，2015(7):52-67.
[5]唐清泉，罗党论．政府补贴动机及其效果的实证研究—来自中国上市公司的经验证据[J]．金融研究，2007(6):149-163.
[6]许玲玲．高新技术企业认定、政治关联与民营企业技术创新[J]．管理评论，2017(9):84-94.
[7]杨国超，刘静，廉鹏，等．减税激励、研发操纵与研发绩效[J]．经济研究，2017(8):112-126.
[8]杨典．公司治理与企业绩效—基于中国经验的社会学分析[J]．中国社会科学，2014(1):72-94.
[9]周亚虹，蒲余路，陈诗一，等．政府扶持与新兴产业发展—以新能源为例[J]．经济研究，2015(6):147-161.
[10]Abadie A. Semiparametric Instrumental Variable Estimation of Treatment Response Models[J]. Journal of Econometrics,2003,113(2):231-263.
[11]Abrevaya J,Shin Y. Rank Estimation of Partially Linear Index Models[J]. Econometrics Journal,2011,14(3):409-437.
[12]Aghion P,Cai J,Dewatripont M,et al. Industrial Policy and Competition[J]. American Economic Journal:Macroeconomics,2015,7(4):1-32.
[13]Ahn H,Powell J L. Semiparametric Estimation of Censored Selection Models with a Nonparametric Selection Mechanism[J]. Journal of Econometrics,1993,58(1-2):3-29.
[14]Angrist J D. Treatment Effect Heterogeneity in Theory and Practice[J]. Economic Journal,2004,114(494):52-83
[15]Angrist J D,Krueger A B. Does Compulsory School Attendance Affect Schooling and Earnings?[J]. Quarterly Journal of Economics,1991,106(4):979-1014.
[16]Chen S. Distribution-Free Estimation of the Random Coefficient Dummy Endogenous Variable Model[J]. Journal of Econometrics,1999,91(1):171-199.
[17]Chen S,Khan S. Semiparametric Estimation of a Heteroskedastic Sample Selection Model[J]. Econometric Theory,2003,19(6):1040-1064.
[18]Chen S,Zhou Y. Semiparametric and Nonparametric Estimation of Sample Selection Models under Symmetry[J]. Journal of Econometrics,2010,157(1):143-150.
[19]Chernozhukov V,Hong H. Three-step Censored Quantile Regression and Extramarital Affairs[J]. Journal of American Statistical Association,2002,97(459):872-882.
[20]Frlich M,Melly B. Identification of Treatment Effects on the Treated with One-Sided Non-compliance[J]. Econometric Reviews,2013,32(3):384-414.
[21]Heckman J,Macurdy T E. Labor Econometrics[J]. Handbook of Econometrics,1986,3:1917-1977.
[22]Heckman J,Navarro-Lozano S. Using Matching,Instrumental Variables,and Control Functions to Estimate Economic Choice Models[J]. Review of Economics and Statistics,2004,86(1):30-57.
[23]Hirano K,Imbens G W,Ridder G. Efficient Estimation of Average Treatment Effects Using the Estimated Propensity Score[J].Econometrica,2003,71(4):1161-1189.
[24]Hong H,Nekipelov D. Semiparametric Efficiency in Nonlinear LATE Models[J]. Quantitative Economics,2010,1(2):279-304.
[25]Kyriazidou E. Estimation of a Panel Data Sample Selection Model[J]. Econometrica:Journal of the Econometric Society,1997:1335-1364.
[26]Newey W K. Kernel Estimation of Partial Means and a General Variance Estimator[J]. Econometric Theory,1994,10(2):1-21.
[27]Powell J L. Semiparametric Estimation of Bivariate Latent Variable Models[R]. Working Paper. Madison in WI:Social Research Institute,University of Wisconsin,1987.
[28]Powell J L,Stock J H,Stoker T M. Semiparametric Estimation of Index Coefficients[J]. Econometrica:Journal of the Econometric Society,1989:1403-1430.
[29]Zhou Y H,Wang L M,He X D. Semiparametric Estimation of Average Treatment Effect Through a Random Coefficient Dummy Endogenous Variable Model[J]. Science China Mathematics,2014,57(11):2415-2428.
(1)在维数较高时，非参数的有限样本性质较差，本文的模拟部分是在变量维数不高的情形下进行的，因此影响并不严重。在实证中，考虑到第一步估计所用变量维数相对较高，本文参照文献采取了序列展开(sieve)方法对倾向得分进行估计，事实上，sieve方法和非参数核估计方法在某种意义下是类似的，因此并不影响主要的理论结果。本文在第一步和第二步估计时均采取四阶高斯核函数，多维核函数计算时采用多个一维核函数的乘积。在第一步窗宽的选择中采取Cross-Validation(CV)法则，在第二步选择窗宽时，参考文献Abrevaya和Shin(2011)的窗宽选取法则。
(1)因篇幅所限，证明过程以附录展示，见《统计研究》网站所列附件。
(1)国家重点支持的八种高新技术领域包括:电子信息技术、生物与新医药技术、航空航天技术、新材料技术、高技术服务业、新能源及节能技术、资源与环境技术以及新技术改造传统产业。
(1)http://www. xinhuanet. com/politics/leaders/2018-11/01/c_1123649488. htm。
基本信息:
DOI：10.19343/j.cnki.11-1302/c.2020.09.010
中图分类号:O212.1;F276.44;F275;F224
引用信息:
[1]纪园园,李世奇,朱平芳.处理效应模型的理论拓展及在政策评价中的应用[J].统计研究,2020,37(09):106-119.DOI:10.19343/j.cnki.11-1302/c.2020.09.010.
基金信息:
国家自然科学基金青年项目“处理效应模型的非参数估计方法及其拓展应用”(71803134);国家自然科学基金面上项目“非线性动态因子模型和函数型时间序列的前沿理论及其应用”(71773078);国家自然科学基金青年项目“家庭债务，需求不足与经济增长—基于家庭流动性约束机制探讨”(71803118);; 上海社会科学院创新工程数量经济学学科团队建设项目
2020-08-25
2020-08-25
2020-08-25