期刊文献+

基于非参数回归的遗漏变量检验 预览 被引量:1

Nonparametric-regression-based testing for omitted variables
在线阅读 下载PDF
分享 导出
摘要 基于非参数回归提出了同时适用于横截面和时间序列数据的遗漏变量检验统计量.与现有文献相比,该统计量不仅避免了模型设定偏误问题,而且具有更高的局部检验功效,能够识别出速度更快的收敛到原假设的局部备择假设.该文选择单一带宽估计条件联合期望和条件边际期望,允许二者的非参数估计误差共同决定统计量的渐近分布,不仅改善了统计量的有限样本性质,而且避免了选择多个带宽和计算多个偏差项产生的繁杂工作.蒙特卡洛模拟结果表明该统计量具有良好的有限样本性质以及比Ait-Sahalia等更高的检验功效.实证分析采用该统计量捕获了F统计量无法识别的产出缺口与通胀之间关系,验证了非线性“产出一通胀”型菲利普斯曲线在中国的适用性。 This paper proposes a nonparametric-regression-based test for omitted variables, which is applicable in both cross-sectional and time series contexts. Our test not only avoids the model misspecification problem, Monte Carlo studies demonstrate the well behavior of our test in finite samples, which could not only capture the omitted variables feature in linear and nonlinear regressions, but also is more powerful than Ait-Sahalia et al. ' s (2001) test. In an application to testing the nonlinear Granger causality in mean, we document the existence of nonlinear relationships between theoutput gap and inflation, that is, the nonlinear "output-inflation" type of Phillips curve maybe is more suitable for China' s inflation forecast.
作者 王霞 洪永淼 WANG Xia, HONG Yong-miao(1. School of Economics and Management, University of Chinese Academy of Sciences, Beijing 100190, China; 2. Department of Economics and Department of Statistical Sciences, Cornell University, NY 14550, USA; 3. The Wang Yanan Institute for Studies in Economics (WISE), Xiamen University, Xiamen 361005, China)
出处 《管理科学学报》 CSSCI 北大核心 2016年第3期77-91,共15页 Journal of Management Sciences in China
基金 国家自然科学青年基金资助项目(71401160) 教育部人文社会科学研究青年基金资助项目(14YJC790120) 中国科学院大学校部教师与研究所科研合作专项基金资助项目.
关键词 遗漏变量 非参数回归 非线性 检验功效 均值格兰杰因果关系 omitted variable nonlinear nonparametric regression power Granger causality in mean
作者简介 王霞(1985-),女,山东济宁人,博士,讲师.Email:wangxia@ucas.ac.cn
  • 相关文献

参考文献29

  • 1Fan Y, Li Q. Consistent model specification tests: Omitted variables and semiparametric function forms[ J ]. Econometrica, 1996, 64(4) : 865 -890. 被引量:1
  • 2Lavergne P, Vuong Q. Nonparametric significance testing[ J ]. Econometric Theory, 2000, 16 (4) : 576 - 601. 被引量:1
  • 3Ait-Sahalia Y, Biekcl P J, Stocker T M. Goodness-of-fit tests for kernel regression with an application to option implied vola- tilities[J]. Journal of Econometrics, 2001, 105(2) : 363 -412. 被引量:1
  • 4Granger C W J. Investigating causal relations by econometric models and cross-spectral methods [ J]. Eeonometrica, 1969, 37(3) : 424 -438. 被引量:1
  • 5Bierens H J. Consistent model specification tests[ J]. Journal of Econometrics, 1982, 20( 1 ) : 105 -134. 被引量:1
  • 6Fan J, Gijbels I. Variable bandwidth and local linear regression smoothers[J]. Annals of Statistics, 1992, 20(4) :2008-2036. 被引量:1
  • 7Hastie T J, Loader C. Local regression : Automatic kernel carpentry (with discussion) [ J ]. Statistical Science, 1993, 8 (2) : 120 -143. 被引量:1
  • 8Hjellvik V, Yao Q, Tjostheim D. Linearity testing using local polynomial approximation [ J ]. Journal of Statistical Planning and Inference, 1998, 68(2) : 295 -321. 被引量:1
  • 9Chen B, Hong Y. Characteristic function-based testing for multifactor continuous-time Markov models via nonparametric re- gression[J]. Econometric Theory, 2010, 26(4) : 1115 -1179. 被引量:1
  • 10Su L, White H. A consistent characteristic function-based test for conditional independence[J]. Journal of Econometrics, 2007, 141(2) : 807 -834. 被引量:1

二级参考文献78

共引文献204

同被引文献11

引证文献1

投稿分析

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部 意见反馈