arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2003.13803econ.EMstat.ME
收藏

使用双重投影的广义倾向得分设定检验

Specification tests for generalized propensity scores using double projections

Pedro H. C. Sant'Anna, Xiaojun Song

AI总结:

本文提出基于双重投影的非参数设定检验方法,适用于含大量协变量的广义倾向得分模型及单指标型模型,对冗余参数估计方法渐近不变,并能以参数速率探测局部备择假设。

摘要:

本文基于条件矩约束,针对模型的正确设定提出一类新的非参数检验,并特别关注广义倾向得分模型。该检验程序建立在两种不同的投影论证之上,由此得到的检验统计量适用于包含大量协变量的设定,并且(渐近地)不受用于估计冗余参数的估计方法影响。我们证明所提出的检验能够探测到以通常的参数速率收敛到原假设的一大类局部备择假设,并通过模拟展示其良好的功效性质。我们还将所提方法扩展至检验参数或半参数单指标型模型。

英文摘要:

This paper proposes a new class of nonparametric tests for the correct specification of models based on conditional moment restrictions, paying particular attention to generalized propensity score models. The test procedure is based on two different projection arguments, leading to test statistics that are suitable to setups with many covariates, and are (asymptotically) invariant to the estimation method used to estimate the nuisance parameters. We show that our proposed tests are able to detect a broad class of local alternatives converging to the null at the usual parametric rate and illustrate its attractive power properties via simulations. We also extend our proposal to test parametric or semiparametric single-index-type models.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑