arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2112.08092econ.EM
收藏

基于协变量的工具变量有效性检验

Testing Instrument Validity with Covariates

Thomas Carr, Toru Kitagawa

AI总结:

针对带条件协变量的异质性处理效应模型,提出基于半参数依赖假设检验工具变量识别假设的新方法,通过联合检验偏残差子密度的等式与不等式约束并引入蒸馏方法提升检验效力。

摘要:

针对带有条件协变量的异质性处理效应模型,我们开发了一种检验工具变量识别假设的新方法。我们假设潜在结果与条件协变量之间存在半参数依赖关系。这使我们能够在可估计的偏残差的子密度之间获得可检验的等式与不等式约束。我们提议联合检验这些约束。为提高检验效力,我们引入了蒸馏方法,即使用截断样本检验不等式约束。在Monte Carlo实验中,我们发现联合检验约束和蒸馏能提升有限样本的检验效力。我们将该检验程序应用于三个工具变量,并拒绝了其中一个的原假设。

英文摘要:

We develop a novel test of the instrumental variable identifying assumptions for heterogeneous treatment effect models with conditioning covariates. We assume semiparametric dependence between potential outcomes and conditioning covariates. This allows us to obtain testable equality and inequality restrictions among the subdensities of estimable partial residuals. We propose jointly testing these restrictions. To improve power, we introduce distillation, where a trimmed sample is used to test the inequality restrictions. In Monte Carlo exercises we find gains in finite sample power from testing restrictions jointly and distillation. We apply our test procedure to three instruments and reject the null for one.

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。

↑