ROBUST NONPARAMETRIC CONFIDENCE INTERVALS FOR REGRESSION-DISCONTINUITY DESIGNS
ROBUST NONPARAMETRIC CONFIDENCE INTERVALS FOR REGRESSION-DISCONTINUITY DESIGNS
复制标题
DOI：
10.3982/ecta11757
复制
发表时间：
2014-11-01
期刊：
影响因子：
6.1
通讯作者：
Titiunik, Rocio
中科院分区：
文献类型：
--
作者：
Calonico, Sebastian;Cattaneo, Matias D.;Titiunik, Rocio
在回归-不连续性（RD）设计中，根据观察到的协变量值是否超过已知临界值，将单位分配给治疗。在这种设计中，局部多项式估计量现在通常用于构建治疗效果的置信区间。然而，这些置信区间在应用中的性能可能会受到其对所采用的特定带宽的敏感性的严重阻碍。可用带宽选择器通常会产生较大的带宽，导致数据驱动的置信区间可能存在偏差，经验覆盖率远低于其标称目标。我们提出了新的理论为基础的，更强大的置信区间估计平均治疗效果在截止尖锐的RD，尖锐的扭结RD，模糊RD，模糊扭结RD设计。我们建议的置信区间构造使用偏差校正的RD估计与一个新的标准误差估计。对于实际的实施，我们讨论均方误差的最佳带宽，这是由传统的置信区间，但我们的强大的方法是有效的建设，并一致的标准误差估计的基础上，我们的新的方差公式。在实际感兴趣的特殊情况下，我们的过程相当于运行二次而不是线性局部回归。更一般地说，我们的研究结果给出了一个正式的理由，简单的推理程序的基础上增加了当地多项式估计的顺序。我们发现，在模拟研究中，我们的置信区间表现出接近正确的经验覆盖率和良好的经验区间长度的平均值，显着改善的替代品在文献中。使用Calonico、Cattaneo和Titiunik（2014 d，2014 b）中描述的配套软件包，所有结果都可以在R和STATA中轻松获得。
In the regression-discontinuity (RD) design, units are assigned to treatment based on whether their value of an observed covariate exceeds a known cutoff. In this design, local polynomial estimators are now routinely employed to construct confidence intervals for treatment effects. The performance of these confidence intervals in applications, however, may be seriously hampered by their sensitivity to the specific bandwidth employed. Available bandwidth selectors typically yield a large bandwidth, leading to data-driven confidence intervals that may be biased, with empirical coverage well below their nominal target. We propose new theory-based, more robust confidence interval estimators for average treatment effects at the cutoff in sharp RD, sharp kink RD, fuzzy RD, and fuzzy kink RD designs. Our proposed confidence intervals are constructed using a bias-corrected RD estimator together with a novel standard error estimator. For practical implementation, we discuss mean squared error optimal bandwidths, which are by construction not valid for conventional confidence intervals but are valid with our robust approach, and consistent standard error estimators based on our new variance formulas. In a special case of practical interest, our procedure amounts to running a quadratic instead of a linear local regression. More generally, our results give a formal justification to simple inference procedures based on increasing the order of the local polynomial estimator employed. We find in a simulation study that our confidence intervals exhibit close-to-correct empirical coverage and good empirical interval length on average, remarkably improving upon the alternatives available in the literature. All results are readily available in R and STATA using our companion software packages described in Calonico, Cattaneo, and Titiunik (2014d, 2014b).