Prediction Intervals for Synthetic Control Methods.

Prediction Intervals for Synthetic Control Methods.
复制标题

DOI:
10.1080/01621459.2021.1979561
复制
发表时间:
2021
影响因子:
3.7
通讯作者:
Titiunik, Rocio
Titiunik, Rocio
中科院分区:
数学1区
文献类型:
--
作者:
Cattaneo, Matias D.;Feng, Yingjie;Titiunik, Rocio

文献摘要

参考文献

被引文献

相似文献

不确定性量化是综合控制(SC)方法分析和解释中的一个基本问题。我们在SC框架中发展了条件预测区间,并给出了这些区间提供有限样本概率保证的条件。我们的方法允许协变量调整和非平稳数据。首先指出,SC预测的统计不确定性由两个不同的随机性来源控制:一个来自前处理期间SC权重的构建(可能被错误指定),另一个来自后处理期间在分析处理效果时的不可观察的随机误差。因此,我们建议的预测区间是在考虑两个随机性来源的情况下构建的。在实现上,我们提出了一种基于模拟的方法和基于有限样本的概率界限论证,自然地产生了原则性的灵敏度分析方法。我们使用经验应用和一个小的模拟研究来说明我们的方法的数值性能。实现我们的方法的Python、R和Stata软件包现已可用。
Uncertainty quantification is a fundamental problem in the analysis and interpretation of synthetic control (SC) methods. We develop conditional prediction intervals in the SC framework, and provide conditions under which these intervals offer finite-sample probability guarantees. Our method allows for covariate adjustment and non-stationary data. The construction begins by noting that the statistical uncertainty of the SC prediction is governed by two distinct sources of randomness: one coming from the construction of the (likely misspecified) SC weights in the pre-treatment period, and the other coming from the unobservable stochastic error in the post-treatment period when the treatment effect is analyzed. Accordingly, our proposed prediction intervals are constructed taking into account both sources of randomness. For implementation, we propose a simulation-based approach along with finite-sample-based probability bound arguments, naturally leading to principled sensitivity analysis methods. We illustrate the numerical performance of our methods using empirical applications and a small simulation study. Python, R and Stata software packages implementing our methodology are available.
DOI: 10.1080/01621459.2021.1979562
发表时间: 2021
影响因子: 3.7
作者:
Kellogg, Maxwell;Mogstad, Magne;Pouliot, Guillaume A.;Torgovitsky, Alexander
通讯作者: Torgovitsky, Alexander
DOI: 10.1080/01621459.2021.1967163
发表时间: 2021-09-17
影响因子: 3.7
作者:
Bai, Jushan;Ng, Serena
通讯作者: Ng, Serena
DOI: 10.1080/01621459.2021.1920957
发表时间: 2021-05-30
影响因子: 3.7
作者:
Chernozhukov, Victor;Wuthrich, Kaspar;Zhu, Yinchu
通讯作者: Zhu, Yinchu
DOI: 10.1080/01621459.2021.1965613
发表时间: 2021-09-17
影响因子: 3.7
作者:
Ferman, Bruno
通讯作者: Ferman, Bruno
DOI: 10.1002/jae.1230
发表时间: 2012-08-01
影响因子: 2.1
作者:
Hsiao, Cheng;Ching, H. Steve;Wan, Shui Ki
通讯作者: Wan, Shui Ki