arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2401.03293econ.EM
收藏

因子模型中的反事实

Counterfactuals in factor models

Jad Beyhum

AI总结:

提出基于公共因子的新模型,利用主成分分析估计特定时间和单位的平均边际效应,适用于高维时间序列与大型面板,并推导了渐近分布,在收入不平等实证中验证了方法有效性。

摘要:

我们研究了一种新模型,其中对应于(可能连续的)处理值的潜在结果通过公共因子联系起来。这些因子可以使用回归因子面板进行估计。我们提出了一种在此背景下估计特定时间和特定单位平均边际效应的程序。我们的方法既适用于高维时间序列,也适用于大型面板。它允许处理效应在时间和单位上存在异质性,并且由于仅依赖于主成分分析和基本计算,因此易于实现。我们推导了平均边际效应估计量的渐近分布,并通过模拟练习突出了其稳健的有限样本性能。该方法也可用于估计平均反事实,或适应于工具变量设置,我们对此进行了讨论。最后,我们通过关于收入不平等的实证应用说明了我们的新方法。

英文摘要:

We study a new model where the potential outcomes, corresponding to the values of a (possibly continuous) treatment, are linked through common factors. The factors can be estimated using a panel of regressors. We propose a procedure to estimate time-specific and unit-specific average marginal effects in this context. Our approach can be used either with high-dimensional time series or with large panels. It allows for treatment effects heterogenous across time and units and is straightforward to implement since it only relies on principal components analysis and elementary computations. We derive the asymptotic distribution of our estimator of the average marginal effect and highlight its solid finite sample performance through a simulation exercise. The approach can also be used to estimate average counterfactuals or adapted to an instrumental variables setting and we discuss these extensions. Finally, we illustrate our novel methodology through an empirical application on income inequality.

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。

↑