event-study analysis

This paper addresses the identification challenge of time-varying and cross-group heterogeneous treatment effects in event study designs, where lagged dependent variables induce omitted-variable bias and conventional assumptions of effect homogeneity and no anticipation are restrictive. We propose a semiparametric two-step estimator based on short-𝑇 dynamic linear panel models: first, quasi-maximum likelihood estimation of common parameters; second, empirical Bayes recovery of individual-level heterogeneous treatment effect trajectories. By explicitly modeling the lagged dependent variable and temporal dependence structure, our method flexibly accommodates state dependence, anticipatory behavior, and dynamic heterogeneity while preserving asymptotic rate optimality. Relative to leading alternatives—including standard two-way fixed-effects and interactive fixed-effects approaches—our estimator delivers substantially improved accuracy and robustness in inferring time-varying treatment effects. The framework provides a novel, theoretically grounded tool for policy evaluation and causal inference in dynamic settings.

This study addresses the frequent conflation in event studies between the direct effect of a treatment and indirect effects arising from adjustments through endogenous covariates. The authors develop a dynamic panel event study framework that, under assumptions of sequential exogeneity and homogeneous feedback, achieves point identification of key parameters governing outcome dynamics, the distribution of heterogeneous treatment effects, and the covariate feedback process. They further propose a dynamic decomposition algorithm to quantify the relative contributions of direct and indirect effects. By explicitly modeling persistence in treatment effects and allowing covariates to respond to both past outcomes and treatment exposure, the method cleanly disentangles direct from indirect causal pathways, offering a more precise tool for causal inference in event study settings.

This paper addresses the identification of dynamic treatment effects in panel data with non-binary, non-absorbing treatments. Under no-anticipation and generalized parallel-trends assumptions, it identifies event-study effects by contrasting observed treatment paths with a “maintain-initial-state” counterfactual path. It further proposes a random-coefficient distributed-lag model to estimate the marginal dynamic policy impact. Unlike conventional two-way fixed-effects estimators—which impose restrictive assumptions on treatment timing and absorption—the method cleanly separates actual policy effects from extrapolated counterfactuals under unimplemented policies. Integrating regression adjustment with weight normalization, the approach is empirically validated using Gentzkow et al. (2011) data, accurately recovering both immediate and lagged effects. The framework enhances interpretability and applicability for evaluating complex, evolving policies, particularly those featuring gradual, reversible, or heterogeneous treatment adoption.

This study addresses the failure of conventional two-way fixed effects (TWFE) models in estimating treatment effects for repeated events, where disentangling the independent dynamic impacts of individual occurrences remains challenging. Focusing on recurrent shocks such as natural disasters, this work proposes a linear parametric framework grounded in a conditional parallel trends assumption based on effect accumulation. Inference is conducted using a sequential imputation estimator combined with Monte Carlo simulations. The proposed approach achieves robust and consistent estimation of the dynamic effects associated with single events, effectively recovering the aggregate trajectory while precisely isolating the independent impact of each shock. Simulation experiments further validate the superiority of this methodology over existing alternatives.

This paper addresses the nonparametric identification challenge of causal effects in high-frequency event studies. It argues that narrow time windows alone are insufficient for valid causal interpretation and introduces two novel identifying conditions: “relative exogeneity” and “separability.” The paper proves that standard linear event-study regression coefficients possess causal interpretation only when policy shocks exhibit infinite variance. Building on nonparametric identification theory, high-dimensional asymptotic inference, and high-frequency time-series modeling, it establishes consistency and asymptotic normality of event-study estimators—even for nonlinear transformations of the outcome variable. The framework is robust to functional form misspecification and provides the first operational causal validation methodology for empirical analyses such as Nakamura & Steinsson (2018). By unifying identification, estimation, and inference under high-frequency settings, this work significantly advances the methodological foundations of causal inference in macroeconomics and political economy.

研究在动态选择下处理时变协变量和潜在异质性对因果推断的影响，通过预处理结果历史识别相似个体，并提出基于核的双重稳健估计方法来解决动态平均处理效应的识别问题。

本文提出一种在无随机实验条件下通过自然发生的营销干预来测量广告增量效果的方法，采用两阶段程序，包括发现干预和因果影响分析。

This study addresses the challenge of estimating the causal effect of longitudinal treatment strategies on survival outcomes using electronic health records, where monitoring frequency of covariates varies across patients, variable types, and time, and may itself carry information about underlying health status—potentially biasing conventional causal inference methods. For the first time, monitoring indicators are formally treated as time-varying confounders. The authors integrate inverse probability weighting, G-computation, and longitudinal targeted maximum likelihood estimation (TMLE) to develop a unified framework for causal effect estimation under informative monitoring. This approach substantially reduces bias arising from ignoring the monitoring mechanism and extends the applicability of both static and dynamic treatment strategies. Simulations confirm its validity, and an application to real-world ICU data demonstrates its ability to accurately assess the impact of different mechanical ventilation initiation strategies on mortality.

该文介绍R包tteICE，通过实施五种策略解决临床试验中因并发事件导致的时间到事件结果的治疗效果评估问题。

This study addresses the challenges in estimating the causal effect of antihypertensive strategies on recurrent acute kidney injury (AKI)—a recurrent event outcome—amid time-varying treatments, time-dependent confounding, and potential model misspecification. Leveraging data from the SPRINT trial, the authors propose a causal inference framework that integrates doubly robust estimation with adjustment for time-varying confounders, while explicitly accounting for medication adherence and death as a semi-competing risk. The approach effectively identifies the average causal effect of standard versus intensive blood pressure lowering on AKI recurrence. By combining model flexibility with robustness to misspecification, the method substantially enhances the reliability of causal conclusions and offers a novel paradigm for analyzing recurrent events in complex longitudinal settings.