Estimating dynamic treatment effects in event studies with heterogeneous treatment effects

By S. Abraham, Liyang Sun. Journal of Econometrics, 2018

3,974 citations recorded by the source corpus.

Event studies are frequently used to estimate average treatment effects on the treated (ATT). In estimating the ATT, researchers commonly use fixed effects models that implicitly assume constant treatment effects across cohorts. We show that this is not an innocuous assumption. In fixed effect models where the sole regressor is treatment status, the OLS coefficient is a non-convex average of the heterogeneous cohort-specific ATTs. When regressors containing lags and leads of treatment are added, the OLS coefficient corresponding to a given lead or lag picks up spurious terms consisting of treatment effects from other periods. Therefore, estimates from these commonly used models are not causally interpretable. We propose alternative estimators that identify certain convex averages of the cohort-specific ATTs, hence allowing for causal interpretation even under heterogeneous treatment effects. To illustrate the empirical content of our results, we show that the fixed effects estimators and our proposed estimators differ substantially in an application to the economic consequences of hospitalization.

Subfields: Statistics and Probability

View Paper: https://www.semanticscholar.org/paper/3321239d27f986ef27494d3a6f6f8bbfdfcc9e00

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Statistics and Probability

Citations in the corpus

What’s trending in difference-in-differences? A synthesis of the recent econometrics literature (2022, positive): “An important implication of the results derived by Sun and Abraham (2021) is that if treatment effects are heterogeneous, the ‘‘treatment lead’’ coefficients from (7) are not guaranteed to be zero even if parallel trends is satisfied in all periods (and vice versa), and thus evaluation of…”
Difference-in-Differences with multiple time periods (2018, methodology): “Alternatively, one could use the interacted two-way fixed effects regression proposed by Sun and Abraham (2020).”
Assessing the Effectiveness of Energy Efficiency Measures in the Residential Sector Gas Consumption Through Dynamic Treatment Effects: Evidence from England and Wales (2022, background): “…these quasi-experimental design as they assume that the treatment effect is constant, between groups and overtime (de Chaisemartin and D ’ Haultfoeuill, 2020; de Chaisemartin and d ’ Haultfoeuille, 2021; Callaway and Sant ’ Anna, 2021; Sun and Abraham, 2021; Roth et al., 2022; Goodman-Bacon, 2021).”
Contamination Bias in Linear Regressions (2021, neutral): “…weighting and contamination bias issues documented previously in the context of two-way fixed effects regressions (e.g., Goodman-Bacon, 2021; Sun & Abraham, 2021; de Chaisemartin & D’Haultfœuille, 2020, 2022; Callaway & Sant’Anna, 2021; Borusyak et al., 2022; Wooldridge, 2021; Hull, 2018b)…”
How Much Should We Trust Staggered Difference-In-Differences Estimates? (2021, positive): “Sun and Abraham (2020) focuses on the “cohortspecific average treatment effects on the treated” (CATT ), k periods from initial treatment, which is conceptually similar to ATT (g, t) of Callaway and Sant’Anna (2020). The key theoretical result in this paper is that, even when using an event-study es”