4.5 Article

Identifying and estimating effects of sustained interventions under parallel trends assumptions

Related references

Note: Only part of the references are listed.
Article Economics

What's trending in difference-in-differences? A synthesis of the recent econometrics literature

Jonathan Roth et al.

Summary: This paper synthesizes recent advances in the econometrics of difference-in-differences (DiD) and provides concrete recommendations for practitioners. The authors articulate a set of canonical assumptions under which the econometrics of DiD are well-understood. They discuss how recent advances in DiD methods relax some components of the canonical DiD setup, highlighting different ways the DiD literature has advanced beyond the canonical model.

JOURNAL OF ECONOMETRICS (2023)

Article Economics

Difference-in-Differences with multiple time periods

Brantly Callaway et al.

Summary: This article discusses identification, estimation, and inference procedures for treatment effect parameters using the Difference-in-Differences (DiD) method, which is applicable to multiple time periods, variation in treatment timing, and when the parallel trends assumption holds potentially only after conditioning on observed covariates. The proposed methods allow for highlighting treatment effect heterogeneity across different dimensions and summarizing the overall effect of participating in the treatment.

JOURNAL OF ECONOMETRICS (2021)

Article Health Care Sciences & Services

Confounding and regression adjustment in difference-in-differences studies

Bret Zeldow et al.

Summary: In difference-in-difference studies, confounders are covariates that change differently over time in the treatment and comparison group, or have a time-varying effect on the outcome. Adjusting for these confounders appropriately, including them in a regression model consistent with the causal model, can provide unbiased estimates. However, recovering an unbiased causal effect using difference-in-differences becomes difficult when time-varying confounders are affected by treatment.

HEALTH SERVICES RESEARCH (2021)

Article Public, Environmental & Occupational Health

Impact Evaluation of Coronavirus Disease 2019 Policy: A Guide to Common Design Issues

Noah A. Haber et al.

Summary: The unprecedented scale and complexity of policy responses to COVID-19 present challenges in evaluating their impacts, with methodological complications making it difficult to synthesize and evaluate evidence. This article introduces common policy impact evaluation designs and highlights key violations in the context of COVID-19, aiming to help decision-makers and researchers understand and weigh the strengths and limitations of evidence.

AMERICAN JOURNAL OF EPIDEMIOLOGY (2021)

Article Economics

Difference-in-differences with variation in treatment timing

Andrew Goodman-Bacon

Summary: The paper explores the relationship between the two-way fixed effects estimator and all possible two-group/two-period DD estimators, showing that it is a weighted average. A causal interpretation of two-way fixed effects DD estimates requires meeting the parallel trends assumption and constant treatment effects over time.

JOURNAL OF ECONOMETRICS (2021)

Article Multidisciplinary Sciences

Stay-at-home orders associate with subsequent decreases in COVID-19 cases and fatalities in the United States

James H. Fowler et al.

Summary: The study found that in the first seven weeks of the COVID-19 outbreak in the United States, counties that implemented stay-at-home orders experienced a significant reduction in confirmed cases and fatalities, with the reductions becoming more pronounced over time.

PLOS ONE (2021)

Article Economics

The Role of Parallel Trends in Event Study Settings: An Application to Environmental Economics

Michelle Marcus et al.

Summary: This paper discusses the impact of parallel trends assumptions on the identification and estimation of causal effects in Difference-in-Differences (DID) research designs, finding a trade-off between robustness and efficiency based on the strength of the parallel trends assumption. New DID estimators reflecting this trade-off are proposed, and their large sample properties are derived.

JOURNAL OF THE ASSOCIATION OF ENVIRONMENTAL AND RESOURCE ECONOMISTS (2021)

Article Economics

Doubly robust difference-in-differences estimators

Pedro H. C. Sant'Anna et al.

JOURNAL OF ECONOMETRICS (2020)

Article Economics

Two-Way Fixed Effects Estimators with Heterogeneous Treatment Effects

Clement De Chaisemartin et al.

AMERICAN ECONOMIC REVIEW (2020)

Article Mathematical & Computational Biology

Double Robust Efficient Estimators of Longitudinal Treatment Effects: Comparative Performance in Simulations and a Case Study

Linh Tran et al.

INTERNATIONAL JOURNAL OF BIOSTATISTICS (2019)

Article Statistics & Probability

Analysis of longitudinal data with drop-out: objectives, assumptions and a proposal

Peter Diggle et al.

JOURNAL OF THE ROYAL STATISTICAL SOCIETY SERIES C-APPLIED STATISTICS (2007)

Article Public, Environmental & Occupational Health

Estimating causal effects

G Maldonado et al.

INTERNATIONAL JOURNAL OF EPIDEMIOLOGY (2002)

Article Statistics & Probability

The calculus of M-estimation

LA Stefanski et al.

AMERICAN STATISTICIAN (2002)

Article Public, Environmental & Occupational Health

Marginal structural models and causal inference in epidemiology

JM Robins et al.

EPIDEMIOLOGY (2000)