mlsanityData to 7 Oct 2026

A Semiparametric Instrumented Difference-in-Differences Approach to Policy Learning

arXiv 2310.09545 ↗First posted 14 Oct 2023stat.ME econ.EM math.STcited by 0

Not on the map. Why?

Abstract (arXiv)

Recently, there has been a surge in methodological development for the difference-in-differences (DiD) approach to evaluate causal effects. Standard methods in the literature rely on the parallel trends assumption to identify the average treatment effect on the treated. However, the parallel trends assumption may be violated in the presence of unmeasured confounding, and the average treatment effect on the treated may not be useful in learning a treatment assignment policy for the entire population. In this article, we propose a general instrumented DiD approach for learning the optimal treatment policy. Specifically, we establish identification results using a binary instrumental variable (IV) when the parallel trends assumption fails to hold. Additionally, we construct a Wald estimator, novel inverse probability weighting (IPW) estimators, and a class of semiparametric efficient and multiply robust estimators, with theoretical guarantees on consistency and asymptotic normality, even when relying on flexible machine learning algorithms for nuisance parameters estimation. Furthermore, we extend the instrumented DiD to the panel data setting. We evaluate our methods in extensive simulations and a real data application.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 26 of its 63 references that are in the map. First posted on arXiv 14 Oct 2023.

Builds on

26 of 63 references.

References · 26

  1. 2016Generalized Random Forestscited by 309
  2. 2019Confidence Intervals for Policy Evaluation in Adaptive Experimentscited by 95
  3. 2018Confounding-Robust Policy Improvementcited by 73
  4. 2021Sensitivity Analysis of Individual Treatment Effects: A Robust Conformal Inference Approachcited by 62
  5. 2020Semiparametric proximal causal inferencecited by 58
  6. 2019Learning When-to-Treat Policiescited by 49
  7. 2020Fast Rates for Contextual Linear Optimizationcited by 43
  8. 2016The State of Applied Econometrics - Causality and Policy Evaluationcited by 41
  9. 2022Doubly Robust Distributionally Robust Off-Policy Evaluation and Learningcited by 34
  10. 2022Off-Policy Confidence Interval Estimation with Confounded Markov Decision Processcited by 31
  11. 2016Bounded, efficient and multiply robust estimation of average treatment effects using instrumental variablescited by 23
  12. 2019A semiparametric instrumental variable approach to optimal treatment regimes under endogeneitycited by 22
14 more
  1. 2021Proximal Learning for Individualized Treatment Regimes Under Unmeasured Confoundingcited by 21
  2. 2022An Instrumental Variable Approach to Confounded Off-Policy Evaluationcited by 20
  3. 2022What's Trending in Difference-in-Differences? A Synthesis of the Recent Econometrics Literaturecited by 18
  4. 2020Estimating Optimal Treatment Rules with an Instrumental Variable: A Partial Identification Learning Approachcited by 17
  5. 2019Policy Targeting under Network Interferencecited by 12
  6. 2022Learning from a Biased Samplecited by 12
  7. 2015Using Decision Lists to Construct Interpretable and Parsimonious Treatment Regimescited by 11
  8. 2023Efficient and robust transfer learning of optimal individualized treatment regimes with right-censored survival datacited by 5
  9. 2020Selecting and ranking individualized treatment rules with unmeasured confoundingcited by 4
  10. 2020General Identification of Dynamic Treatment Regimes Under Interferencecited by 2
  11. 2022Structural mean models for instrumented difference-in-differencescited by 2
  12. 2020A Negative Correlation Strategy for Bracketing in Difference-in-Differencescited by 1
  13. 2022Using negative controls to identify causal effects with invalid instrumental variablescited by 1
  14. 2022A Nonparametric Framework for Universal Difference-in-Differencescited by 1

Built on by

Not cited yet.