Skip to Main Content
HBS Home
  • About
  • Academic Programs
  • Alumni
  • Faculty & Research
  • Baker Library
  • Giving
  • Harvard Business Review
  • Initiatives
  • News
  • Recruit
  • Map / Directions
Faculty & Research
  • Faculty
  • Research
  • Featured Topics
  • Academic Units
  • …→
  • Harvard Business School→
  • Faculty & Research→
Publications
Publications
  • 2018
  • Working Paper

Efficient Discovery of Heterogeneous Treatment Effects in Randomized Experiments via Anomalous Pattern Detection

By: Edward McFowland III, Sriram Somanchi and Daniel B. Neill
  • Format:Print
  • | Language:English
ShareBar

Abstract

In the recent literature on estimating heterogeneous treatment effects, each proposed method makes its own set of restrictive assumptions about the intervention’s effects and which subpopulations to explicitly estimate. Moreover, the majority of the literature provides no mechanism to identify which subpopulations are the most affected–beyond manual inspection–and provides little guarantee on the correctness of the identified subpopulations. Therefore, we propose Treatment Effect Subset Scan (TESS), a new method for discovering which subpopulation in a randomized experiment is most significantly affected by a treatment. We frame this challenge as a pattern detection problem where we efficiently maximize a nonparametric scan statistic over subpopulations. Furthermore, we identify the subpopulation which experiences the largest distributional change as a result of the intervention, while making minimal assumptions about the intervention’s effects or the underlying data generating process. In addition to the algorithm, we demonstrate that the asymptotic Type I and II error can be controlled, and provide sufficient conditions for detection consistency–i.e., exact identification of the affected subpopulation. Finally, we validate the efficacy of the method by discovering heterogeneous treatment effects in simulations and in real-world data from a well-known program evaluation study.

Keywords

Causal Inference; Program Evaluation; Algorithms; Distributional Average Treatment Effect; Treatment Effect Subset Scan; Heterogeneous Treatment Effects

Citation

McFowland III, Edward, Sriram Somanchi, and Daniel B. Neill. "Efficient Discovery of Heterogeneous Treatment Effects in Randomized Experiments via Anomalous Pattern Detection." Working Paper, 2018. (2nd Round Revision.)
  • Read Now

About The Author

Edward McFowland III

Technology and Operations Management
→More Publications

More from the Authors

    • 2023
    • Journal of Machine Learning Research

    Exploiting Discovered Regression Discontinuities to Debias Conditioned-on-observable Estimators

    By: Benjamin Jakubowski, Siram Somanchi, Edward McFowland III and Daniel B. Neill
    • 2023
    • Journal of the American Statistical Association

    Estimating Causal Peer Influence in Homophilous Social Networks by Inferring Latent Locations.

    By: Edward McFowland III and Cosma Rohilla Shalizi
    • October–December 2022
    • INFORMS Journal on Data Science

    Achieving Reliable Causal Inference with Data-Mined Variables: A Random Forest Approach to the Measurement Error Problem

    By: Mochen Yang, Edward McFowland III, Gordon Burtch and Gediminas Adomavicius
More from the Authors
  • Exploiting Discovered Regression Discontinuities to Debias Conditioned-on-observable Estimators By: Benjamin Jakubowski, Siram Somanchi, Edward McFowland III and Daniel B. Neill
  • Estimating Causal Peer Influence in Homophilous Social Networks by Inferring Latent Locations. By: Edward McFowland III and Cosma Rohilla Shalizi
  • Achieving Reliable Causal Inference with Data-Mined Variables: A Random Forest Approach to the Measurement Error Problem By: Mochen Yang, Edward McFowland III, Gordon Burtch and Gediminas Adomavicius
ǁ
Campus Map
Harvard Business School
Soldiers Field
Boston, MA 02163
→Map & Directions
→More Contact Information
  • Make a Gift
  • Site Map
  • Jobs
  • Harvard University
  • Trademarks
  • Policies
  • Accessibility
  • Digital Accessibility
Copyright © President & Fellows of Harvard College