September 9, 2019

Assessing Treatment Effect Variation in Observational Studies: Results from a Data Challenge

By Carlos Carvalho, Avi Feller, Jared Murray, Spencer Woody and David Yeager (Introduction)
Susan Athey and Stefan Wager (Estimating Treatment Effects with Causal Forests: An Application)
Nicole Carnegie, Vincent Dorie and Jennifer Hill (Examining Treatment Effect Heterogeneity Using BART)
Fredrik Johansson (Machine Learning Analysis of Heterogeneity in the Effect of Student Mindset Interventions)
Luke Keele and Samuel Pimentel (Matching with attention to effect modification in a data challenge)
Bryan Keller, Jianshen Chen and Tianyang Zhang (Heterogeneous Subgroup Identification with Observational Data)
Soren Kunzel, Simon Walter and Jasjeet Sekhon (Causaltoolbox -- Estimator Stability for Heterogeneous Treatment Effects)
Harsh Parikh, Cynthia Rudin and Alexander Volfovsky (An Application of Matching After Learning To Stretch (MALTS))
Qingyuan Zhao and Snigdha Panigrahi (Selective Inference for Effect Modification: An Empirical Investigation)


A growing number of methods aim to assess the challenging question of treatment effect variation in observational studies. This special section of Observational Studies reports the results of a workshop conducted at the 2018 Atlantic Causal Inference Conference designed to understand the similarities and differences across these methods.   Eight groups of researchers participated in the workshop and analyzed a synthetic observational data set that was generated using a recent large-scale randomized trial in education.  Each group contributed an article in this section.

Applications and Case Studies Methodology