Who should be Treated? Empirical Welfare Maximization Methods for Treatment Choice

By Toru Kitagawa, Aleksey Tetenov. 2015

425 citations recorded by the source corpus.

Subfields: Economics and Econometrics, Statistics and Probability, Causal Inference & Discovery, Economics & Operations Research

How researchers see this paper

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

In Economics and Econometrics

In Statistics and Probability

In Causal Inference & Discovery

In Economics & Operations Research

Citations in the corpus

Machine Learning Methods That Economists Should Know About (2019, methodology): “A major theme of this review is that even though there are cases where using simple of-the-shelf algorithms from the ML literature can be effective (see Mullainathan and Spiess [2017] for a number of examples), there are also many cases where this is not the case.”
Learning When-to-Treat Policies (2019, methodology): “By Assumptions 1–3, IPW is consistent if the treatment probabilities are known a priori, and by uniform concentration arguments following Kitagawa and Tetenov (2018), the regret of the policy π̂ learned by maximizing V̂IPWπ over π ∈ decays as 1/ √ n if is not too large (e.g., if is a VC-class).”
Efficient Policy Learning (2017, methodology): “12Using the techniques developed in this paper, we can sharpen the bounds of Kitagawa and Tetenov (2018) and asymptotically replace M/η by E [ Y 2 i /(e(Xi)(1− e(Xi))) ]1/2 .”
Quasi-oracle estimation of heterogeneous treatment effects (2017, background): “This problem is closely related to, but subtly diﬀerent from the problem of estimating τ ∗ ( · ) under squared-error loss; see Kitagawa and Tetenov (2018), Manski (2004) and Murphy (2005) for a discussion.”
Policy Learning With Observational Data (2017, methodology): “The main result of Kitagawa and Tetenov (2018) is that, if treatment propensities e ( X i ) are known, then a variant of inverse-propensity weighted policy learning achieves regret on the order of VC(Π) /n .”
The Impact of Machine Learning on Economics (2018, background): “Finally, a motivating goal for understanding treatment eﬀects is estimating optimal policy functions; this has been recently studied in economics by, e.g., Kitagawa and Tetenov (2015).”
Stratification Trees for Adaptive Randomization in Randomized Controlled Trials (2018, background): “See Perchet et al. (2013) for relevant literature in the context of bandit problems).”