arXiv 10 Feb 2023 · Econometrics · 1 citations (OpenAlex)
arXiv:2302.05260 · PDF · DOI · OpenAlex · Extracted main text
Machine learning (ML) estimates of conditional average treatment effects (CATE) can guide policy decisions, either by allowing targeting of individuals with beneficial CATE estimates, or as inputs to decision trees that optimise overall outcomes. There is limited information available regarding how well these algorithms perform in real-world policy evaluation scenarios. Using synthetic data, we compare the finite sample performance of different policy learning algorithms, machine learning techniques employed during their learning phases, and methods for presenting estimated policy values. For each algorithm, we assess the resulting treatment allocation by measuring deviation from the ideal ("oracle") policy. Our main finding is that policy trees based on estimated CATEs outperform trees learned from doubly-robust scores. Across settings, Causal Forests and the Normalised Double-Robust Learner perform consistently well, while Bayesian Additive Regression Trees perform poorly. These methods are then applied to a case study targeting optimal allocation of subsidised health insurance, with the goal of reducing infant mortality in Indonesia.
appendix boundary found by appendix_command · 58% of the source is main text. Read the extracted text to check this.
The works this paper leans on most, across its whole bibliography — not restricted to papers in our corpus. Ranked by composite intensity, which combines how often a work is mentioned, how many sections mention it, and how much of that falls in the main text rather than the appendix.
| Reference | Intensity | Mentions | Sections | Main text | |
|---|---|---|---|---|---|
| 1 | Athey, Susan, Wager, Stefan (2021) Policy learning with observational data | 1.000 | 15 | 4 | 100% |
| 2 | Athey, Susan, Tibshirani, Julie, Wager, Stefan (2019) Generalized random forests | 1.000 | 5 | 3 | 100% |
| 3 | Chernozhukov, Victor, Chetverikov, Denis, Demirer, Mert, Duflo, Esth… (2017) Double/debiased/neyman machine learning of treatment effects | 1.000 | 5 | 3 | 100% |
| 4 | Hirano, Keisuke, Porter, Jack R (2009) Asymptotics for statistical treatment rules | 0.811 | 4 | 2 | 100% |
| 5 | Kreif, Noemi, DiazOrdaz, Karla, Moreno-Serra, Rodrigo, Mirelman, And… (2021) Estimating heterogeneous policy impacts using causal machine learning: a case study of health insurance reform in Indonesia self | 0.811 | 4 | 2 | 100% |
| 6 | Hill, Jennifer, Linero, Antonio, Murray, Jared (2020) Bayesian additive regression trees: A review and look forward | 0.737 | 3 | 2 | 100% |
| 7 | Hu, Liangyuan, Gu, Chenyang (2021) Estimation of causal effects of multiple treatments in healthcare database studies with rare outcomes | 0.737 | 3 | 2 | 100% |
| 8 | Kennedy, Edward H (2020) Optimal doubly robust estimation of heterogeneous causal effects | 0.737 | 3 | 2 | 100% |
| 9 | Chernozhukov, Victor, Demirer, Mert, Duflo, Esther, Fernandez-Val, I… (2018) Generic machine learning inference on heterogeneous treatment effects in randomized experiments, with an application to immuniza… | 0.644 | 2 | 2 | 100% |
| 10 | Knaus, Michael C (2022) Double machine learning-based programme evaluation under unconfoundedness | 0.644 | 2 | 2 | 100% |
Showing the top 10 of 42 scored citations.