Nonparametric Estimation of Heterogeneous Treatment Effects: From Theory to Learning Algorithms
arXiv:2101.10943
Abstract
The need to evaluate treatment effectiveness is ubiquitous in most of empirical science, and interest in flexibly investigating effect heterogeneity is growing rapidly. To do so, a multitude of model-agnostic, nonparametric meta-learners have been proposed in recent years. Such learners decompose the treatment effect estimation problem into separate sub-problems, each solvable using standard supervised learning methods. Choosing between different meta-learners in a data-driven manner is difficult, as it requires access to counterfactual information. Therefore, with the ultimate goal of building better understanding of the conditions under which some learners can be expected to perform better than others a priori, we theoretically analyze four broad meta-learning strategies which rely on plug-in estimation and pseudo-outcome regression. We highlight how this theoretical reasoning can be used to guide principled algorithm design and translate our analyses into practice by considering a variety of neural network architectures as base-learners for the discussed meta-learning strategies. In a simulation study, we showcase the relative strengths of the learners under different data-generating processes.
To appear in the Proceedings of the 24th International Conference on Artificial Intelligence and Statistics (AISTATS) 2021
Cited by in corpus (7)
- SurvITE: Learning Heterogeneous Treatment Effects from Time-to-Event Data
- Heterogeneous Treatment Effect Estimation using machine learning for Healthcare application: tutorial and benchmark
- Assisting Clinical Decisions for Scarcely Available Treatment via Disentangled Latent Representation
- Experimental Standards for Deep Learning in Natural Language Processing Research
- Causal Effect Variational Autoencoder with Uniform Treatment
- Partial counterfactual identification and uplift modeling: theoretical results and real-world assessment
- Doing Great at Estimating CATE? On the Neglected Assumptions in Benchmark Comparisons of Treatment Effect Estimators