Estimation of causal effects with multiple treatments: a review and new ideas

Abstract

The propensity score is a common tool for estimating the causal effect of a binary treatment in observational data. In this setting, matching, subclassification, imputation, or inverse probability weighting on the propensity score can reduce the initial covariate bias between the treatment and control groups. With more than two treatment options, however, estimation of causal effects requires additional assumptions and techniques, the implementations of which have varied across disciplines. This paper reviews current methods, and it identifies and contrasts the treatment effects that each one estimates. Additionally, we propose possible matching techniques for use with multiple, nominal categorical treatments, and use simulations to show how such algorithms can yield improved covariate similarity between those in the matched sets, relative the pre-matched cohort. To sum, this manuscript provides a synopsis of how to notate and use causal methods for categorical treatments.

References in corpus (3)

• Matching Methods for Causal Inference: A Review and a Look Forward
• Demystifying Double Robustness: A Comparison of Alternative Strategies for Estimating a Population Mean from Incomplete Data
• Estimating the average treatment effects of nutritional label use using subclassification with regression adjustment

Cited by in corpus (16)

• The causal effect of a timeout at stopping an opposing run in the NBA
• Propensity Score Weighting for Causal Inference with Multiple Treatments
• The Importance of Causality in Decision Making: A Perspective on Recommender Systems
• The Medical Deconfounder: Assessing Treatment Effects with Electronic Health Records
• Causal Effect Inference for Structured Treatments
• Student Log-Data from a Randomized Evaluation of Educational Technology: A Causal Case Study
• Confounding Adjustment Methods for Multi-level Treatment Comparisons Under Lack of Positivity and Unknown Model Specification
• NCoRE: Neural Counterfactual Representation Learning for Combinations of Treatments
• Estimation of Causal Effects of Multiple Treatments in Observational Studies with a Binary Outcome
• Copula-based Sensitivity Analysis for Multi-Treatment Causal Inference with Unobserved Confounding
• A Generalizability Score for Aggregate Causal Effect
• Deep Stable Representation Learning on Electronic Health Records
• Estimating Individual Advertising Effect in E-Commerce
• Effects of Multi-Aspect Online Reviews with Unobserved Confounders: Estimation and Implication
• Fair Effect Attribution in Parallel Online Experiments
• Functional Data Analysis with Causation in Observational Studies: Covariate Balancing Functional Propensity Score for Functional Treatments