Skip to content

Abstract Search

Primary Submission Category: Machine Learning and Causal Inference

Latent distribution estimation for the evaluation of the complier average causal effect

Authors: Celine Beji, Raphaël Porcher,

Presenting Author: Celine Beji*

The complier average causal effect (CACE) estimator, defined as the average of potential outcomes in the latent sub-population that complies with their assigned treatment, is more and more used in clinical trials to study the effect of a medication or an intervention rather than the effect of its prescription. Although advanced methods such as instrumental variables and G-estimation have been developed, it requires strong assumptions of exclusion restriction and principal ignorability.

We propose a new approach to CACE estimation, in the vein of principal stratification framework, that does not require these assumptions. We estimate the latent distribution of four relevant groups of individuals: compliers, never-takers, always-takers and defiers. We reframe the problem as a missing data problem and introduce a two-step procedure that estimates CACE via the latent distribution of the principal strata. We study the estimator sensitivity to assumptions using Monte Carlo simulations, for three different estimation methods using a mixture of experts, a revisited Expectation-Maximization algorithm and a neural network. We apply this approach on randomized trials which evaluate the effect of an individualized education program on risk factors reduction after an acute coronary syndrome.