English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Tools annual

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

We investigate the problem of machine learning-based (ML) predictiveinference on individual treatment effects (ITEs). Previous work has focusedprimarily on developing ML-based meta-learners that can provide point estimatesof the conditional average treatment effect (CATE); these are model-agnosticapproaches for combining intermediate nuisance estimates to produce estimatesof CATE. In this paper, we develop conformal meta-learners, a general frameworkfor issuing predictive intervals for ITEs by applying the standard conformalprediction (CP) procedure on top of CATE meta-learners. We focus on a broadclass of meta-learners based on two-stage pseudo-outcome regression and developa stochastic ordering framework to study their validity. We show that inferencewith conformal meta-learners is marginally valid if their (pseudo outcome)conformity scores stochastically dominate oracle conformity scores evaluated onthe unobserved ITEs. Additionally, we prove that commonly used CATEmeta-learners, such as the doubly-robust learner, satisfy a model- anddistribution-free stochastic (or convex) dominance condition, making theirconformal inferences valid for practically-relevant levels of target coverage.Whereas existing procedures conduct inference on nuisance parameters (i.e.,potential outcomes) via weighted CP, conformal meta-learners enable directinference on the target parameter (ITE). Numerical experiments show thatconformal meta-learners provide valid intervals with competitive efficiencywhile retaining the favorable point estimation properties of CATEmeta-learners.

Conformal Meta-learners for Predictive Inference of Individual Treatment Effects