English

Ensembled Prediction Intervals for Causal Outcomes Under Hidden Confounding

Machine Learning 2023-11-02 v2 Artificial Intelligence Methodology Machine Learning

Abstract

Causal inference of exact individual treatment outcomes in the presence of hidden confounders is rarely possible. Recent work has extended prediction intervals with finite-sample guarantees to partially identifiable causal outcomes, by means of a sensitivity model for hidden confounding. In deep learning, predictors can exploit their inductive biases for better generalization out of sample. We argue that the structure inherent to a deep ensemble should inform a tighter partial identification of the causal outcomes that they predict. We therefore introduce an approach termed Caus-Modens, for characterizing causal outcome intervals by modulated ensembles. We present a simple approach to partial identification using existing causal sensitivity models and show empirically that Caus-Modens gives tighter outcome intervals, as measured by the necessary interval size to achieve sufficient coverage. The last of our three diverse benchmarks is a novel usage of GPT-4 for observational experiments with unknown but probeable ground truth.

Keywords

Cite

@article{arxiv.2306.09520,
  title  = {Ensembled Prediction Intervals for Causal Outcomes Under Hidden Confounding},
  author = {Myrl G. Marmarelis and Greg Ver Steeg and Aram Galstyan and Fred Morstatter},
  journal= {arXiv preprint arXiv:2306.09520},
  year   = {2023}
}
R2 v1 2026-06-28T11:06:39.820Z