Conformal Prediction for Causal Effects of Continuous Treatments
This work addresses a gap in causal inference for safety-critical domains by extending conformal prediction to continuous treatments, though it is incremental as it builds on existing methods for binary treatments.
The paper tackles the problem of uncertainty quantification for causal effects of continuous treatments, which is crucial for applications like personalized medicine, by developing a novel conformal prediction method that provides finite-sample guarantees even with unknown propensity scores, and demonstrates its effectiveness on synthetic and real-world datasets.
Uncertainty quantification of causal effects is crucial for safety-critical applications such as personalized medicine. A powerful approach for this is conformal prediction, which has several practical benefits due to model-agnostic finite-sample guarantees. Yet, existing methods for conformal prediction of causal effects are limited to binary/discrete treatments and make highly restrictive assumptions such as known propensity scores. In this work, we provide a novel conformal prediction method for potential outcomes of continuous treatments. We account for the additional uncertainty introduced through propensity estimation so that our conformal prediction intervals are valid even if the propensity score is unknown. Our contributions are three-fold: (1) We derive finite-sample prediction intervals for potential outcomes of continuous treatments. (2) We provide an algorithm for calculating the derived intervals. (3) We demonstrate the effectiveness of the conformal prediction intervals in experiments on synthetic and real-world datasets. To the best of our knowledge, we are the first to propose conformal prediction for continuous treatments when the propensity score is unknown and must be estimated from data.