• Corpus ID: 219179356

Conformal prediction intervals for the individual treatment effect

  title={Conformal prediction intervals for the individual treatment effect},
  author={Danijel Kivaranovic and Robin Ristl and Martin Posch and Hannes Leeb},
  journal={arXiv: Methodology},
We propose several prediction intervals procedures for the individual treatment effect with either finite-sample or asymptotic coverage guarantee in a non-parametric regression setting, where non-linear regression functions, heteroskedasticity and non-Gaussianity are allowed. The construct the prediction intervals we use the conformal method of Vovk et al. (2005). In extensive simulations, we compare the coverage probability and interval length of our prediction interval procedures. We… 
5 Citations

Figures from this paper

Conformal inference of counterfactuals and individual treatment effects
  • Lihua Lei, E. Candès
  • Mathematics, Computer Science
    Journal of the Royal Statistical Society: Series B (Statistical Methodology)
  • 2021
This work proposes a conformal inference-based approach that can produce reliable interval estimates for counterfactuals and individual treatment effects under the potential outcome framework and achieves the desired coverage with reasonably short intervals.
Adaptive Conformal Inference Under Distribution Shift
This work develops methods for forming prediction sets in an online setting where the data generating distribution is allowed to vary over time in an unknown fashion and achieves the desired coverage frequency over long-time intervals irrespective of the true data generating process.
Conformal Sensitivity Analysis for Individual Treatment Effects
Estimating an individual treatment effect (ITE) is essential to personalized decision making. However, existing methods for estimating the ITE often rely on unconfoundedness, an assumption that is
Distributional conformal prediction.
A robust method based on models for conditional distributions such as quantile and distribution regression that exploits the probability integral transform and relies on permuting estimated ranks to construct conditionally valid prediction intervals under heteroskedasticity.
AutoCP: Automated Pipelines for Accurate Prediction Intervals
Unlike the familiar AutoML frameworks that attempt to select the best prediction model, AutoCP constructs prediction intervals that achieve the user-specified target coverage rate while optimizing the interval length to be accurate and less conservative.


Conformalized Quantile Regression
This paper proposes a new method that is fully adaptive to heteroscedasticity, which combines conformal prediction with classical quantile regression, inheriting the advantages of both.
Distribution-Free Predictive Inference for Regression
A general framework for distribution-free predictive inference in regression, using conformal inference, which allows for the construction of a prediction band for the response variable using any estimator of the regression function, and a model-free notion of variable importance, called leave-one-covariate-out or LOCO inference.
Adaptive, Distribution-Free Prediction Intervals for Deep Neural Networks
The PI-Network is provided, a transparent, tractable modification of the standard predictive loss used to train deep networks, which outputs three values instead of a single point estimate and optimizes a loss function inspired by quantile regression.
Identification of predicted individual treatment effects in randomized clinical trials
This study first applies the predicted individual treatment effect approach to a randomized controlled trial designed to improve behavioral and physical symptoms and conducts a Monte Carlo simulation study to evaluate the accuracy of predictedindividual treatment effects.
A tutorial on conformal prediction
This tutorial presents a self-contained account of the theory of conformal prediction and works through several numerical examples of how the model under which successive examples are sampled independently from the same distribution can be applied to any method for producing ŷ.
Subgroup identification in clinical trials via the predicted individual treatment effect
This work explores linear models and compares different estimation methods, such as maximum likelihood and the Lasso with and without randomized response, and evaluates via simulations the performance of using the predicted individual treatment effect to identify subgroups where a novel treatment leads to better outcomes compared to a control treatment.
On deep learning as a remedy for the curse of dimensionality in nonparametric regression
Assuming that a smoothness condition and a suitable restriction on the structure of the regression function hold, it is shown that least squares estimates based on multilayer feedforward neural
Causal Inference Using Potential Outcomes
Causal effects are defined as comparisons of potential outcomes under different treatments on a common set of units. Observed values of the potential outcomes are revealed by the assignment
Optimized multiple testing procedures for nested sub-populations based on a continuous biomarker
A framework to select optimal thresholds and corresponding optimized multiple testing procedures that maximize the expected power to identify at least one subgroup with a positive treatment effect is proposed.
Estimating causal effects of treatments in randomized and nonrandomized studies.
A discussion of matching, randomization, random sampling, and other methods of controlling extraneous variation is presented. The objective is to specify the benefits of randomization in estimating