Distribution-Free Predictive Inference for Regression

We develop a general framework for distribution-free predictive inference in regression, using conformal inference. The proposed methodology allows for the construction of a prediction band for the response variable using any estimator of the regression function. The resulting prediction band preser...

Full description

Saved in:
Bibliographic Details
Published in:Journal of the American Statistical Association Vol. 113; no. 523; pp. 1094 - 1111
Main Authors: Lei, Jing, G'Sell, Max, Rinaldo, Alessandro, Tibshirani, Ryan J., Wasserman, Larry
Format: Journal Article
Language:English
Published: Alexandria Taylor & Francis 03.07.2018
Taylor & Francis Group,LLC
Taylor & Francis Ltd
Subjects:
Computational efficiency
computer software
Computing time
Distribution-free
Empirical analysis
equations
heteroskedasticity
Inference
Intervals
Model misspecification
prediction
Prediction band
Predictions
Property
Regression
Regression analysis
Reproducibility
Statistical analysis
Statistical methods
Statistics
Theory and Methods
Variable importance
Variants
ISSN:0162-1459, 1537-274X, 1537-274X
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:We develop a general framework for distribution-free predictive inference in regression, using conformal inference. The proposed methodology allows for the construction of a prediction band for the response variable using any estimator of the regression function. The resulting prediction band preserves the consistency properties of the original estimator under standard assumptions, while guaranteeing finite-sample marginal coverage even when these assumptions do not hold. We analyze and compare, both empirically and theoretically, the two major variants of our conformal framework: full conformal inference and split conformal inference, along with a related jackknife method. These methods offer different tradeoffs between statistical accuracy (length of resulting prediction intervals) and computational efficiency. As extensions, we develop a method for constructing valid in-sample prediction intervals called rank-one-out conformal inference, which has essentially the same computational efficiency as split conformal inference. We also describe an extension of our procedures for producing prediction bands with locally varying length, to adapt to heteroscedasticity in the data. Finally, we propose a model-free notion of variable importance, called leave-one-covariate-out or LOCO inference. Accompanying this article is an R package conformalInference that implements all of the proposals we have introduced. In the spirit of reproducibility, all of our empirical results can also be easily (re)generated using this package.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
ISSN:0162-1459
1537-274X
1537-274X
DOI:10.1080/01621459.2017.1307116