Distributional conformal prediction
| Autor: | Yinchu Zhu, Kaspar Wüthrich, Victor Chernozhukov |
|---|---|
| Jazyk: | angličtina |
| Rok vydání: | 2021 |
| Předmět: |
FOS: Computer and information sciences
Heteroscedasticity Multidisciplinary quantile regression model-free validity conditional validity Econometrics (econ.EM) Prediction interval Conditional probability distribution Overfitting Quantile regression Methodology (stat.ME) FOS: Economics and business distribution regression prediction intervals Physical Sciences Applied mathematics Time series Probability integral transform Statistics - Methodology Mathematics Quantile Economics - Econometrics |
| Zdroj: | Proc Natl Acad Sci U S A Proceedings of the National Academy of Sciences of the United States of America, vol 118, iss 48 |
| Popis: | We propose a robust method for constructing conditionally valid prediction intervals based on models for conditional distributions such as quantile and distribution regression. Our approach can be applied to important prediction problems, including cross-sectional prediction, k-step-ahead forecasts, synthetic controls and counterfactual prediction, and individual treatment effects prediction. Our method exploits the probability integral transform and relies on permuting estimated ranks. Unlike regression residuals, ranks are independent of the predictors, allowing us to construct conditionally valid prediction intervals under heteroskedasticity. We establish approximate conditional validity under consistent estimation and provide approximate unconditional validity under model misspecification, under overfitting, and with time series data. We also propose a simple "shape" adjustment of our baseline method that yields optimal prediction intervals. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|