Classification-Powered Conformal Inference for Zero-inflated Outcomes
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866913091994779648 |
|---|---|
| author | Li, Zhirui Diaz-Rincon, Ricardo Shickel, Benjamin Zhang, Sai Bhattacharya, Sohom Liang, Muxuan |
| author_facet | Li, Zhirui Diaz-Rincon, Ricardo Shickel, Benjamin Zhang, Sai Bhattacharya, Sohom Liang, Muxuan |
| contents | Zero-inflated outcomes, where responses are zero with positive probability and otherwise continuous, are common in biomedical, environmental, and social science studies. We propose a conformal prediction based framework that provides distribution-free uncertainty quantification tailored to such outcomes. Standard conformal methods often ignore strong predictors distinguishing zero from non-zero outcomes, leading to overly conservative and unnecessarily long prediction sets. Our method integrates a classification step to identify zero outcomes and applies conformal inference to the non-zero part, producing prediction sets that are either ${0}$ or an interval. Under exchangeability, we establish that the proposed procedure attains the target marginal coverage and achieves asymptotically minimal interval length within this framework, regardless of the choice of classification or regression models. Extensive simulations and real-data application demonstrate the superior performance of our approach. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_04219 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Classification-Powered Conformal Inference for Zero-inflated Outcomes Li, Zhirui Diaz-Rincon, Ricardo Shickel, Benjamin Zhang, Sai Bhattacharya, Sohom Liang, Muxuan Methodology Zero-inflated outcomes, where responses are zero with positive probability and otherwise continuous, are common in biomedical, environmental, and social science studies. We propose a conformal prediction based framework that provides distribution-free uncertainty quantification tailored to such outcomes. Standard conformal methods often ignore strong predictors distinguishing zero from non-zero outcomes, leading to overly conservative and unnecessarily long prediction sets. Our method integrates a classification step to identify zero outcomes and applies conformal inference to the non-zero part, producing prediction sets that are either ${0}$ or an interval. Under exchangeability, we establish that the proposed procedure attains the target marginal coverage and achieves asymptotically minimal interval length within this framework, regardless of the choice of classification or regression models. Extensive simulations and real-data application demonstrate the superior performance of our approach. |
| title | Classification-Powered Conformal Inference for Zero-inflated Outcomes |
| topic | Methodology |
| url | https://arxiv.org/abs/2605.04219 |