Data augmented bootstrap: Unifying confidence interval construction by approximate invariance
Researchers have introduced the data augmented bootstrap (DAB), a new framework designed to unify the construction of confidence intervals. This method leverages approximately invariant transformations of data, encompassing existing techniques like conformal prediction and the classical bootstrap as special cases. DAB provides theoretical coverage guarantees that adapt based on the strength of the invariance, without requiring a group structure, and integrates data augmentation into statistical methods. AI
IMPACT Introduces a unified statistical framework for confidence intervals, potentially improving reliability in ML model evaluation.