Data augmented bootstrap constructs confidence intervals via approximately invariant transformations, recovering classical bootstrap, conformal prediction, wild bootstrap, and SymmPI as special cases with interpolated finite-sample to asymptotic coverage guarantees.
arXiv preprint arXiv:2502.20579 , year=
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
stat.ME 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
C-SymmPI reformulates conditional coverage as miscoverage error over a user-specified function class to deliver near-conditional guarantees under group symmetries and distributional invariance.
citing papers explorer
-
Data augmented bootstrap: Unifying confidence interval construction by approximate invariance
Data augmented bootstrap constructs confidence intervals via approximately invariant transformations, recovering classical bootstrap, conformal prediction, wild bootstrap, and SymmPI as special cases with interpolated finite-sample to asymptotic coverage guarantees.
-
Conditional Predictive Inference for General Structured Data with Group Symmetries
C-SymmPI reformulates conditional coverage as miscoverage error over a user-specified function class to deliver near-conditional guarantees under group symmetries and distributional invariance.