Cross-audit projection (CAP) combines K-fold resampling with asymptotic bias correction to achieve second-order unbiasedness for class-specific risk estimation while remaining first-order equivalent to the empirical risk.
(1995), ``Assessing Prediction Error in Non-parametric Regression,'' Scandinavian Journal of Statistics, 22, 83--94
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
stat.ME 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Cross-Audit Projection for Model Risk Prediction
Cross-audit projection (CAP) combines K-fold resampling with asymptotic bias correction to achieve second-order unbiasedness for class-specific risk estimation while remaining first-order equivalent to the empirical risk.