Comparison

Bias–Variance Tradeoff Among Cross-Validation Methods

Cross-validation methods differ in the bias and variance of their estimated test error. A validation-set approach trains on a relatively small subset of the data and may therefore overestimate test error. Leave-one-out cross-validation trains each model on n1n-1 observations, producing an approximately unbiased estimate, but its estimates tend to have higher variance. In KK-fold cross-validation, each model is trained on (K1)n/K(K-1)n/K observations, so values such as K=5K=5 or K=10K=10 generally provide an intermediate bias with lower variance than leave-one-out cross-validation.

0

1

Updated 2026-07-18

Tags

Data Science