Cross validation is an essential tool in statistical learning [note]Lecture 1 on cross validation - Statistical Learning @ Stanford[/note] to estimate the accuracy of your algorithm. Despite its great power it also exposes some fundamental risk when done wrong which may terribly bias your accuracy estimate.
Cross Validation done wrong
Cross Validation done wrong
Cross Validation done wrong
Cross validation is an essential tool in statistical learning [note]Lecture 1 on cross validation - Statistical Learning @ Stanford[/note] to estimate the accuracy of your algorithm. Despite its great power it also exposes some fundamental risk when done wrong which may terribly bias your accuracy estimate.