Ex. 15.2 (TODO)
Ex. 15.2
Show that as the number of bootstrap samples \(B\) gets large, the oob error estimate for a random forest approaches its \(N\)-fold CV error estimate, and that in the limit, the identity is exact.
Show that as the number of bootstrap samples \(B\) gets large, the oob error estimate for a random forest approaches its \(N\)-fold CV error estimate, and that in the limit, the identity is exact.