Revision as of 20:25, 13 December 2018 edit Ochado (talk \| contribs) 157 edits m →The backward pass ← Previous edit		Revision as of 08:52, 20 December 2018 edit undo Stephen Milborrow (talk \| contribs) 60 edits Undid previous revision because it distracts (slightly) from the clarity of the exposition Tag: Undo Next edit →
Line 221: deleting the least effective term at each step until it finds the best submodel. Model subsets are compared using the ~~generalized cross validation~~GCV criterion described below. The backward pass has an advantage over the forward pass:

Multivariate adaptive regression spline: Difference between revisions