The number the comparison was missing

What it costs to choose the tuning parameter for every candidate separately rather than once for the table, under AR(1) at 0.8, paired on the draw. The window's figure is the one the earlier field reported; the order's is the one it named and did not make. They are the same size — 0.00401 against 0.00360, at 2.30 and 1.72 paired standard errors — and matching the lists at eight values leaves them the same size again. The prediction that the longer list would make the order's cost the larger of the two is not what happens; what happens is that the two rules cost the same once they are scored by the same criterion, which took a missing term to arrange.

The extra error from choosing a tuning parameter per candidate, under AR(1) at 0.8, three ways. Scored by the criterion this collection has used for a sieve since the estimated-covariance field — which carries no determinant — a per-candidate order costs -0.00011, at -0.16 standard errors, and the honest reading of that is nothing. Scored by the criterion the window's rule has always used, which carries the volume its whitening moves, the same rule costs 0.00415 at 2.02 — the window's own 0.00401. The rules were never different. The criteria were.