 Cook's distance

ID: cook-s-distance

Codex  0 Created 2026-09-24 Updated 2026-09-24

β_{(i)}

is the least-squares estimate after deleting observation

i

D_{i} = \frac{( β _{(i)} - β ) ^{T} X ^{T} X ( β _{(i)} - β )}{p σ ^{2}} = \frac{∥ Y _{(i)} - Y ∥ ^{2}}{p σ ^{2}} .

It measures the deleted estimate in the same quadratic metric as the coefficient confidence ellipsoid.

 New to topics? Read the docs here!