Jacknife resampling

Description

The jacknife method sets up objects ready for jacknifing, i.e. to systematically recompute a given statistic leaving out one observation at a time. From this new set of "observations" for the statistic an estimate for the bias can be calculated as well as an estimate for the variance of the statistic.

Input objects cannot have length > 1 along the iter dimension, and the resulting object will have as many iterations as elements in the original object.

Generic function

jacknife(object, ...)

Methods

signature(object=FLQuant) :

Returns an FLQuant with iter=length(object), where in each iteration one element has been sequantally converted to NA.

Author(s)

The FLR Team

See Also

FLQuant

Examples

flq <- FLQuant(1:8)
iters(jacknife(flq))