corrected.var: Corrected variance function

Description Usage Arguments Details Value Author(s) References

View source: R/utilities.R

Description

Calculate variance corrected for non-independence of k-fold iterations

Usage

1

Arguments

x

numeric vector: input values

nk

numeric: number of k-fold iterations

Details

'corrected.var' calculates variance corrected for non-independence of k-fold iterations. See Appendix of Shcheglovitova & Anderson (2013) and other references (Miller 1974; Parr 1985; Shao and Wu 1989) for additional details. This function calculates variance that is corrected for the non-independence of k cross-validation iterations. Following Shao and Wu (1989):

Sum Of Squares * ((n-1)/n)

where n = the number of k-fold iterations.

Value

A numeric value of the corrected variance.

Author(s)

Robert Muscarella <bob.muscarella@gmail.com>

References

Miller, R. G. (1974) The jackknife - a review. Biometrika, 61: 1-15. doi: 10.1093/biomet/61.1.1

Parr, W. C. (1985) Jackknifing differentiable statistical functionals. Journal of the Royal Statistics Society, Series B, 47: 56-66. doi: 10.1111/j.2517-6161.1985.tb01330.x

Shao J. and Wu, C. F. J. (1989) A general theory for jackknife variance estimation. Annals of Statistics, 17: 1176-1197. doi: 10.1214/aos/1176347263

Shcheglovitova, M. and Anderson, R. P. (2013) Estimating optimal complexity for ecological niche models: a jackknife approach for species with small sample sizes. Ecological Modelling, 269: 9-17. doi: 10.1016/j.ecolmodel.2013.08.011


ENMeval documentation built on Jan. 10, 2022, 1:07 a.m.