Jackknife Estimation

Usage

# S4 method for DiversityIndex
jackknife(object, f = NULL)

Arguments

object: An R object (typically a DiversityIndex object).
f: A function that takes a single numeric vector (the leave-one-out values of do) as argument.

Value

If f is NULL (the default), jackknife() returns a named numeric

vector with the following elements:

original: The observed value of do applied to object.
mean: The jackknife estimate of mean of do.
bias: The jackknife estimate of bias of do.
error: he jackknife estimate of standard error of do.

If f is a function, jackknife() returns the result of f applied to the leave-one-out values of do.

Author

N. Frerebeau

Examples

## Data from Conkey 1980, Kintigh 1989
data("cantabria")

## Shannon diversity index
(h <- heterogeneity(cantabria, method = "shannon"))
#> [1] 3.269200 2.955298 2.491683 2.485604 2.329187

## Bootstrap resampling
bootstrap(h, f = NULL)
#>                  original     mean         bias      error
#> Altamira         3.269200 3.278206  0.009006676 0.08307194
#> Cueto de la Mina 2.955298 2.972727  0.017429550 0.15398977
#> El Juyo          2.491683 2.512902  0.021218780 0.20477828
#> El Cierro        2.485604 2.489387  0.003782870 0.21801177
#> La Paloma        2.329187 2.304147 -0.025039501 0.26161788

bootstrap(h, f = summary)
#>                      Min.  1st Qu.   Median     Mean  3rd Qu.     Max.
#> Altamira         3.025561 3.223493 3.274640 3.274596 3.331732 3.510869
#> Cueto de la Mina 2.510647 2.879026 2.986806 2.977599 3.078147 3.392700
#> El Juyo          1.867719 2.400420 2.540724 2.524350 2.667965 3.082037
#> El Cierro        1.671531 2.369194 2.515860 2.495118 2.651108 3.035360
#> La Paloma        1.213008 2.163956 2.343947 2.316331 2.499333 3.061994

quant <- function(x) quantile(x, probs = c(0.25, 0.50))
bootstrap(h, f = quant)
#>                       25%      50%
#> Altamira         3.229519 3.285076
#> Cueto de la Mina 2.878630 2.980912
#> El Juyo          2.396635 2.532030
#> El Cierro        2.366988 2.504375
#> La Paloma        2.145842 2.329187

## Jackknife resampling
jackknife(h)
#>                  original     mean       bias      error
#> Altamira         3.269200 3.246457 -0.9779158 0.08145529
#> Cueto de la Mina 2.955298 2.932856 -0.9649994 0.15907033
#> El Juyo          2.491683 2.469588 -0.9500688 0.19670002
#> El Cierro        2.485604 2.462723 -0.9838709 0.22195573
#> La Paloma        2.329187 2.305876 -1.0023704 0.25266291

bootstrap(h, f = summary)
#>                      Min.  1st Qu.   Median     Mean  3rd Qu.     Max.
#> Altamira         3.045532 3.229899 3.283922 3.281962 3.334989 3.514534
#> Cueto de la Mina 2.301774 2.872228 2.977945 2.968116 3.075886 3.332967
#> El Juyo          1.695724 2.396411 2.537224 2.526913 2.674774 3.222411
#> El Cierro        1.723392 2.333030 2.496161 2.472532 2.637416 2.985356
#> La Paloma        1.277034 2.163956 2.338372 2.313336 2.491497 2.959830