unmarked (version 1.4.3)

nonparboot-methods: Nonparametric bootstrapping in unmarked

Description

Call nonparboot on an unmarkedFit to obtain non-parametric bootstrap samples. These can then be used by vcov in order to get bootstrap estimates of standard errors.

Methods

signature(object = "unmarkedFit")

Obtain nonparametric bootstrap samples for a general unmarkedFit.

signature(object = "unmarkedFitColExt")

Obtain nonparametric bootstrap samples for colext fits.

signature(object = "unmarkedFitDS")

Obtain nonparametric bootstrap samples for a distsamp fits.

signature(object = "unmarkedFitMPois")

Obtain nonparametric bootstrap samples for a distsamp fits.

signature(object = "unmarkedFitOccu")

Obtain nonparametric bootstrap samples for a occu fits.

signature(object = "unmarkedFitOccuPEN")

Obtain nonparametric bootstrap samples for an occuPEN fit.

signature(object = "unmarkedFitOccuPEN_CV")

Obtain nonparametric bootstrap samples for occuPEN_CV fit.

signature(object = "unmarkedFitOccuRN")

Obtain nonparametric bootstrap samples for a occuRN fits.

signature(object = "unmarkedFitPCount")

Obtain nonparametric bootstrap samples for a pcount fits.

Details

Calling nonparboot on an unmarkedFit returns the original unmarkedFit, with the bootstrap samples added on. Then subsequent calls to vcov with the argument method="nonparboot" will use these bootstrap samples. Additionally, standard errors of derived estimates from either linearComb or backTransform can be instructed to use bootstrap samples by providing the argument method = "nonparboot".

For occu and occuRN both sites and occassions are re-sampled. For all other fitting functions, only sites are re-sampled.

Examples

data(ovendata)
ovenFrame <- unmarkedFrameMPois(ovendata.list$data,
siteCovs=as.data.frame(scale(ovendata.list$covariates[,-1])), type = "removal")
(fm <- multinomPois(~ 1 ~ ufc + trba, ovenFrame))
fm <- nonparboot(fm, B = 20) # should use larger B in real life.
vcov(fm, method = "hessian")
vcov(fm, method = "nonparboot")
avg.abundance <- backTransform(linearComb(fm, type = "state", coefficients = c(1, 0, 0)))

## Bootstrap sample information propagates through to derived quantities.
vcov(avg.abundance, method = "hessian")
vcov(avg.abundance, method = "nonparboot")
SE(avg.abundance, method = "nonparboot")