fwb (version 0.3.0)

set_fwb_wtype: Set weights type

Description

Set the default for the type of weights used in the weighted bootstrap computed by fwb() and vcovFWB().

Usage

set_fwb_wtype(wtype = getOption("fwb_wtype", "exp"))
get_fwb_wtype(fwb)

Value

set_fwb_wtype() returns a call to options() with the options set to those prior to set_fwb_wtype() being called. This makes it so that calling options(op), where op is the output of set_fwb_wtype(), resets the fwb_wtype to its original value. get_fwb_wtype() returns a string containing the fwb_wtype value set globally (if no argument is supplied) or used in the supplied fwb object.

Arguments

wtype

string; the type of weights to use. Allowable options include "exp" (the default), "pois", "multinom", and "mammen". Abbreviations allowed. See fwb() for what these mean.

fwb

optional; an fwb object, the output of a call to fwb(). If left empty, will extract the weights type from options().

Details

set_fwb_wtype(x) is equivalent to calling options(fwb_wtype = x). get_fwb_wtype() is equivalent to calling getOption("fwb_wtype") when no argument is supplied and to extracting the wtype component of an fwb object when supplied.

See Also

fwb() for a definition of each types of weights; vcovFWB(); options(); boot::boot() for the traditional bootstrap.

Examples

# Performing a Weibull analysis of the Bearing Cage
# failure data as done in Xu et al. (2020)
set.seed(123, "L'Ecuyer-CMRG")
data("bearingcage")

#Set fwb type to "mammen"
op <- set_fwb_wtype("mammen")

weibull_est <- function(data, w) {
  fit <- survival::survreg(survival::Surv(hours, failure) ~ 1,
                           data = data, weights = w,
                           dist = "weibull")

  c(eta = unname(exp(coef(fit))), beta = 1/fit$scale)
}

boot_est <- fwb(bearingcage, statistic = weibull_est,
                R = 199, verbose = FALSE)
boot_est

#Get the fwb type used in the bootstrap
get_fwb_wtype(boot_est)
get_fwb_wtype()

#Restore original options
options(op)

get_fwb_wtype()