
Create generalized bootstrap replicate weights
Source:R/replicate-weights.R
create_gen_boot_weights.RdGenerates generalized bootstrap replicate weights via
svrep::as_gen_boot_design(). Requires a survey_taylor design.
Usage
create_gen_boot_weights(
data,
replicates = 500L,
...,
variance_estimator = "SD1",
tau = 1,
aux_var_names = NULL,
mse = TRUE,
seed = NULL
)Arguments
- data
A
survey_taylordesign.- replicates
integer(1), default500L. Number of bootstrap replicates.- ...
Must be empty.
- variance_estimator
character(1). Target variance estimator. One of"SD1"(default),"SD2","Horvitz-Thompson","Yates-Grundy","Poisson Horvitz-Thompson","Stratified Multistage SRS","Ultimate Cluster","Deville-1","Deville-2","Deville-Tille","BOSB", or"Beaumont-Emond".- tau
numeric(1)or"auto", default1. Rescaling constant to prevent negative replicate weights.- aux_var_names
<
tidy-select> orNULL. Auxiliary variable columns. Required whenvariance_estimator = "Deville-Tille".- mse
logical(1), defaultTRUE.- seed
integer(1)orNULL. RNG seed.