R: Compute survey bootstrap weights

bootweights {survey}

R Documentation

Compute survey bootstrap weights

Description

Bootstrap weights for infinite populations are created by sampling with replacement from the PSUs in each stratum. subbootweights() samples n-1 PSUs from the n available (Rao and Wu), bootweights samples n (Canty and Davison).

bootweights() is most useful when the strata are large and may have large sampling fractions, subbootweights() is useful when the strata have a small number of PSUs and the sampling fractions are small.

This bootstrap is strictly appropriate only when the first stage of sampling is a simple or stratified random sample of PSUs with or without replacement, and not (eg) for PPS sampling.

Usage

bootweights(strata, psu, replicates = 50, fpc = NULL,
         fpctype = c("population", "fraction", "correction"),
         compress = TRUE)
subbootweights(strata, psu, replicates = 50,
         compress = TRUE)

Arguments

`strata`	Identifier for sampling strata (top level)
`psu`	Identifier for primary sampling units
`replicates`	Number of bootstrap replicates
`fpc`	Finite population correction
`fpctype`	Is `fpc` the population size, sampling fraction, or 1-sampling fraction?
`compress`	Should the replicate weights be compressed?

Value

A set of replicate weights

References

Canty AJ, Davison AC. (1999) Resampling-based variance estimation for labour force surveys. The Statistician 48:379-391