resample_strat_uniform: Draw stratified random sample

In pat-s/sperrorest: Perform Spatial Error Estimation and Variable Importance Assessment

Draw stratified random sample

Description

resample_strat_uniform draws a stratified random sample (with or without replacement) from the samples in data. Stratification is over the levels of data[, param$response]. The same number of samples is drawn within each level.

Usage

resample_strat_uniform(
  data,
  param = list(strat = "class", nstrat = Inf, replace = FALSE)
)

Arguments

data	a data.frame, rows represent samples
param	a list with the following components: strat is either the name of a factor variable in data that defines the stratification levels, or a vector of type factor and length nrow(data); n is a numeric value specifying the size of the subsample; replace determines if sampling is with or without replacement

Details

If param$replace=FALSE, a subsample of size min(param$n,nrow(data)) will be drawn from data. If param$replace=TRUE, the size of the subsample is param$n.

Value

a data.frame containing a subset of the rows of data.

See Also

resample_uniform(), sample()

Examples

data(ecuador) # Muenchow et al. (2012), see ?ecuador
d <- resample_strat_uniform(ecuador,
  param = list(strat = "slides", nstrat = 100)
)
nrow(d) # == 200
sum(d$slides == "TRUE") # == 100

pat-s/sperrorest documentation built on June 6, 2023, 7:51 a.m.