Draw probability sample proportional to size (PPS) from single study

Sampling handler for drawing proportional sample with given characteristics from individual study population

sample_pps(
  data,
  sampling_variable = "pps",
  drop_nonsampled = FALSE,
  target_n_pps = 400,
  n_clusters = target_n_pps,
  sampling_frame = NULL,
  strata = NULL,
  cluster = NULL,
  weights_type = c("absolute", "relative")
)

Arguments

data: pass-through population data frame
sampling_variable: character string that is used as prefix for all variables generated by proportional sampling. Default is 'pps'
drop_nonsampled: logical indicating whether to drop units that are not sampled. Default is FALSE
target_n_pps: target size of proportional sample
n_clusters: number of clusters
sampling_frame: character vector containing all binary vectors identifying sampling frame
strata: character vector containing name(s) of stratifying variables. Currently not implemented
cluster: character vector containing name(s) of all cluster variables
weights_type: character string giving the type of weights to compute. Can be one of "absolute" or "relative". Currently only absolute weights are calculated

Value

Population or sample data frame for single study with PPS sample characteristics added

[sampling_variable]: Sampling indicator
[sampling_variable]_frame: Indicator for sampling frame (respondents with 0 cannot be enrolled)
[sampling_variable]_strata: ID of respondent's strata
[sampling_variable]_strata_prop: Proportion of sampling frame in the strata to which respondent belongs
[sampling_variable]_cluster: ID of respondent's cluster
[sampling_variable]_cluster_prop: Proportion of strata in the cluster to which respondent belongs
[sampling_variable]_weight: Sampling weights