Sample covariates using bootstrap

Usage

sample_covariates_bootstrap(
  data,
  n_subjects = nrow(data),
  conditional = NULL,
  seed = NULL,
  na.rm = TRUE,
  cat_covs = NULL,
  noise = NULL,
  ...
)

Arguments

data: data.frame (n x p) containing the original, observed, time-invariant covariates (ID should not be included) that will be used to inform the imputation.
n_subjects: number of simulated subjects, default is the number of subjects in the data.
conditional: list with conditional limits for sampled population. For continuous covariates, specify a numeric vector of length 2 giving the c(min, max) range, e.g. list("WT" = c(40, 60), "BMI" = c(15, 25)). For categorical covariates (those listed in cat_covs), specify a character vector of the allowed category values, e.g. list("SEX" = c("F")).
seed: integer random seed passed to set.seed() for reproducibility. Default NULL does not set a seed.
na.rm: logical. If TRUE (default), rows with NA in any column are dropped before sampling.
cat_covs: character vector of categorical covariates. Used to filter categorical conditional limits by value and to exclude these columns from the multiplicative noise jitter.
noise: optional single non-negative number giving the log-scale SD of multiplicative log-normal noise applied to the sampled continuous covariates (e.g. 0.05 for ~5%), to obscure the original values. NULL (default) applies no noise.
...: additional arguments (ignored).

Value

a data.frame with the simulated covariates, with n_subjects rows and p columns