Create a tbl_svy survey object using replicate weights

Create a survey object with replicate weights.

as_survey_rep(.data, ...)

# S3 method for data.frame
as_survey_rep(
  .data,
  variables = NULL,
  repweights = NULL,
  weights = NULL,
  type = c("BRR", "Fay", "JK1", "JKn", "bootstrap", "successive-difference", "ACS",
    "other"),
  combined_weights = TRUE,
  rho = NULL,
  bootstrap_average = NULL,
  scale = NULL,
  rscales = NULL,
  fpc = NULL,
  fpctype = c("fraction", "correction"),
  mse = getOption("survey.replicates.mse"),
  degf = NULL,
  ...
)

# S3 method for tbl_lazy
as_survey_rep(
  .data,
  variables = NULL,
  repweights = NULL,
  weights = NULL,
  type = c("BRR", "Fay", "JK1", "JKn", "bootstrap", "successive-difference", "ACS",
    "other"),
  combined_weights = TRUE,
  rho = NULL,
  bootstrap_average = NULL,
  scale = NULL,
  rscales = NULL,
  fpc = NULL,
  fpctype = c("fraction", "correction"),
  mse = getOption("survey.replicates.mse"),
  degf = NULL,
  ...
)

# S3 method for svyrep.design
as_survey_rep(.data, ...)

# S3 method for survey.design2
as_survey_rep(
  .data,
  type = c("auto", "JK1", "JKn", "BRR", "bootstrap", "subbootstrap", "mrbbootstrap",
    "Fay"),
  rho = 0,
  fpc = NULL,
  fpctype = NULL,
  ...,
  compress = TRUE,
  mse = getOption("survey.replicates.mse")
)

# S3 method for tbl_svy
as_survey_rep(
  .data,
  type = c("auto", "JK1", "JKn", "BRR", "bootstrap", "subbootstrap", "mrbbootstrap",
    "Fay"),
  rho = 0,
  fpc = NULL,
  fpctype = NULL,
  ...,
  compress = TRUE,
  mse = getOption("survey.replicates.mse")
)

Arguments

.data: A data frame (which contains the variables specified below)
...: ignored
variables: Variables to include in the design (default is all)
repweights: Variables specifying the replication weight variables
weights: Variables specifying sampling weights
type: Type of replication weights
combined_weights: TRUE if the repweights already include the sampling weights. This is usually the case.
rho: Shrinkage factor for weights in Fay's method
bootstrap_average: For type = "bootstrap", if the bootstrap weights have been averaged, gives the number of iterations averaged over.
scale, rscales: Scaling constant for variance, see svrepdesign for more information.
fpc: Variables specifying a finite population correction, see svrepdesign for more details.
fpctype: Finite population correction information
mse: if TRUE, compute variances based on sum of squares around the point estimate, rather than the mean of the replicates
degf: Design degrees of freedom: a single number, or NULL, in which case a value will be computed automatically, which can be slow for very large data sets. See svrepdesign for more details.
compress: if TRUE, store replicate weights in compressed form (if converting from design)

Value

An object of class tbl_svy

Details

If provided a data.frame, it is a wrapper around svrepdesign. All survey variables must be included in the data.frame itself. Variables are selected by using bare column names, or convenience functions described in select.

If provided a svyrep.design object from the survey package, it will turn it into a srvyr object, so that srvyr functions will work with it

If provided a survey design (survey.design2 or tbl_svy), it is a wrapper around as.svrepdesign, and will convert from a survey design to replicate weights.

Examples

# Examples from ?survey::svrepdesign()
library(survey)
library(dplyr)
data(scd)
# use BRR replicate weights from Levy and Lemeshow
scd <- scd %>%
  mutate(rep1 = 2 * c(1, 0, 1, 0, 1, 0),
         rep2 = 2 * c(1, 0, 0, 1, 0, 1),
         rep3 = 2 * c(0, 1, 1, 0, 0, 1),
         rep4 = 2 * c(0, 1, 0, 1, 1, 0))

scdrep <- scd %>%
  as_survey_rep(type = "BRR", repweights = starts_with("rep"),
                combined_weights = FALSE)
#> Warning: No sampling weights provided: equal probability assumed

# dplyr 0.7 introduced new style of NSE called quosures
# See `vignette("programming", package = "dplyr")` for details
repwts <- quo(starts_with("rep"))
scdrep <- scd %>%
  as_survey_rep(type = "BRR", repweights = !!repwts,
                combined_weights = FALSE)
#> Warning: No sampling weights provided: equal probability assumed