as_survey
can be used to create a tbl_svy
using design information
(as_survey_design
), replicate weights (as_survey_rep
),
or a two phase design (as_survey_twophase
), or an object created by the
survey package.
as_survey(.data, ...) # S3 method for tbl_svy as_survey(.data, ...) # S3 method for data.frame as_survey(.data, ...) # S3 method for tbl_lazy as_survey(.data, ...) # S3 method for survey.design2 as_survey(.data, ...) # S3 method for svyrep.design as_survey(.data, ...) # S3 method for twophase2 as_survey(.data, ...)
.data | a data.frame or an object from the survey package |
---|---|
... | other arguments, see other functions for details |
a tbl_svy
See vignette("databases", package = "dplyr")
for more information on setting up databases in dplyr.
#>#>#>#> #>#>#> #>#> #>#>#> #>#>#> #>data(api) # stratified sample dstrata <- apistrat %>% as_survey(strata = stype, weights = pw) # Examples from ?survey::svrepdesign data(scd) # use BRR replicate weights from Levy and Lemeshow scd$rep1 <- 2 * c(1, 0, 1, 0, 1, 0) scd$rep2 <- 2 * c(1, 0, 0, 1, 0, 1) scd$rep3 <- 2 * c(0, 1, 1, 0, 0, 1) scd$rep4 <- 2 * c(0, 1, 0, 1, 1, 0) scdrep <- scd %>% as_survey(type = "BRR", repweights = starts_with("rep"), combined_weights = FALSE)#> Warning: No sampling weights provided: equal probability assumed# Examples from ?survey::twophase # two-phase simple random sampling. data(pbc, package="survival") pbc <- pbc %>% mutate(randomized = !is.na(trt) & trt > 0, id = row_number()) d2pbc <- pbc %>% as_survey(id = list(id, id), subset = randomized) # dplyr 0.7 introduced new style of NSE called quosures # See `vignette("programming", package = "dplyr")` for details st <- quo(stype) wt <- quo(pw) dstrata <- apistrat %>% as_survey(strata = !!st, weights = !!wt)