Use piping, verbs like 'group_by' and 'summarize', and other 'dplyr' inspired syntactic style when calculating summary statistics on survey data using functions from the 'survey' package.
srvyr focuses on calculating summary statistics from survey data, such as the mean, total or quantile. It allows for the use of many dplyr verbs, such as
mutate, the convenience of pipe-able functions, lazyeval's style of non-standard evaluation and more consistent return types than the survey package.
You can try it out:
To create a
tbl_svy object (the core concept behind the srvyr package), use the function
as_survey_design() with the bare column names of the names you would use in
library(survey)data(api)dstrata <- apistrat %>%as_survey_design(strata = stype, weights = pw)
Now many of the dplyr verbs are available.
mutate() if you want to add or modify a variable.
dstrata <- dstrata %>%mutate(api_diff = api00 - api99)
summarise() calculates summary statistics such as mean, total, quantile or ratio.
dstrata %>%summarise(api_diff = survey_mean(api_diff, vartype = "ci")))
group_by() if you want to summarise by groups.
dstrata %>%group_by(stype) %>%summarise(api_diff = survey_mean(api_diff, vartype = "ci")))
You can still use functions from the survey package if you'd like to:
svyglm(api99 ~ stype, dstrata)
If you'd like to contribute, please let me know! I started this as a way to learn about R package development, so you'll have to bear with me as I learn, but I would appreciate bug reports, pull requests or other suggestions!
Fixed a problem with confidence levels not being passed into quantiles
Added deff parameter to
a df parameter to those functions and
mutate match dplyr's behavior when arguments aren't named
cascade summarizes groups, and cascades to create
summary statistics of groups of groups.
Fixed a bug for confidence intervals for
survey_total() on groups.
Fixed some issues with the upcoming version of dplyr.