tab_functions: Tabulate counts and proportions

In R4EPI/tuni: Tables for Epidemiological Analysis

Tabulate counts and proportions

Description

Tabulate counts and proportions

Usage

tab_linelist(
  x,
  ...,
  strata = NULL,
  keep = TRUE,
  drop = NULL,
  na.rm = TRUE,
  prop_total = FALSE,
  row_total = FALSE,
  col_total = FALSE,
  wide = TRUE,
  transpose = NULL,
  digits = 1,
  pretty = TRUE
)

tab_survey(
  x,
  ...,
  strata = NULL,
  keep = TRUE,
  drop = NULL,
  na.rm = TRUE,
  prop_total = FALSE,
  row_total = FALSE,
  col_total = FALSE,
  wide = TRUE,
  transpose = NULL,
  digits = 1,
  method = "logit",
  deff = FALSE,
  pretty = TRUE
)

Arguments

x	a data.frame() or tbl_svy object
...	categorical variables to tabulate
strata	a stratifier to split the data
keep	a character vector specifying which values to retain in the tabulation. Defaults to TRUE, which keeps all the values.
drop	a character vector specifying which values to drop in the tabulation. Defaults to NULL, which keeps all values.
na.rm	When TRUE (default), missing (NA) values present in var will be removed from the data set with a warning, causing a change in denominator for the tabulations. Setting this to FALSE creates an explicit missing value called "(Missing)".
prop_total	if TRUE and strata is not NULL, then the totals of the rows will be reported as proportions of the total data set, otherwise, they will be proportions within the stratum (default).
row_total	create a new column with the total counts for each row of stratified data.
col_total	create a new row with the total counts for each column of stratified data.
wide	if TRUE (default) and strata is defined, then the results are presented in a wide table with each stratification counts and estimates in separate columns. If FALSE, then the data will be presented in a long format where the counts and estimates are presented in single columns. This has no effect if strata is not defined.
transpose	if wide = TRUE, then this will transpose the columns to the rows, which is useful when you stratify by age group. Default is NULL, which will not transpose anything. You have three options for transpose: transpose = "variable": uses the variable column, (dropping values if strata exists). Use this if you know that your values are all identical or at least identifiable by the variable name. transpose = "value" : uses the value column, (dropping variables if strata exists). Use this if your values are important and the variable names are generic placeholders. transpose = "both" : combines the variable and value columns. Use this if both the variables and values are important.
digits	(survey only) if pretty = FALSE, this indicates the number of digits used for proportion and CI
pretty	(survey only) if TRUE, default, the proportion and CI are merged
method	(survey only) a method from survey::svyciprop() to calculate the confidence interval. Defaults to "logit".
deff	a logical indicating if the design effect should be reported. Defaults to TRUE.

Value

a tibble::tibble() with a column for variables, a column for values, and counts and proportions. If strata is not NULL and wide = TRUE, then there will be separate columns for each strata for the counts and proportions. Survey data will report confidence intervals.

Examples

have_packages <- require("matchmaker") & require("epidict")

if (have_packages) {
  withAutoprint({

    # Simulating linelist data

    linelist <- epidict::gen_data("Measles", numcases = 1000, org = "MSF")
    measles_dict <- epidict::msf_dict("Measles", compact = FALSE)

    # Cleaning linelist data
    linelist_clean <- matchmaker::match_df(
      x = linelist,
      dictionary = measles_dict,
      from = "option_code",
      to = "option_name",
      by = "data_element_shortname",
      order = "option_order_in_set"
    )

    # get a descriptive table by sex
    tab_linelist(linelist_clean, sex)

    # describe prenancy statistics, but remove missing data from the tally
    tab_linelist(linelist_clean, trimester, na.rm = TRUE)

    # describe by symptom

    tab_linelist(linelist_clean,
      cough, nasal_discharge, severe_oral_lesions,
      transpose = "value"
    )
    # describe prenancy statistics, stratifying by vitamin A perscription
    tab_linelist(linelist_clean, trimester, sex,
      strata = prescribed_vitamin_a,
      na.rm = TRUE, row_total = TRUE
    )
  })
}

have_survey_packages <- require("survey") && require("srvyr")
if (have_survey_packages) {
  withAutoprint({
    data(api)

    # stratified sample
    surv <- apistrat %>%
      as_survey_design(strata = stype, weights = pw)

    s <- surv %>%
      tab_survey(awards, strata = stype, col_total = TRUE, row_total = TRUE, deff = TRUE)
    s

    # making things pretty
    s %>%
      # wrap all "n" variables in braces (note space before n).
      epikit::augment_redundant(" (n)" = " n") %>%
      # relabel all columns containing "prop" to "% (95% CI)"
      epikit::rename_redundant(
        "% (95% CI)" = ci,
        "Design Effect" = deff
      )

    # long data
    surv %>%
      tab_survey(awards, strata = stype, wide = FALSE)

    # tabulate binary variables
    surv %>%
      tab_survey(yr.rnd, sch.wide, awards, keep = "Yes")

    # stratify the binary variables
    surv %>%
      tab_survey(yr.rnd, sch.wide, awards,
        strata    = stype,
        keep      = "Yes"
      )

    # invert the tabulation
    surv %>%
      tab_survey(yr.rnd, sch.wide, awards,
        strata = stype,
        drop = "Yes",
        deff = TRUE,
        row_total = TRUE
      )
  })
}

R4EPI/tuni documentation built on March 20, 2023, 4:37 p.m.