suppress: Suppress data according to APDE standards or custom requests...

In PHSKC-APDE/rads: Assisted computation of King County public health data

Suppress data according to APDE standards or custom requests & adding caution flag for high RSE

Description

Default suppression is according to APDE/DOH standards (https://www.doh.wa.gov/Portals/1/Documents/1500/SmallNumbers.pdf) Each dataset may have it's own more stringent standards. When the reference sheet of all suppression guidelines is made available, this code should be updated to use that resource.

This function expects data that has already been formatted for CHI

Usage

suppress(
  sup_data = NULL,
  suppress_range = c(0, 9),
  secondary = FALSE,
  secondary_ids = c("tab", "indicator_key", "cat1", "cat2_group", "year"),
  secondary_exclude,
  flag_only = FALSE
)

Arguments

sup_data	a data.table or data.frame. Must contain the data to be suppressed with standard metric names, i.e., mean, median, sum, rate, lower, upper, se, rse, numerator, denominator, proportion
suppress_range	integer vector of length 2. They specify the minimum and maximum range for suppression.
secondary	logical (T, TRUE, F, or FALSE) indicating whether secondary suppression should be run
secondary_ids	character vector of column names which are used to define groups for secondary suppression. Note, this should not include the most granular level. For example, if you wanted secondary suppression for race/ethnicity where category == race/ethnicity and group == AIAN, Asian, Black, etc., you should have secondary_ids = c("geography", "category") rather than secondary_ids = c("geography", "category", "group")
secondary_exclude	an expression identifying the rows to be filtered / excluded from secondary suppression because the categories are not mutually exclusive (e.g., race3)
flag_only	logical (T, TRUE, F, or FALSE) indicating whether data to be suppressed should be flagged without setting estimates to NA

Value

a data.table with suppression applied to CHI standard columns.

Examples

  set.seed(98104)
  dt <- data.table::data.table(
    chi_year = rep(2018, 100),
    mean = rnorm(100, .25, .05),
    numerator = round(rnorm(100, 20, 9), 0)
  )
  table(dt$numerator) # before
  newdt <- suppress(dt, suppress_range = c(0, 20), secondary = FALSE) # apply suppression
  table(newdt$numerator) # after

PHSKC-APDE/rads documentation built on April 14, 2025, 10:47 a.m.