com_qualified_item_missingness: Compute Indicators for Qualified Item Missingness

In dataquieR: Data Quality in Epidemiological Research

Compute Indicators for Qualified Item Missingness

Description

Compute Indicators for Qualified Item Missingness

Usage

com_qualified_item_missingness(
  resp_vars,
  study_data,
  meta_data,
  label_col = NULL,
  expected_observations = c("HIERARCHY", "ALL", "SEGMENT")
)

Arguments

resp_vars	variable list the name of the measurement variables
study_data	data.frame the data frame that contains the measurements
meta_data	data.frame the data frame that contains metadata attributes of study data
label_col	variable attribute the name of the column in the metadata with labels of variables
expected_observations	enum HIERARCHY | ALL | SEGMENT. Report the number of observations expected using the old PART_VAR concept. See com_item_missingness for an explanation.

Value

list list with entries:

Examples

## Not run: 
prep_load_workbook_like_file("inst/extdata/Metadata_example_v3-6.xlsx")
clean <- prep_get_data_frame("item_level")
clean <- subset(clean, `Metadata name` == "Example" &
  !dataquieR:::util_empty(VAR_NAMES))
clean$`Metadata name` <- NULL
clean[, "MISSING_LIST_TABLE"] <- "missing_matchtable1"
prep_add_data_frames(item_level = clean)
clean <- prep_get_data_frame("missing_matchtable1")
clean <- clean[clean$`Metadata name` == "Example", , FALSE]
clean <-
  clean[suppressWarnings(as.character(as.integer(clean$CODE_VALUE)) ==
    as.character(clean$CODE_VALUE)), , FALSE]
clean$CODE_VALUE <- as.integer(clean$CODE_VALUE)
clean <- clean[!is.na(clean$`Metadata name`), , FALSE]
clean$`Metadata name` <- NULL
prep_add_data_frames(missing_matchtable1 = clean)
ship <- prep_get_data_frame("ship")
number_of_mis <- ceiling(nrow(ship) / 20)
resp_vars <- sample(colnames(ship), ceiling(ncol(ship) / 20), FALSE)
mistab <- prep_get_data_frame("missing_matchtable1")
valid_replacement_codes <-
  mistab[mistab$CODE_INTERPRET != "P", "CODE_VALUE",
    drop =
    TRUE] # sample only replacement codes on item level. P uses the actual
          # values
for (rv in resp_vars) {
  values <- sample(as.numeric(valid_replacement_codes), number_of_mis,
    replace = TRUE)
  if (inherits(ship[[rv]], "POSIXct")) {
    values <- as.POSIXct(values, origin = min(as.POSIXct(Sys.Date()), 0))
  }
  ship[sample(seq_len(nrow(ship)), number_of_mis, replace = FALSE), rv] <-
    values
}
com_qualified_item_missingness(resp_vars = NULL, ship, "item_level", LABEL)
com_qualified_item_missingness(resp_vars = "Diabetes Age onset", ship,
  "item_level", LABEL)
com_qualified_item_missingness(resp_vars = NULL, "study_data", "meta_data",
  LABEL)
study_data <- ship
meta_data <- prep_get_data_frame("item_level")
label <- LABEL

## End(Not run)

dataquieR documentation built on July 26, 2023, 6:10 p.m.