util_dist_selection {dataquieR}

Utility function to characterize study variables

Description

This function summarizes some properties of measurement variables.

Usage

util_dist_selection(study_data, val_lab = NULL)

Arguments

study_data

study data, pre-processed with prep_prepare_dataframes to replace missing value codes by NA

val_lab

matching metadata column containing the VALUE_LABELS as vector (if available)

Value

data frame with one row for each variable in the study data and the following columns: Variables contains the names of the variables IsInteger contains a check whether the variable contains integer values only (variables coded as factor will be converted to integers) IsMultCat contains a check for variables with integer or string values whether there are more than two categories NCategory contains the number of distinct values for variables with values coded as integers or strings (excluding NA and empty entries) AnyNegative contains a check whether the variable contains any negative values NDistinct contains the number of distinct values PropZeroes reports the proportion of zeroes

See Also

Other metadata_management: CAN_THIS_BE_REMOVED_util_combine_missing_lists(), util_find_free_missing_code(), util_find_var_by_meta(), util_get_var_att_names_of_level(), util_get_vars_in_segment(), util_looks_like_missing(), util_no_value_labels(), util_validate_known_meta(), util_validate_missing_lists()