se_dummy is an internal helper function used to generate dummy (0/1) variables
based on the combinations of multiple categorical variables. It is primarily used by
se_prop() to support grouped dummy encoding.
Usage
se_dummy(data, ..., sep = "_")
Arguments
- data
A data frame or tibble.
- ...
One or more categorical columns (unquoted or quoted) whose combinations will be
used to generate joint dummy variables.
- sep
A character string to separate combined category names (default is "_").
Value
A tibble including all original data columns and additional dummy columns
representing all unique combinations of the provided categorical variables.
Examples
df <- tibble::tibble(gender = c("male", "female"), country = c("US", "Other"))
se_dummy(df, gender, country)
#> # A tibble: 2 × 4
#> gender country joint_female_Other joint_male_US
#> <chr> <chr> <int> <int>
#> 1 male US 0 1
#> 2 female Other 1 0
