wpa (version 1.4.3)

create_IV: Calculate Information Value for a selected outcome variable

Description

Specify an outcome variable and return IV outputs. All numeric variables in the dataset are used as predictor variables.

Usage

create_IV(
  data,
  predictors = NULL,
  outcome,
  bins = 5,
  siglevel = 0.05,
  return = "plot"
)

Arguments

data

A Person Query dataset in the form of a data frame.

predictors

A character vector specifying the columns to be used as predictors. Defaults to NULL, where all numeric vectors in the data will be used as predictors.

outcome

A string specifying a binary variable, i.e. can only contain the values 1 or 0.

bins

Number of bins to use in Information::create_infotables(), defaults to 5.

siglevel

Significance level to use in comparing populations for the outcomes, defaults to 0.05

return

String specifying what to return. This must be one of the following strings:

• "plot"

• "summary"

• "list"

• "plot-WOE"

• "IV"

See Value for more information.

Value

A different output is returned depending on the value passed to the return argument:

• "plot": 'ggplot' object. A bar plot showing the IV value of the top (maximum 12) variables.

• "summary": data frame. A summary table for the metric.

• "list": list. A list of outputs for all the input variables.

• "plot-WOE": A list of 'ggplot' objects that show the WOE for each predictor used in the model.

• "IV" returns the original Information object returned by Information::create_infotables().

See Also

Other Variable Association: IV_by_period(), IV_report(), plot_WOE()

Other Information Value: IV_by_period(), IV_report(), plot_WOE()

Examples

# NOT RUN {
# Return a summary table of IV
sq_data %>%
  dplyr::mutate(X = ifelse(Workweek_span > 40, 1, 0)) %>%
  create_IV(outcome = "X",
            predictors = c("Email_hours",
                           "Meeting_hours",
                           "Instant_Message_hours"),
            return = "plot")


# Return summary
sq_data %>%
  dplyr::mutate(X = ifelse(Collaboration_hours > 2, 1, 0)) %>%
  create_IV(outcome = "X",
            predictors = c("Email_hours", "Meeting_hours"),
            return = "summary")

# }