performance (version 0.9.1)

r2_zeroinflated: R2 for models with zero-inflation

Description

Calculates R2 for models with zero-inflation component, including mixed effects models.

Usage

r2_zeroinflated(model, method = c("default", "correlation"))

Value

For the default-method, a list with the R2 and adjusted R2 values. For method = "correlation", a named numeric vector with the correlation-based R2 value.

Arguments

model

A model.

method

Indicates the method to calculate R2. See 'Details'. May be abbreviated.

Details

The default-method calculates an R2 value based on the residual variance divided by the total variance. For method = "correlation", R2 is a correlation-based measure, which is rather crude. It simply computes the squared correlation between the model's actual and predicted response.

Examples

# \donttest{
if (require("pscl")) {
  data(bioChemists)
  model <- zeroinfl(
    art ~ fem + mar + kid5 + ment | kid5 + phd,
    data = bioChemists
  )

  r2_zeroinflated(model)
}
# }