RAE: Relative absolute error

In measures: Performance Measures for Statistical Learning

Description

Defined as sum_of_absolute_errors / mean_absolute_deviation. Undefined for single instances and when every truth value is identical. In this case the output will be NA.

Usage

RAE(truth, response)

Arguments

truth	[numeric] vector of true values
response	[numeric] vector of predicted values

Examples

n = 20
set.seed(123)
truth = rnorm(n)
response = rnorm(n)
RAE(truth, response)

measures documentation built on Jan. 19, 2021, 5:08 p.m.