metric_mae: metric_mae

In gloverd2/admr: Contains standard functions for Admiral Advance Analytics

Description

Returns the mean absolute error for a set of predictions. Note: Predictions should be annualized (independent of exposure) Note: Low is good

Usage

metric_mae(actual, predicted, weight = NULL, na.rm = FALSE, rebase = FALSE)

Arguments

actual	Array[Numeric] - Values we are aiming to predict.
predicted	Array[Numeric] - Values that we have predicted.
weight	Optional: Array[Numeric] - Weighting of predictions. If NULL even weighting is used
na.rm	Optional: boolean - If FALSE function will return NA is any value in NA
rebase	Optional: boolean - If TRUE predictions weighted mean will be rebased to match actual mean
family	can be NULL has this metric doesn't depend on family

Value

Numeric: value of mean absolute error

See Also

Other Metrics: metric_deviance(), metric_nloglik(), metric_pode(), metric_pove(), metric_rmse()

Examples

set.seed(666)
actual <- rep(10, 10)
predicted <- rnorm(n = 10, mean = 10, sd = 1)
weight <- pmax(rnorm(n = 10, mean = 10, sd = 1) , 0)

metric_mae(actual, predicted)
metric_mae(actual, predicted, weight)

gloverd2/admr documentation built on Dec. 2, 2020, 11:16 p.m.