R/gpl1_sf.R

In scoringfunctions: A Collection of Loss Functions for Assessing Point Forecasts

Defines functions gpl1_sf

Documented in gpl1_sf

gpl1_sf <- function(x, y, p, b)
{
    err <- x^b - y^b
    
    (p * pmax(-err, 0) + (1 - p) * pmax(err, 0))/(abs(b))
}

Try the scoringfunctions package in your browser