Measure to compare true observed response with predicted response in regression tasks.
Note that this is an unaggregated measure, returning the losses per observation.
Arguments
- truth
(
numeric()
)
True (observed) values. Must have the same length asresponse
.- response
(
numeric()
)
Predicted response values. Must have the same length astruth
.- a
(
numeric(1)
)
Shape parameter controlling asymmetry. Negative values penalize overestimation more, positive values penalize underestimation more. Asa
approaches 0, the loss resembles squared error loss. Default is-1
.- b
(
numeric(1)
)
Positive scaling factor for the loss. Larger values increase the loss magnitude. Default is1
.- ...
(
any
)
Additional arguments. Currently ignored.
Details
The Linear-Exponential Loss is defined as $$ b (\exp (t_i - r_i) - a (t_i - r_i) - 1), $$ where \(a \neq 0, b > 0\).
Meta Information
Type:
"regr"
Range (per observation): \([0, \infty)\)
Minimize (per observation):
TRUE
Required prediction:
response
References
Varian, R. H (1975). “A Bayesian Approach to Real Estate Assessment.” In Fienberg SE, Zellner A (eds.), Studies in Bayesian Econometrics and Statistics: In Honor of Leonard J. Savage, 195–208. North-Holland, Amsterdam.