MetricsWeighted (version 0.2.0)

deviance_normal: Normal Deviance

Description

Weighted average of (unscaled) unit normal deviance. This equals the weighted mean-squared error, see e.g. [1]. The smaller the deviance, the better.

Usage

deviance_normal(actual, predicted, w = NULL, ...)

Arguments

actual

Observed values.

predicted

Predicted values.

w

Optional case weights.

...

Further arguments passed to mse.

Value

A numeric vector of length one.

References

[1] Jorgensen, B. (1997). The Theory of Dispersion Models. Chapman & Hall/CRC. ISBN 978-0412997112.

See Also

deviance_tweedie, mse.

Examples

# NOT RUN {
deviance_normal(1:10, c(1:9, 12))
deviance_normal(1:10, c(1:9, 12), w = rep(1, 10))
deviance_tweedie(1:10, c(1:9, 12), tweedie_p = 0)
deviance_normal(1:10, c(1:9, 12), w = 1:10)
# }