risk.entropic()

Entropic risk measure (1 / theta) log E[exp(theta X)]: the certainty

Usage

risk.entropic(
    dist,
    theta,
)

equivalent of a loss under exponential utility.

It rises from the mean (theta -> 0) to the largest draw (theta -> inf); for a normal loss it is mu + theta sigma**2 / 2.

Parameters

dist: Sampled, PredictiveDistribution or list of float

A predictive distribution is measured on its total.

theta: float

Risk aversion, positive.

Returns

float

Examples

>>> import math
>>> from prospicio.risk import entropic
>>> round(entropic([0.0, 1.0], math.log(2.0)), 12) == round(math.log2(1.5), 12)

True