distributions.claim_count()

The claim count with this mean and dispersion Var[N] / E[N]:

Usage

distributions.claim_count(
    mean,
    dispersion,
)

binomial below 1, Poisson at 1, negative binomial above 1.

A binomial needs a whole number of trials, so below 1 the trials are mean / (1 - dispersion) rounded up: the mean is kept and the dispersion moves up to the nearest attainable value.

Parameters

mean: float

dispersion: float

Positive.

Returns

Binomial or Poisson or NegativeBinomial

Examples

>>> from prospicio.distributions import claim_count
>>> claim_count(4.0, 2.5)

NegativeBinomial(r=2.6666666666666665, beta=1.5)