aggregate.panjer()

Aggregate loss S = X_1 + ... + X_N by Panjer’s recursion.

Usage

aggregate.panjer(
    frequency,
    severity,
    points,
)

Parameters

frequency: (Poisson, NegativeBinomial or Binomial)

severity: Grid

Severity on a grid; the result uses its step.

points: int

Points in the aggregate grid.

Returns

tuple of (Grid, CompoundReport)

Raises

ValueError

If points is 0 or P(S = 0) underflows (use fft).

Examples

>>> from prospicio.aggregate import panjer
>>> from prospicio.distributions import Grid, Poisson
>>> sev = Grid(1.0, [0.1, 0.3, 0.25, 0.2, 0.1, 0.05])
>>> agg, report = panjer(Poisson(3.0), sev, 100)
>>> round(agg.mean(), 6)

6.15