reserving.TailLogLinear

R ChainLadder’s tail = TRUE rule (its tailfactor function).

Usage

reserving.TailLogLinear()

When the third- and second-last factors multiply to more than 1.0001, ln(f - 1) is regressed on the development index over the factors above 1 and the next 100 extrapolated factors are multiplied; otherwise the tail is 1. A tail above 2 is reset to 1, as R does.

Examples

>>> from prospicio.reserving import Mack, TailLogLinear, Triangle
>>> tri = Triangle.from_long(
...     [2020] * 4 + [2021] * 3 + [2022] * 2 + [2023],
...     [12, 24, 36, 48, 12, 24, 36, 12, 24, 12],
...     [100.0, 150.0, 165.0, 170.0, 110.0, 170.0, 180.0, 120.0, 175.0, 130.0],
... )
>>> fit = Mack(tail=TailLogLinear()).fit(tri, "values")
>>> fit.tail > 1.0 and fit.standard_error[0] > 0.0

True