Skip to main content

kernels.fit_mack()

Fit the distribution-free chain ladder on a single-cohort Triangle.

Usage

Source

kernels.fit_mack(
    triangle,
    *,
    loss_field="paid_loss",
    as_of=None,
    sigma_rule="mack",
    zero_cells=None,
    average="volume",
    links=None
)

as_of slices the backtest diagonal first (the training window); the triangle must hold exactly one segment combination. sigma_rule selects how the last development step’s variance is estimated - see _estimate_factors. zero_cells, average and links are as in fit_mack_grid().