reserving.ChainLadder
The chain-ladder method: each origin’s latest value projected to
Usage
reserving.ChainLadder()ultimate with age-to-age factors estimated from the triangle and a tail.
Parameters
average: (volume, simple, regression) = "volume"-
How link ratios are averaged into one factor per age: volume weighted, their mean, or least squares through the origin (Mack’s alpha of 1, 0 and 2).
sigma_interpolation: (log - linear, mack) = "log-linear"-
How a variance parameter with a single link ratio is filled in.
tail: (float, TailConstant, TailCurve, TailBondy or TailLogLinear)- Development past the oldest age: a number is a constant factor from the oldest age to ultimate. No tail (a factor of 1) by default.
Examples
>>> from prospicio.reserving import ChainLadder, Triangle
>>> tri = Triangle.from_long([2020, 2020, 2021], [12, 24, 12], {"paid": [100.0, 150.0, 200.0]})
>>> fit = ChainLadder().fit(tri, "paid")
>>> fit.ldf, fit.ultimate, fit.total_reserve([1.5], [150.0, 300.0], 100.0)
Attributes
| Name | Description |
|---|---|
| average | How link ratios are averaged. |
| sigma_interpolation | How unestimable variance parameters are filled in. |
| tail | The tail: a constant factor as a number, otherwise its estimator. |
average
How link ratios are averaged.
average: str
sigma_interpolation
How unestimable variance parameters are filled in.
sigma_interpolation: str
tail
The tail: a constant factor as a number, otherwise its estimator.
tail: Any
Methods
| Name | Description |
|---|---|
| fit() | Fits one measure column in every segment of a triangle, each on its |
fit()
Fits one measure column in every segment of a triangle, each on its
Usage
fit(triangle, column)own.
Parameters
triangle: Triangle-
Cumulative or incremental, with any number of segments.
column: str
Returns
ChainLadderFit
Raises
ValueError- If the column is unknown, a factor cannot be estimated or the tail cannot be fitted (a constant that is not positive, a curve with fewer than two factors above 1 to fit); with keys, the message names the segment.