make_bic_penalty#
- make_bic_penalty(n_params: int, n: int, additional_cpts: int = 1) float [source][source]#
Create a Bayesian Information Criterion (BIC) penalty.
The BIC penalty is a constant penalty given by
(n_params + additional_cpts) * log(n)
, where n is the sample size and n_params is the number of parameters per segment in the model across all variables, and additional_cpts is the number of additional change point parameters per segment. For change detection, this is 1.- Parameters:
- n_paramsint
Number of model parameters per segment.
- nint
Sample size.
- additional_cpts: int, optional, default=1
Number of additional change point parameters per segment. For change detection, this is 1.
- Returns:
- float
The BIC penalty value.