pastas.stats.metrics.bic#

pastas.stats.metrics.bic(obs: pandas.Series | None = None, sim: pandas.Series | None = None, res: pandas.Series | None = None, missing: str = 'drop', nparam: int = 1) → float#

Compute the Bayesian Information Criterium (BIC).

Parameters:

  • obs (pandas.Series, optional) – Series with the observed values.

  • sim (pandas.Series, optional) – The Series with the simulated values.

  • res (pandas.Series, optional) – The Series with the residual values. If time series for the residuals are provided, the sim and obs arguments are ignored. Note that the residuals must be computed as obs - sim here.

  • nparam (int, optional) – number of calibrated parameters.

  • missing (str, optional) – string with the rule to deal with missing values. Only “drop” is supported now.

Notes

The Bayesian Information Criterium (BIC) [Akaike, 1979] is computed as follows:

\[\text{BIC} = -2 log(L) + n_{param} * log(N)\]

where \(n_{param}\) is the number of calibration parameters.