pastas.stats.metrics.aicc
=========================

.. py:function:: pastas.stats.metrics.aicc(obs: pandas.Series | None = None, sim: pandas.Series | None = None, res: pandas.Series | None = None, missing: str = 'drop', nparam: int = 1) -> float

   
   Compute the Akaike Information Criterium with second order
   bias correction for the number of observations (AICc)

   :param obs: Series with the observed values.
   :type obs: pandas.Series, optional
   :param sim: The Series with the simulated values.
   :type sim: pandas.Series, optional
   :param res: 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.
   :type res: pandas.Series, optional
   :param nparam: number of calibrated parameters.
   :type nparam: int, optional
   :param missing: string with the rule to deal with missing values. Only "drop" is
                   supported now.
   :type missing: str, optional

   .. rubric:: Notes

   The corrected Akaike Information Criterium (AICc)
   :cite:p:`sugiura_further_1978` is computed as follows:

   .. math:: \text{AIC} = -2 log(L) + 2 nparam - (2 nparam (nparam + 1) / (nobs - nparam - 1))

   where :math:`n_{param}` is the number of calibration parameters, nobs is
   the number of observations and L is the likelihood function for the model.
   In the case of ordinary least squares:

   .. math:: log(L) = - (nobs / 2) * log(RSS / -nobs)

   where RSS denotes the residual sum of squares.















   ..
       !! processed by numpydoc !!