statsmodels.tools.eval_measures.aic¶

statsmodels.tools.eval_measures.aic(llf, nobs, df_modelwc)[source]¶

Akaike information criterion

Parameters:

llf ({float, array_like}) – value of the loglikelihood
nobs (int) – number of observations
df_modelwc (int) – number of parameters including constant

Returns:

aic – information criterion

Return type:

References

https://en.wikipedia.org/wiki/Akaike_information_criterion