~ Bayesian information criterion

The Bayesian information criterion (BIC) or Schwarz information criterion (SIC) is a criterion for model selection in a finite set of models. We prefer the model with the lowest BIC. Its general defenition is1

$$ \text{BIC} = \log N\cdot d - 2\ \text{loglik} ,$$

where $N$ is the number of data points $d$ is the number of parameters estimated by the model and $\text{loglik}$ is the log of the maximized likelihood function.

Page made with mdzk