Bayesian Information Criterion (BIC)

Keith Tan


BIC = nxln(SSE/n) + ln(n)x(k+1)

n: number of observations, k: number of parameters

BIC is a measure of how well the model fits the data, taking into account the complexity of the model and the size of the sample. A lower BIC value indicates a better fitting model, as it suggests that the model is able to accurately predict the dependent variable with a lower number of parameters and a larger sample size.

Also Known As:
Schwarz’s Bayesian information criteria
« Back to Index