Table 2.

Different forms of a model selection estimator

Selection Criterion	Equation
Akaike Information Criterion (AIC)	2k + nln(RSS/n)
Sample size corrected AIC (AICc)	AIC + (2k2 + 2k)/(n − k − 1)
Bayesian Information Criterion (BIC)	nln(RSS/n) + kln(n)

k is the number of parameters

n is the number of data points

RSS is the residual sum of squares: RSS = $\sum _{i=1}^n{\left(I_{\mathit{obs}}-I_{\mathit{\text{calc}}}\right)}^2$