infocrit

Calculate Akaike and Bayesian information criteria

Syntax

   [aic,bic] = infocrit(L,k,m)

Arguments

See also Common variable names and data structures.

input

   L          maximum log-likelihood
   k          number of free parameters
   m          number of observations

output

   aic        AIC value
   bic        BIC value

Description

Calculates the Akaike and Bayesian information criteria from the maximised log-likelihood of a model [1]. For the Akaike information criterion, the finite sample bias-corrected form ("AICc") of Hurvich and Tsai [2] is calculated.

References

[1] K. P. Burnham and D. R. Anderson, "Model Selection and Multimodel Inference: A Practical Information-Theoretic Approach", 2nd ed., Springer-Verlag, 2002.

[2] C. M. Hurvich and C.-L. Tsai, "Regression and time series model selection in small samples", Biometrika, 76, 1989.

See also

tsdata_to_infocrit