As we may know, the capacity of a model to overfit could easily increase by an increase in the complexity of that model (take complexity roughly as a number of parameters). To handle this problem, there are some model selection criteria that are suggested by statisticians. As described in Wikipedia,

The AIC and BIC are both methods of assessing model fit penalized for the number of estimated parameters.

I am wondering if anyone used methods like Hannan–Quinn information criterion and Kashyap information criterion (KIC).

I am really having trouble understanding the intuition behind KIC. I mean how KIC is using Fisher information matrix and how these methods are used for Model Selection


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.