AICc value derivation (Akaike information criteria for finite samples)

[mertcan]

Hi everyone, initially let me introduce a concept widely used in ARIMA in the following. $$AICc = AIC + \frac {2k^2+2k} {n-k-1}$$ where n denotes the sample size and k denotes the number of parameters. Thus, AICc is essentially AIC with an extra penalty term for the number of parameters. Note that as n → ∞, the extra penalty term converges to 0, and thus AICc converges to AIC. I have derived AIC value but could provide me with the proof of the extra term $$\frac {2k^2+2k} {n-k-1}$$ particularly used in finite samples?

 

[mertcan]

Hi everyone would you mind if I asked why I can not receive any response?

 

[mertcan]

I am still waiting for your responses?