tsDyn (version 0.7-30)

BIC: Bayesian (Schwarz) information criterion

Description

Function calling AIC witk k= log(n) as default instead of k=2.

Usage

BIC(object, ...,k)

Arguments

object

object of class lm or nlar

...

further arguments passed to AIC

k

penalty term

Value

• Numeric value with the corresponding BIC

Details

This is just a direct function to use the BIC criterion from the AIC. The penalty term is: k=log(N). N is the number of observations in the initial series and hence does not correspond to the number of fitted observations with time series due to the lagged ariables.

Examples

mod.linear<-linear(log10(lynx), m=2)
mod.setar <- setar(log10(lynx), m=2, thDelay=1, th=3.25)

AIC(mod.linear)
AIC(mod.setar)

BIC(mod.linear)
BIC(mod.setar)