Information Criterion Families of Prior Distribution for Coefficients in BMA Models

Creates an object representing the prior distribution on coefficients for BAS.

Usage

IC.prior(penalty)

Arguments

penalty

a scalar used in the penalized loglikelihood of the form penalty*dimension

Value

returns an object of class "prior", with the family and hyerparameters.

Details

The log marginal likelihood is approximated as -2*(deviance + penalty*dimension). Allows alternatives to AIC (penalty = 2) and BIC (penalty = log(n)). For BIC, the argument may be missing, in which case the sample size is determined from the call to `bas.glm` and used to determine the penalty.

See also

g.prior

Other beta priors: CCH(), EB.local(), Jeffreys(), TG(), beta.prime(), g.prior(), hyper.g(), hyper.g.n(), intrinsic(), robust(), tCCH(), testBF.prior()

Author

Merlise Clyde

Examples

IC.prior(2)
#> $family
#> [1] "IC"
#> 
#> $class
#> [1] "IC"
#> 
#> $hyper
#> [1] 2
#> 
#> $hyper.parameters
#> $hyper.parameters$penalty
#> [1] 2
#> 
#> 
#> attr(,"class")
#> [1] "prior"
aic.prior()
#> $family
#> [1] "AIC"
#> 
#> $class
#> [1] "IC"
#> 
#> $hyper.parameters
#> $hyper.parameters$penalty
#> [1] 2
#> 
#> 
#> $hyper
#> [1] 2
#> 
#> attr(,"class")
#> [1] "prior"
bic.prior(100)
#> $family
#> [1] "BIC"
#> 
#> $class
#> [1] "IC"
#> 
#> $hyper.parameters
#> $hyper.parameters$penalty
#> [1] 4.60517
#> 
#> $hyper.parameters$n
#> [1] 100
#> 
#> 
#> $hyper
#> [1] 4.60517
#> 
#> attr(,"class")
#> [1] "prior"