modelSelection: Model selection using different criteria

In JieGroup/bc: Model Selection with Bridge Criterion

Description

This function uses specified criteria to select the optimal subset from a list of subsets, given design matrix X and observation y.

Usage

modelSelection(loglik, dim, n, criteria, penaltyBC = NULL)

Arguments

loglik	Vector of (unnormalized) log-likelihood values evaluated for each model evaluted at the maximum likelihood estimator
dim	Vector of dimension (or number of free unknown parameters) of each model
n	Integer of sample size
criteria	Vector of strings ('AIC, BIC, BC') indicating criteria to use
penaltyBC	Vector of non-default penalty values in using BC, default to NULL so that only the suggested value n^(1/3) will be considered

Value

Vector (cri_opt) of indices of candidate models

Vector (cri_name) of the criteria used

Vector (PI) of parametricness index, default to one value that corresponds to the default BC penalty

Examples

res <- modelSelection(loglik = c(4.1, 5.2, 6.3), dim = c(1, 2, 3), n = 100, 
criteria='AIC, BIC, BC', penaltyBC=NULL)

JieGroup/bc documentation built on June 1, 2019, 12:48 p.m.