PhylogeneticEM (version 1.0.0)

penalty_BaraudGiraudHuet_likelihood: Penalty function type Baraud Giraud Huet.

Description

penalty_BaraudGiraudHuet_likelihood is the penalty defined by : pen' = ntaxa * log(1 + pen/(ntaxa - K)) with pen = C * (ntaxa - K)/(ntaxa - K - 1) * EDkhi[K + 1; ntaxa - K - 1; exp(-Delta_K)/(K + 1)] and Delta = log(model_complexity) + log(K + 1) such that sum(exp(-Delta_K)) < infty.

Usage

penalty_BaraudGiraudHuet_likelihood(K, model_complexity, ntaxa, C = 1.1)

Arguments

K

the dimension of the model.

model_complexity

the complexity of the set of models with dimention K.

ntaxa

the number of tips.

C

a constant, C > 1. Default is C = 1.1 (as suggested in Baraud Giraud Huet (2009))

Value

value of the penalty.

Details

See Baraud Giraud Huet (2009, 2011). Must be applied to log-likelihood crierion. Function pen is computed using function penalty from package LINselect.

See Also

penalty_BirgeMassart_shape1, penalty_BirgeMassart_shape2