dynloglikMC {FitDynMix}R Documentation

Log-likelihood of a Lognormal-GPD dynamic mixture

Description

This function evaluates the log-likelihood of a Lognormal-GPD dynamic mixture, with Cauchy or exponential weight, approximating the normalizing constant via Monte Carlo simulation.

Usage

dynloglikMC(x, y, nreps, xiInst, betaInst, weight)

Arguments

x

if weight is equal to 'cau', (6 by 1) numerical vector: values of μc\mu_c, τ\tau, μ\mu, σ\sigma, ξ\xi, β\beta; if weight is equal to 'exp', (5 by 1) numerical vector: values of λ\lambda, μ\mu, σ\sigma, ξ\xi, β\beta.

y

vector: points where the function is evaluated.

nreps

non-negative integer: number of replications to be used in the computation of the integral in the normalizing constant.

xiInst

non-negative real: shape parameter of the instrumental GPD.

betaInst

non-negative real: scale parameter of the instrumental GPD.

weight

'cau' or 'exp': name of weight distribution.

Value

Log-likelihood of the lognormal-GPD mixture evaluated at y.

Examples

llik <- dynloglikMC(c(1,2,0,1,.25,3.5),Metro2019,10000,3,3,'exp')

[Package FitDynMix version 1.0.0 Index]