LogLike: Individual log-likelihood

In spatcounts: Spatial count regression

Description

'LogLike' calculates the individual log-likelihood which is needed for 'Clarketest' and 'Vuongtest'.

Usage

LogLike(Yin, fm.X, region, regmodel, thinning = 1, burnin = 1)

Arguments

Yin	response vector of length n.
fm.X	formula for mean design.
region	region of each observation.
regmodel	the output of model fits obtained by using 'est.sc'.
thinning	number of MCMC iterations between two writing steps (if thinning=1 (default), all states are calculated whereas if e.g. thinning=10 only each 10 iteration is calculated)
burnin	number of steps dropped from the chain to allow for a burn-in phase. Defaults to 1.

Value

ll	is a matrix of dimension (n x (totalit+2)), where each column represents one iteration and contains the likelihood contributions of each observation.

Examples

data(sim.Yin)
data(sim.fm.X)
data(sim.region)
data(sim.gmat)
data(sim.nmat)

poi <- est.sc(sim.Yin, ~1+sim.fm.X[,1]+sim.fm.X[,2], sim.region, 
model="Poi", sim.gmat, sim.nmat, 3)

ll.poi <- LogLike(sim.Yin, ~1+sim.fm.X[,1]+sim.fm.X[,2], sim.region, poi)

# log likelihood for the single iterations
apply(ll.poi$ll,2,sum)

spatcounts documentation built on May 29, 2017, 11:04 p.m.