geoBayes (version 0.7.5)

bf2optim: Empirical Bayes estimator

Description

Estimation by empirical Bayes.

Usage

bf2optim(bf1obj, paroptim, useCV = TRUE, control = list())

Value

The output from the function optim. The "value" element is the log-Bayes factor, not the negative log-Bayes factor.

Arguments

bf1obj

Output from the function bf1skel which contains the Bayes factors and importance sampling weights.

paroptim

A named list with the components "linkp", "phi", "omg", "kappa". Each component must be numeric with length 1, 2, or 3 with elements in increasing order but for the binomial family linkp is also allowed to be the character "logit" and "probit". If the compontent's length is 1, then the corresponding parameter is considered to be fixed at that value. If 2, then the two numbers denote the lower and upper bounds for the optimisation of that parameter (infinities are allowed). If 3, these correspond to lower bound, starting value, upper bound for the estimation of that parameter.

useCV

Whether to use control variates for finer corrections.

control

A list of control parameters for the optimisation. See optim.

Details

This function is a wrap around bf2new using the "L-BFGS-B" method of the function optim to estimate the parameters.

Examples

if (FALSE) {
data(rhizoctonia)
### Define the model
corrf <- "spherical"
kappa <- 0
ssqdf <- 1
ssqsc <- 1
betm0 <- 0
betQ0 <- .01
family <- "binomial.probit"
### Skeleton points
philist <- c(100, 140, 180)
omglist <- c(.5, 1)
parlist <- expand.grid(linkp=0, phi=philist, omg=omglist, kappa = kappa)
### MCMC sizes
Nout <- 100
Nthin <- 1
Nbi <- 0
### Take MCMC samples
runs <- list()
for (i in 1:NROW(parlist)) {
  runs[[i]] <- mcsglmm(Infected ~ 1, family, rhizoctonia, weights = Total,
                       atsample = ~ Xcoord + Ycoord,
                       Nout = Nout*c(.8,.2), Nthin = Nthin, Nbi = Nbi,
                       betm0 = betm0, betQ0 = betQ0,
                       ssqdf = ssqdf, ssqsc = ssqsc,
                       phi = parlist$phi[i], omg = parlist$omg[i],
                       linkp = parlist$linkp[i], kappa = parlist$kappa[i],
                       corrfcn = corrf,
                       corrtuning=list(phi = 0, omg = 0, kappa = 0))
}
bf <- bf1skel(runs)
est <- bf2optim(bf, list(phi = c(100, 200), omg = c(0, 2)))
est
}