GetBMA: Compute the Bayesian Model average
In sppmix: Modeling Spatial Poisson and Related Point Processes

Description Usage Arguments Value Author(s) See Also Examples

This function uses the posterior realizations from a est_mix_bdmcmc call, to compute the Bayesian Model Average across different number of components and returns the fitted Poisson point process with mixture of normals intensity surface.

For examples see

http://faculty.missouri.edu/~micheasa/sppmix/sppmix_all_examples.html#GetBMA

1 2	GetBMA(fit, win = fit$data$window, burnin = fit$L/10, LL = 100, zlims = c(0, 0))

`fit`	Object of class `bdmcmc_res`.
`win`	An object of class `owin`.
`burnin`	Number of initial realizations to discard. By default, it is 1/10 of the total number of iterations.
`LL`	Length of the side of the square grid. The density or intensity is calculated on an L * L grid. The larger this value is, the slower the calculation, but the better the approximation as well as the smoother the resulting plots.
`zlims`	The limits of the z axis. Defaults to [0,max(z)].

An image as an object of class im.object.

Sakis Micheas

est_mix_bdmcmc, plotmix_3d, plot_density

fit=est_mix_bdmcmc(pp = spatstat::redwood, m = 5)
BMA=GetBMA(fit)
burnin=.1*fit$L
title1 = paste("Bayesian model average of",fit$L-burnin,"posterior realizations")
plotmix_3d(BMA,title1=title1)
plot_density(as.data.frame(BMA))+ggplot2::ggtitle("Bayesian model average intensity surface")
plot_density(as.data.frame(BMA),TRUE)+ggplot2::ggtitle(
 "Contours of the Bayesian model average intensity surface")