The hardware and bandwidth for this mirror is donated by dogado GmbH, the Webhosting and Full Service-Cloud Provider. Check out our Wordpress Tutorial.
If you wish to report a bug, or if you are interested in having us mirror your free-software or open-source project, please feel free to contact us at mirror[@]dogado.de.
nimblewomble
:
An R package for Bayesian wombling with nimble
The goal of nimblewomble
is to perform Bayesian Wombling
(boundary analysis) using nimble
.
For more details on point-referenced Wombling please refer to: a. Bayesian Wombling: Sudipto Banerjee and Alan E. Gelfandhttps://doi.org/10.1198/016214506000000041 b. Bayesian Modeling with Curvature Processes: Aritra Halder, Sudipto Banerjee and Dipak K. Dey https://doi.org/10.1080/01621459.2023.2177166
You can install the development version of nimblewomble
like so:
::install_github("arh926/nimblewomble") devtools
This is a basic example which shows you the workflow on a simulated data:
require(nimble)
require(nimblewomble)
set.seed(1)
= 1e2
N = 1
tau = matrix(runif(2 * N, -10, 10), ncol = 2); colnames(coords) = c("x", "y")
coords = rnorm(N, 20 * sin(sqrt(coords[, 1]^2 + coords[, 2]^2)), tau)
y
= gp_fit(coords = coords, y = y, kernel = "matern1")
mc_sp
= zbeta_samples(y = y, coords = coords,
zbeta model = mc_sp$mcmc,
kernel = "matern1")
= ysplit = seq(-10, 10, by = 1)[-c(1, 21)]
xsplit = as.matrix(expand.grid(xsplit, ysplit), ncol = 2)
grid colnames(grid) = c("x", "y")
= sprates(grid = grid,
gradients coords = coords,
model = zbeta,
kernel = "matern1")
require(ggplot2)
require(ggplot2)
require(cowplot)
require(MBA)
require(metR)
= sp_ggplot(data_frame = data.frame(grid,
p1 z = gradients$estimate.sx[,"50%"],
sig = gradients$estimate.sx$sig))
p1
= # Pick a curve from the surface that is interesting to you
curve = spwombling(coords = coords,
wm curve = curve,
model = zbeta,
kernel = "matern1")
= sapply(wm$estimate.wm$sig, function(x){
col.pts if(x == 1) return("green")
else if(x == -1) return("cyan")
else return(NA)
})
= sp_ggplot(obs, legend.key.height = 0.7, legend.key.width = 0.4, text.size = 10)
p2
+ geom_path(curve, mapping = aes(x, y), linewidth = 2) +
p2 geom_path(curve, mapping = aes(x, y), colour = c(col.pts, NA), linewidth = 1, na.rm = TRUE)
Name | ||
---|---|---|
Aritra Halder (maintainer) | aritra.halder@drexel.edu | Asst. Professor, Dept. of Biostatistics, Drexel Univ. |
Sudipto Banerjee | sudipto@ucla.edu | Professor & Past Chair, Dept. of Biostatistics, UCLA |
These binaries (installable software) and packages are in development.
They may not be fully stable and should be used with caution. We make no claims about them.
Health stats visible at Monitor.