caterpoints: Points on a "caterplot"

In mcmcplots: Create Plots from MCMC Output

Description

Adds points to a caterplot.

Usage

caterpoints(x, parnames, horizontal = TRUE, ...)

Arguments

x	vector of points to add to a caterplot.
parnames	an optional vector of parameter names. If specified, x must have a names attribute. The argument parnames will be used to subset the vector x for plotting, as in x[parnames].
horizontal	logical value that should match the argument of the same name in the original call to caterplot.
...	further arguments passed to the function points.

Author(s)

S. McKay Curtis

See Also

caterplot

Examples

## Create fake MCMC output
nc <- 10; nr <- 1000
pnames <- c(paste("alpha[", 1:5, "]", sep=""), paste("gamma[", 1:5, "]", sep=""))
means <- rpois(10, 20)
fakemcmc <- coda::as.mcmc.list(
    lapply(1:3,
           function(i) coda::mcmc(matrix(rnorm(nc*nr, rep(means, each=nr)),
                                         nrow=nr, dimnames=list(NULL,pnames)))))
posterior.medians <- apply(do.call("rbind", fakemcmc), 2, median)


## caterplot plots of the fake MCMC output
par(mfrow=c(2,2))
caterplot(fakemcmc, "alpha", collapse=FALSE)
caterpoints(runif(5, 10, 20), pch="x", col="red")
caterplot(fakemcmc, "alpha", horizontal=FALSE)
caterpoints(runif(5, 10, 20), horizontal=FALSE, pch="x", col="red")
parms <- caterplot(fakemcmc, random=3) # keep the names of plotted parameters
caterpoints(posterior.medians[parms], pch="x", col="red")

Example output

Loading required package: coda

mcmcplots documentation built on May 2, 2019, 1:29 p.m.