corplot: corplot

In petedodd/MCIR: Monte Carlo Inference Routines: A Collection of Generic Algorithms for Bayesian Inference

Description

A hexbinned pairs and density plot to examine correlations.

Usage

corplot(X, main = "", labels = NULL, file = "", points = FALSE)

Arguments

X	a matrix whose columns refer to parameters and whose rows to samples
main	the plot title (if desired)
labels	a character vector of length ncol(X) to label parameters
file	a filename to save pdf output plot to (else plotted to default to device)

Details

The diagonal panels are histograms of each parameter representing estimates of marginal density. The lower half shows hexbinned plots of correlations between parameters (estimates of pairwise joint densities) together with a loess smoother to indicate trend. If points=TRUE the pair plots are not hexbinned and points are plotted with alpha proportional to weight.

Value

None

Author(s)

Pete Dodd

Examples

corplot(matrix(rnorm(3e4),ncol=3),labels=c('x','y','z'),main='3D isotropic Gaussian')

petedodd/MCIR documentation built on Jan. 9, 2020, 9:18 a.m.