plot.rmsb: Plot Posterior Densities and Summaries

In rmsb: Bayesian Regression Modeling Strategies

Plot Posterior Densities and Summaries

Description

For an rms Bayesian fit object, plots posterior densities for selected parameters along with posterior mode, mean, median, and highest posterior density interval. If the fit was produced by stackMI the density represents the distribution after stacking the posterior draws over imputations, and the per-imputation density is also drawn as pale curves. If exactly two parameters are being plotted and bivar=TRUE, hightest bivariate posterior density contrours are plotted instead, for a variety of prob values including the one specified, using

Usage

## S3 method for class 'rmsb'
plot(
  x,
  which = NULL,
  nrow = NULL,
  ncol = NULL,
  prob = 0.95,
  bivar = FALSE,
  bivarmethod = c("ellipse", "kernel"),
  ...
)

Arguments

x	an rms Bayesian fit object
which	names of parameters to plot, defaulting to all non-intercepts. Can instead be a vector of integers.
nrow	number of rows of plots
ncol	number of columns of plots
prob	probability for HPD interval
bivar	set to TRUE to plot bivariate density contours instead of univariate results (ignored if the number of parameters plotted is not exactly two)
bivarmethod	passed as method argument to pdensityContour
...	passed to pdensityContour

Value

ggplot2 object

Author(s)

Frank Harrell

rmsb documentation built on Sept. 11, 2024, 8:12 p.m.