Skip to contents

Diagnostic Plots for a Bayesian Fit

Source: R/plots_extra.R
plot.bd_bayes.Rd

Trace and posterior density plots for each parameter of a [bayes_betadanish()] fit.

Usage

# S3 method for class 'bd_bayes'
plot(
  x,
  which = NULL,
  type = c("both", "trace", "density"),
  col = "steelblue",
  ...
)

Arguments

x

An object of class `"bd_bayes"`.

which

Optional character vector of parameters to show. Defaults to all of them.

type

`"both"` (default) for trace and density side by side, or `"trace"` or `"density"` alone.

col

Colour for the traces and densities.

...

Further graphical parameters.

Value

Invisibly returns `x`.

Details

Read the traces first. A well-mixed chain looks like noise around a stable level, with no drift and no long excursions. Visible trend means the burn-in was too short; a chain that sticks at one value for many iterations means the proposal is too wide and almost every move is being rejected, which is worth fixing with `tune` before interpreting anything.

The graphical parameters are restored on exit, so the function leaves the device as it found it.

See also

[bayes_betadanish()]

Examples

# \donttest{
if (requireNamespace("MCMCpack", quietly = TRUE) &&
    requireNamespace("coda", quietly = TRUE)) {
  dat <- simulate_bd_data(80, a = 1, b = 3, c = 2, k = 0.5, seed = 6)
  bfit <- bayes_betadanish(dat$time, dat$status, submodel = TRUE,
                           burnin = 200, mcmc = 800, seed = 1)
  plot(bfit)
}
#> 
#> 
#> @@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@
#> The Metropolis acceptance rate was 0.50800
#> @@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@

# }