Diagnostic plots

Generate trace, density, and autocorrelation plots from an rjtrace object.

# S3 method for rjtrace
plot(
  rj.obj,
  param.name = NULL,
  phase = NULL,
  type = "both",
  adjust = 2,
  gvals = NULL,
  priors = NULL,
  covariates.incl = FALSE,
  autocorr = FALSE,
  individual = TRUE
)

Arguments

rj.obj	rjMCMC trace object of class rjtrace.
param.name	Parameter name(s). Defaults to NULL, which returns plots for all parameters in the model.
phase	Integer. If used, will only generate plots for the parameters of the monophasic (1) or biphasic (2) model.
covariates.incl	Logical. If TRUE, the trace is filtered to only retain posterior estimates obtained when the contextual covariates were included in the model. Only relevant when covariate.select = TRUE in configure_rjMCMC.
autocorr	Logical. Whether to output chain autocorrelation plots.
individual	Logical. If TRUE, separate density lines will be plotted for each chain. If FALSE, one density line will be plotted for all chains.

Details

Adapted from Casey Youngflesh's function MCMCtrace.

See also

run_rjMCMC trace_rjMCMC

Author

Phil J. Bouchet

Examples

if (FALSE) {
library(espresso)

# Import the example data, excluding species with sample sizes < 5
# and considering the sonar covariate
mydat <- read_data(file = NULL, min.N = 5, covariates = "sonar") 
summary(mydat)

# Configure the sampler
mydat.config <- configure_rjMCMC(dat = mydat,
                                 model.select = TRUE,
                                 covariate.select = FALSE,
                                 function.select = FALSE,
                                 n.rep = 100)
summary(mydat.config)

# Run the reversible jump MCMC
rj <- run_rjMCMC(dat = mydat.config,
                 n.chains = 2,
                 n.burn = 100,
                 n.iter = 100,
                 do.update = FALSE)

# Burn and thin
rj.trace <- trace_rjMCMC(rj.dat = rj)

# Get density and trace plots
plot(rj.trace)
}