diagnostics: Checks a fitted RoBTT object

Description

diagnostics creates visual checks of individual models convergence. Numerical overview of individual models can be obtained by summary(object, type = "models", diagnostics = TRUE), or even more detailed information by summary(object, type = "individual").

Usage

diagnostics(
  fit,
  parameter,
  type,
  show_models = NULL,
  lags = 30,
  title = is.null(show_models) | length(show_models) > 1,
  ...
)
diagnostics_autocorrelation(
  fit,
  parameter = NULL,
  show_models = NULL,
  lags = 30,
  title = is.null(show_models) | length(show_models) > 1,
  ...
)
diagnostics_trace(
  fit,
  parameter = NULL,
  show_models = NULL,
  title = is.null(show_models) | length(show_models) > 1,
  ...
)
diagnostics_density(
  fit,
  parameter = NULL,
  show_models = NULL,
  title = is.null(show_models) | length(show_models) > 1,
  ...
)

Value

diagnostics returns either NULL if plot_type = "base"

or an object/list of objects (depending on the number of parameters to be plotted) of class 'ggplot2' if plot_type = "ggplot2".

Arguments

fit: a fitted RoBTT object
parameter: a parameter to be plotted. Either "delta", "rho", "nu", "mu", or "sigma".
type: type of MCMC diagnostic to be plotted. Options are "chains" for the chains' trace plots, "autocorrelation" for autocorrelation of the chains, and "densities" for the overlaying densities of the individual chains. Can be abbreviated to first letters.
show_models: MCMC diagnostics of which models should be plotted. Defaults to NULL which plots MCMC diagnostics for a specified parameter for every model that is part of the ensemble.
lags: number of lags to be shown for type = "autocorrelation". Defaults to 30.
title: whether the model number should be displayed in title. Defaults to TRUE when more than one model is selected.
...: additional arguments to be passed to par if plot_type = "base".

Details

The visualization functions are based on stan_plot function and its color schemes.

Examples

Run this code

if (FALSE) {
# using the example data from Darwin
data("fertilization", package = "RoBTT")
fit <- RoBTT(
  x1       = fertilization$Self,
  x2       = fertilization$Crossed,
  prior_delta = prior("cauchy", list(0, 1/sqrt(2))),
  prior_rho   = prior("beta",   list(3, 3)),
  seed        = 1, 
  chains      = 1,
  warmup      = 1000,
  iter        = 2000,
  control     = set_control(adapt_delta = 0.95)
)

### ggplot2 version of all of the plots can be obtained by adding 'model_type = "ggplot"
# diagnostics function allows to visualize diagnostics of a fitted RoBTT object, for example,
# the trace plot for the mean parameter in each model model
diagnostics(fit, parameter = "delta", type = "chain")

# in order to show the trace plot only for the 11th model, add show_models parameter
diagnostics(fit, parameter = "delta", type = "chain", show_models = 11)

# furthermore, the autocorrelations
diagnostics(fit, parameter = "delta", type = "autocorrelation")

# and overlying densities for each plot can also be visualize
diagnostics(fit, parameter = "delta", type = "densities")
}