diagnostic: Check if a BUGS model has converged

In FRBCesab/popbayes: Bayesian Model to Estimate Population Trends from Counts Series

Check if a BUGS model has converged

Description

From the output of the function fit_trend() (or read_bugs()), this function checks if the estimation of all parameters of one (or several) BUGS model has converged. This diagnostic is performed by comparing the Rhat value of each parameter to a threshold (default is 1.1). If some Rhat values are greater than this threshold (no convergence), a message listing problematic models is displayed.

Usage

diagnostic(data, threshold = 1.1)

Arguments

data	a named list of BUGS outputs. The output of fit_trend() or read_bugs().
threshold	a numeric.

Value

No return value.

Examples

## Load Garamba raw dataset ----
file_path <- system.file("extdata", "garamba_survey.csv", 
                         package = "popbayes")
                         
garamba <- read.csv(file = file_path)

## Create temporary folder ----
temp_path <- tempdir()

## Format dataset ----
garamba_formatted <- popbayes::format_data(
  data              = garamba, 
  path              = temp_path,
  field_method      = "field_method",
  pref_field_method = "pref_field_method",
  conversion_A2G    = "conversion_A2G",
  rmax              = "rmax")
                                        
## Select one serie ----
a_buselaphus <- popbayes::filter_series(garamba_formatted, 
                                        location = "Garamba",
                                        species  = "Alcelaphus buselaphus")

## Fit population trends (requires JAGS) ----
a_buselaphus_mod <- popbayes::fit_trend(a_buselaphus, path = temp_path)

## Check for convergence ----
popbayes::diagnostic(a_buselaphus_mod)

FRBCesab/popbayes documentation built on Jan. 26, 2024, 12:13 p.m.