Summarize posterior draws from a one-arm fitted model

summary.mixgpd_fit() computes posterior summaries for monitored model parameters.

Usage

# S3 method for class 'mixgpd_fit'
summary(object, pars = NULL, probs = c(0.025, 0.5, 0.975), ...)

Arguments

object

A fitted object of class "mixgpd_fit".

pars

Optional character vector of parameters to summarize. If NULL, summarize all (excluding v's).

probs

Numeric vector of quantiles to report.

...

Unused.

Value

An object of class "mixgpd_summary".

Details

The returned table is a parameter-level summary of the posterior draws, not a predictive summary. Use predict.mixgpd_fit for posterior predictive quantities such as densities, survival probabilities, quantiles, and means.

The summary respects the stored truncation metadata and reports WAIC if it was requested during MCMC.

See also

print.mixgpd_fit, params, predict.mixgpd_fit, ess_summary.

Examples

# \donttest{
y <- abs(stats::rnorm(25)) + 0.1
bundle <- build_nimble_bundle(y = y, backend = "sb", kernel = "normal",
                             GPD = TRUE, components = 3,
                             mcmc = list(niter = 100, nburnin = 50, thin = 1, nchains = 1))
fit <- run_mcmc_bundle_manual(bundle)
#> [mixgpd] Validating configuration
#> [mixgpd] Checking build/compile cache
#> [mixgpd] Building model and MCMC configuration
#> [mixgpd] Compiling NIMBLE model
#> [mixgpd] Initializing chains
#> [mixgpd] Running MCMC
#> [mixgpd] Finalizing WAIC and diagnostics
#> [mixgpd] Assembling fit object
summary(fit, pars = c("alpha", "threshold"))
#> MixGPD summary | backend: Stick-Breaking Process | kernel: Normal Distribution | GPD tail: TRUE | epsilon: 0.025
#> n = 25 | components = 3
#> Summary
#> Initial components: 3 | Components after truncation: 3
#> 
#> Summary table
#>  parameter  mean    sd q0.025 q0.500 q0.975
#>      alpha 1.366 0.557  0.526  1.156  2.255
#>  threshold 0.118 0.001  0.117  0.117  0.121
# }