R: QBLD Summary Class

summary.qbld {qbld}

R Documentation

QBLD Summary Class

Description

Outputs a ‘summary.qbld’ class object, and prints as described.

Usage

## S3 method for class 'qbld'
summary(object,quantiles = c(0.025, 0.25, 0.5, 0.75, 0.975),epsilon = 0.05,...)

## S3 method for class 'summary.qbld'
print(x, ...)

Arguments

`object`	: ‘qbld’ class object
`quantiles`	: Vector of quantiles for summary of the covariates, defaulted to `c(0.025, 0.25, 0.5, 0.75, 0.975)`
`epsilon`	: epsilon value for calculating significance stars (see details), 0.05 by default.
`...`	: Other summary arguments
`x`	: (for print.summary.qbld) ‘qbld.summary’ class object

Details

‘qbld.summary’ class summarizes the outputs of the model.qbld function. Markov Std Error (MCSE), Effective sample size (ESS) are calculated using mcmcse package. Gelman-Rubin diagnostic (R hat), and significance stars are indicated using Vats and Knudson et. al.

Value

summary.qbld produces following sets of summary statistics for each variable:

statistics: Contains the mean, sd, markov std error, ess and Gelman-Rubin diagnostic
quantiles: Contains quantile estimates for each variable
nsim: No. of simulations run
burn: Burn-in used or not
which: Block, or Unblock version of sampler
p: quantile for the AL distribution on the error term
multiess: multiess value for the sample
multigelman: multivariate version of Gelman-Rubin

References

Vats, Dootika and Christina Knudson. “Revisiting the Gelman-Rubin Diagnostic.” arXiv

James M. Flegal, John Hughes, Dootika Vats, and Ning Dai. (2020). mcmcse: Monte Carlo Standard Errors for MCMC. R package version 1.4-1. Riverside, CA, Denver, CO, Coventry, UK, and Minneapolis, MN.

Christina Knudson and Dootika Vats (2020). stableGR: A Stable Gelman-Rubin Diagnostic for Markov Chain Monte Carlo. R package version 1.0.