ordinalRR.control {ordinalRR}

Set control parameters for a Bayesian ordinal R&R model.

Description

The R-function ‘ordinalRR.control’ sets various control parameters for the prior if using the random-effects version of the model and for the MCMC. See Section 3.2 of Culp, Ryan, Chen, and Hamada (2018) for more on this prior. Default settings match this paper.

Usage

ordinalRR.control(mu.mu.alpha = 0.8, tau.mu.alpha = 0.4, mu.tau.alpha = 4,
tau.tau.alpha = 0.4, mu.lambda = 2, tau.lambda = 0.2, rjags.B = 10000L,
rjags.Burn = 1000L, rjags.n.chains = 1L, rjags.n.adapt = 5000L,r.seed=10L,rjags.seed=10L)

Arguments

mu.mu.alpha

‘positive scalar’ mean of the normal prior for mu.alpha.

tau.mu.alpha

‘positive scalar’ precision=1/variance of the normal prior for mu.alpha.

mu.tau.alpha

‘positive scalar’ mean of the log-normal prior for tau.alpha.

tau.tau.alpha

‘positive scalar’ precision of the log-normal prior for tau.alpha.

mu.lambda

‘positive scalar’ mean of the log-normal prior for the lambda.h.

tau.lambda

‘positive scalar’ precision of the log-normal prior for the lambda.h.

rjags.B

‘positive integer’ length of JAGS MCMC chain retained.

rjags.Burn

‘positive integer’ length of initial JAGS MCMC chain burnin discarded.

rjags.n.chains

‘1’ number of JAGS MCMC chains (currently only programmed to accept 1).

rjags.n.adapt

‘positive integer’ rjags n.adapt parameter within command jag.model().

r.seed

‘positive integer’ sets seed within R during function ordinalRR(). This is for predictive inference on a new rater which is only used with the random-effects model. This does not fix the JAGS seed for the MCMC.

rjags.seed

‘positive integer’ sets seed within JAGS for the posterior sample from function ordinalRR().

Author(s)

Ken Ryan

References

Culp, S.L., Ryan, K.J., Chen, J., and Hamada, M.S. (2018). “Analysis of Repeatability and Reproducibility Studies with Ordinal Measurements.” Technometrics, doi:10.1080/00401706.2018.1429317.

Plummer, M. (2016). “RJAGS: Bayesian Graphical Models using MCMC.” R Package Version 4-6, https://CRAN.R-project.org/package=rjags.

Plummer, M. (2017). “JAGS: A Program for Analysis of Bayesian Graphical Models using Gibbs Sampling.” Version 4.3.0, http://mcmc-jags.sourceforge.net.