reparareff: Reparameterized version of the one-way random effect model
Description
This function proposes a reanalysis of the one-way random effect model processed in
randomeff via a Gibbs
sampler using another parameterization of the model in order to exhibit a different
convergent behavior.
Usage
reparareff(nsim = 10^4, a = 10, b = 10)
Arguments
nsim
Number of Gibbs iterations
a
Common shape parameter for the inverted variances
b
Common scale parameter for the inverted variances
Value
This function produces a plot made of six acf output corresponding to the
parameters $mu$, $theta1$, and $theta2$, both in the
original parameterization and in the new one.
References
Chapter 7 of EnteR Monte Carlo Statistical Methods