Automated Markov Chain Monte Carlo for Arbitrarily Structured
Correlation Matrices
Description
Supports automated Markov chain Monte Carlo for arbitrarily structured correlation
matrices. The user supplies data, a correlation matrix in symbolic form, the current state
of the chain, a function that computes the log likelihood, and a list of prior distributions.
The package's flagship function then carries out a parameter-at-a-time update of all correlation
parameters, and returns the new state. The method is presented in Hughes (2023), in preparation.