Before proceeding further with CODA, all users should be aware that none of the convergence diagnostics implemented in this package (or indeed, anywhere else) are foolproof. cowles:carlin:95 tested a number of these methods, and found examples when each failed to detect lack of convergence. We recommend using a combination of diagnostics plus visual inspection of the trace plots and summary statistics generated by CODA . In this way, the user should be able to assess the convergence of the BUGS output with a reasonable degree of confidence, whilst recognising that it is not possible to say with certainty that the sample is representative of the underlying stationary distribution.