Bayesian Methods in Health Economics

Bayesian analysis in practice 145

deviance 40.326 2.014 38.389 45.351 1.005 500

For each parameter, n.eff is a crude measure of effective sample size,

and Rhat is the potential scale reduction factor

(at convergence, Rhat=1).

DIC info (using the rule, pD = var(deviance)/2)

pD = 2.0 and DIC = 42.4

DIC is an estimate of expected predictive error

(lower deviance is better).

Convergence seems to be reached satisfactorily as all the nodes are associated

with low values of the Gelman–Rubin statistic, as well as with relatively large

values of the effective sample size. Consequently, we can use the simulations

produced by JAGS to perform the health economic analysis.

First we make them available to the R workspace attaching the elements of

the object chemo, w