This function computes the log-likelihood difference for the candidate \(\delta_j\) random effects. It is a helper function and not meant to be used on its own.
llDiffD(dat, deltaj, cand, thetai, gamma, tau2)
llDiffD
returns the vector of log-likelihood differences.
data frame containing the observed sample counts.
vector of previous accepted values for the \(\delta_j\) random effects.
vector of candidate values for the \(\delta_j\) random effects.
vector of previous accepted values for the \(\theta_i\) random effects.
last sampled value for the \(\gamma\) parameter.
last sampled value for the \(\tau^2\) parameter.
Sergio Venturini sergio.venturini@unicatt.it,
Jessica A. Myers jmyers6@partners.org
For further details see Myers et al. (2011).
Myers, J. A., Venturini, S., Dominici, F. and Morlock, L. (2011), "Random Effects Models for Identifying the Most Harmful Medication Errors in a Large, Voluntary Reporting Database". Technical Report.
bhm.constr.resamp
,
bhm.mcmc
,
bhm.resample
.