PASSIVE SMOKING IN THE WORKPLACE - CLASSICAL AND BAYESIAN METAANALYSES

There are currently several classical and Bayesian methods of meta-ana lysis available for combining epidemiological results. We describe and compare these in a consistent framework, and apply them to published studies of the relative risk of lung cancer associated with exposure t o environmental tobacco smoke in the workplace. We find that although all methods give reasonably similar combined estimates of relative ris k of lung cancer associated with this exposure (none of which is signi ficantly raised above unity, in either a frequentist or a Bayesian sen se), the approximations arising from classical methods appear to be no nconservative and should be used with caution. The Bayesian methods, w hich account more explicitly for possible inhomogeneity in studies, gi ve slightly lower estimates again of relative risk and wider posterior credible intervals, indicating that inference from the non-Bayesian a pproaches might be optimistic.