Edited by Raymond J.G.M. Florax, Peter Nijkamp and Kenneth G. Willis
11. Meta-analysis: a Bayesian perspective Chris Brunsdon, Kenneth G. Willis 1 INTRODUCTION ‘Meta-analysis’ is an increasingly widely-used term to describe the process of integrating the ﬁndings of several research studies carried out in some area of interest. Typically, one wishes to combine several measurements of some parameter (possibly obtained using several diﬀerent methods) to obtain an overall estimate, based on information from all of the previous studies. Additionally, one may wish to carry out statistical signiﬁcance tests of some hypothesis relating to that parameter, again using information from all of the studies. It is hoped that the pooling of information will result in a parameter estimate with a smaller standard error or a more powerful signiﬁcance test than that obtained from any one of the individual studies. This notion can be extended in a number of ways. If information about the methodology of each of the studies is available, one can perform a meta-regression in which the parameter estimates from each study are regressed against methodology variables. In this way, parameter estimates from individual studies can be standardized for the eﬀects of diﬀerent measurement techniques. Similarly, one can regress the parameter estimates against contextual variables. For example, if each study involves estimating some economic index in a speciﬁc geographical location, one could regress index estimates against a set of environmental and demographic variables for each location. This allows one to predict the likely index estimates in further geographical locations, provided the same environmental and...
You are not authenticated to view the full text of this chapter or article.
Elgaronline requires a subscription or purchase to access the full text of books or journals. Please login through your library system or with your personal username and password on the homepage.
Non-subscribers can freely search the site, view abstracts/ extracts and download selected front matter and introductory chapters for personal use.
Your library may not have purchased all subject areas. If you are authenticated and think you should have access to this title, please contact your librarian.