Premium
The potential for meta‐analysis to support decision analysis in ecology
Author(s) -
Mengersen Kerrie,
MacNeil M. Aaron,
Caley M. Julian
Publication year - 2015
Publication title -
research synthesis methods
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 3.376
H-Index - 35
eISSN - 1759-2887
pISSN - 1759-2879
DOI - 10.1002/jrsm.1105
Subject(s) - decision analysis , computer science , linkage (software) , risk analysis (engineering) , meta analysis , variety (cybernetics) , cost–benefit analysis , management science , uncertainty analysis , decision support system , ecology , data science , operations research , artificial intelligence , economics , business , biology , medicine , biochemistry , mathematical economics , gene , engineering , simulation
Meta‐analysis and decision analysis are underpinned by well‐developed methods that are commonly applied to a variety of problems and disciplines. While these two fields have been closely linked in some disciplines such as medicine, comparatively little attention has been paid to the potential benefits of linking them in ecology, despite reasonable expectations that benefits would be derived from doing so. Meta‐analysis combines information from multiple studies to provide more accurate parameter estimates and to reduce the uncertainty surrounding them. Decision analysis involves selecting among alternative choices using statistical information that helps to shed light on the uncertainties involved. By linking meta‐analysis to decision analysis, improved decisions can be made, with quantification of the costs and benefits of alternate decisions supported by a greater density of information. Here, we briefly review concepts of both meta‐analysis and decision analysis, illustrating the natural linkage between them and the benefits from explicitly linking one to the other. We discuss some examples in which this linkage has been exploited in the medical arena and how improvements in precision and reduction of structural uncertainty inherent in a meta‐analysis can provide substantive improvements to decision analysis outcomes by reducing uncertainty in expected loss and maximising information from across studies. We then argue that these significant benefits could be translated to ecology, in particular to the problem of making optimal ecological decisions in the face of uncertainty. Copyright © 2013 John Wiley & Sons, Ltd.