Search: id:"swepub:oai:DiVA.org:lnu-70306" >
Bayesian evidence s...
Bayesian evidence synthesis is no substitute for meta-analysis : a re-analysis of Scheibehenne, Jamil and Wagenmakers (2016)
-
- Carlsson, Rickard, 1984- (author)
- Linnéuniversitetet,Institutionen för psykologi (PSY)
-
- Schimmack, Ulrich (author)
- University of Toronto, Canada
-
- Williams, Donald R. (author)
- University of California, USA
-
show more...
-
- Bürkner, Paul-Christian (author)
- University of Münster, Germany
-
show less...
-
(creator_code:org_t)
- Linnaeus University Centre for Labour Market and Discrimination Studies, 2016
- English 5 s.
-
Series: Working paper series ; 2016:7
- Related links:
-
https://lnu.diva-por... (primary) (Raw object)
-
show more...
-
https://urn.kb.se/re...
-
show less...
Abstract
Subject headings
Close
- Scheibehenne, Jamil, and Wagenmakers (2016; SJW) recently introduced Bayesian evidence synthesis (BES). They applied it to a set of original studies that examined the influence of social norms on towel reuse at hotels. While most of the original studies provided nonsignificant results (p > .05), BES provided “strong support” (p. 3) for the effect. Due to methodological limitations, we think that this conclusion is wrong and that BES suffers from several problems. Combining frequentist and Bayesian approaches, we: illustrate the perilsof pooling data; assess publication bias, and conduct a Bayesian meta-analysis.
Subject headings
- SAMHÄLLSVETENSKAP -- Ekonomi och näringsliv -- Nationalekonomi (hsv//swe)
- SOCIAL SCIENCES -- Economics and Business -- Economics (hsv//eng)
Keyword
- Economics
- Nationalekonomi
Publication and Content Type
- vet (subject category)
- rap (subject category)
To the university's database