Whose Prior is it Anyway? A Note on 'Rigorous Large-Scale Educational RCTs are Often Uninformative'

Simpson, A.

doi:10.3102/0013189x19855076

Whose Prior is it Anyway? A Note on 'Rigorous Large-Scale Educational RCTs are Often Uninformative'

Simpson, A.

Authors

Professor Adrian Simpson adrian.simpson@durham.ac.uk
Principal

Abstract

A recent paper uses Bayes factors to argue a large minority of rigorous, large-scale education RCTs are ‘uninformative’. The definition of ‘uninformative’ depends on the authors’ hypothesis choices for calculating Bayes factors. These arguably over-adjust for effect size inflation and involve a fixed prior distribution, disregarding the trials’ varied intentions.

Citation

Simpson, A. (2019). Whose Prior is it Anyway? A Note on 'Rigorous Large-Scale Educational RCTs are Often Uninformative'. Educational Researcher, 48(6), 382-384. https://doi.org/10.3102/0013189x19855076

Journal Article Type	Article
Acceptance Date	May 14, 2019
Online Publication Date	Jul 12, 2019
Publication Date	Aug 31, 2019
Deposit Date	May 16, 2019
Publicly Available Date	May 16, 2019
Journal	Educational Researcher
Print ISSN	0013-189X
Electronic ISSN	1935-102X
Publisher	SAGE Publications
Peer Reviewed	Peer Reviewed
Volume	48
Issue	6
Pages	382-384
DOI	https://doi.org/10.3102/0013189x19855076

Files

Accepted Journal Article (189 Kb)
PDF

Copyright Statement
Simpson, A. (2019). Whose Prior is it Anyway? A Note on “Rigorous Large-Scale Educational RCTs are Often Uninformative. Educational Researcher 48(6): 382-384. Copyright © 2019 AERA. DOI: 10.3102/0013189X19855076