NotesFAQContact Us
Search Tips
Peer reviewed Peer reviewed
Direct linkDirect link
ERIC Number: EJ1109102
Record Type: Journal
Publication Date: 2015-Dec
Pages: 14
Abstractor: As Provided
ISSN: ISSN-1759-2879
Bayesian Meta-Analysis of Cronbach's Coefficient Alpha to Evaluate Informative Hypotheses
Okada, Kensuke
Research Synthesis Methods, v6 n4 p333-346 Dec 2015
This paper proposes a new method to evaluate informative hypotheses for meta-analysis of Cronbach's coefficient alpha using a Bayesian approach. The coefficient alpha is one of the most widely used reliability indices. In meta-analyses of reliability, researchers typically form specific informative hypotheses beforehand, such as "alpha of this test is greater than 0.8" or "alpha of one form of a test is greater than the others." The proposed method enables direct evaluation of these informative hypotheses. To this end, a Bayes factor is calculated to evaluate the informative hypothesis against its complement. It allows researchers to summarize the evidence provided by previous studies in favor of their informative hypothesis. The proposed approach can be seen as a natural extension of the Bayesian meta-analysis of coefficient alpha recently proposed in this journal (Brannick and Zhang, [Brannick MT, 2013]). The proposed method is illustrated through two meta-analyses of real data that evaluate different kinds of informative hypotheses on superpopulation: one is that alpha of a particular test is above the criterion value, and the other is that alphas among different test versions have ordered relationships. Informative hypotheses are supported from the data in both cases, suggesting that the proposed approach is promising for application.
Wiley-Blackwell. 350 Main Street, Malden, MA 02148. Tel: 800-835-6770; Tel: 781-388-8598; Fax: 781-388-8232; e-mail:; Web site:
Publication Type: Journal Articles; Reports - Research
Education Level: N/A
Audience: N/A
Language: English
Sponsor: N/A
Authoring Institution: N/A
Grant or Contract Numbers: N/A