Argues that the conclusion reached by D. R. Atkinson et al (see record 1983-01959-001) that reviewers were biased toward statistically significant results is premature. A statistical power analysis shows that the power of their bogus study was low. Low power in a study reporting nonsignificant findings is a valid reason for recommending not to publish. Therefore, differential acceptance recommendations for bogus manuscripts differing only in the statistical significance of the results were justified. (16 ref) (PsycINFO Database Record (c) 2006 APA, all rights reserved).
All Science Journal Classification (ASJC) codes
- Social Psychology
- Clinical Psychology
- Psychiatry and Mental health
- bias toward statistically significant results for publication, reviewers, criticism of conclusions of D. R. Atkinson et al