Journal Editorial Policies Regarding Statistical Significance Tests: Heat Is to Fire as p Is to Importance

Author: Thompson B.

Source: Educational Psychology Review, Volume 11, Number 2, June 1999 , pp. 157-169(13)

Publisher: Springer

Buy & download fulltext article:

Price: $47.00 plus tax (Refund Policy)

Abstract:

The present paper responds to defenses of statistical significance testing offered by Levin and Robinson. First, some inaccurate perceptions of contemporary criticisms of statistical tests are noted. Second, areas of disagreement are explored. For example, it is noted that all nine empirical studies of reporting practices since 1994 show that “encouraging” (per the 1994 APA style manual) authors to report effect sizes has not worked; two reasons for this failure are explored. Finally, two important areas of agreement regarding needed improvements in contemporary practices are noted.

Keywords: statistical significance; effect size; editorial policy; statistics; research methods

Language: English

Document Type: Research article

Affiliations: 1: Texas A&M University and Baylor College of Medicine. TAMU Department of Educational Psychology, College Station, Texas 77843-4225. e100bt@tamvm1.tamu.edu. http://acs.tamu.edu/~bbt6147/

Publication date: 1999-06-01