Methodological Issues Related to the Use of P Less than 0.05 in Health Behavior Research

American Alliance for Health, Physical Education, Recreation and Dance. 1900 Association Drive, Reston, VA 20191. Tel: 800-213-7193; Fax: 703-476-9527; e-mail: info@aahperd.org; Web site: http://www.aahperd.org

Y

6

Intervals; Health Behavior; Epidemiology; Statistical Significance; Effect Size; Research Methodology; Sample Size; Psychology; Credibility; Research

1932-5037

This paper reviews methodological issues related to the use of P less than 0.05 in health behavior research and suggests how application and presentation of statistical significance may be improved. Assessment of sample size and P less than 0.05, the file drawer problem, the Law of Large Numbers and the statistical significance arguments in epidemiology, health behavior, and psychology were examined. The reporting of confidence intervals (CI), effect sizes (ES), and use of non-statistical graphics can improve portrayal and understanding of findings. Health behavior literature has had some scholarly examination of how to improve analysis of findings but has not had an in-depth dialog on other concepts related to P less than 0.05. Attention to these concepts could improve clarity in how research outcomes are presented and thereby increase credibility of health behavior research. (Contains 1 table.)

As Provided

43

2010

EJ871104