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

Abstract

This paper reviews methodological issues related to the use of P<0.05 in health behavior research and suggests how application and presentation of statistical significance may be improved. Assessment of sample size and P<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 nonstatistical 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<0.05. Attention to these concepts could improve clarity in how research outcomes are presented and thereby increase credibility of health behavior research.