TY  - JOUR
PY  - 2009//
TI  - Methodological issues related to the use of p0.05 in health behavior research
JO  - American journal of health education
A1  - Duryea, Elias
A1  - Graner, Stephen P.
A1  - Becker, Jeremy
SP  - 120
EP  - 125
VL  - 40
IS  - 2
N2  - 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 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<0.05. Attention to these concepts could improve clarity in how research outcomes are presented and thereby increase credibility of health behavior research.<p /> 
LA  - 
SN  - 1932-5037
UR  - http://dx.doi.org/
ID  - ref1
ER  -