Statistical power in nursing research.

Abstract

A power analysis was performed on 62 articles that were published in Nursing Research and Research in Nursing and Health during 1989. The analysis revealed that when effects were small, the mean power of the statistical tests being performed to test research hypotheses was .26, indicating a very high risk of committing a Type II error. When effects were moderate, the mean power increased to .71, which is still below the conventionally acceptable power of .80. Only when a study involved large effects was the power adequate (mean of .95). Of the 583 power estimates calculated, 53% were for small effects. These analyses indicate that a substantial number of published nursing studies, and presumably even more of unpublished studies, have insufficient power to detect real effects, primarily because the samples used are too small.