[Skip to Content]
[Skip to Content Landing]
April 11, 1986

Clinically and Statistically Significant Differences

Author Affiliations

Delta Health Center Mound Bayou, Miss

JAMA. 1986;255(14):1876. doi:10.1001/jama.1986.03370140074008

To the Editor.—  Keeler et al1 in their article state that "differences of 1.9 mm Hg in diastolic blood pressure... are important—they translate into differences of 5% to 8% in the probability of dying in the next year." As a clinician, I am very skeptical that a reduction in diastolic blood pressure of approximately 0.5 mm Hg per year (1.9 mm Hg achieved over a three- to five-year period) in the free group is clinically significant. Could this be another case of confusing statistical significance with clinical significance?If indeed the reduction in diastolic blood pressure was clinically significant, it seems that a difference in the number of deaths in the hypertensive subgroup of 856 patients should have been noted over the three- to five-year period of follow-up. Was such a difference noted? (It has already been reported that the total numbers of deaths in the free vs cost-sharing