Digit preference in clinical measurements results in loss of power. A method for quantifying this loss of power and adjusting sample sizes accordingly is described. Emphasis is placed on prevention, insisting on measuring variables with precision in clinical research.
Hypertension Detection and Follow-up Program Cooperative Group.Variability of blood pressure and the results of screening in the hypertension detection and follow-up program. J Chron Dis.1978;31:651–667.
2.
CannerPLBorhaniNOObermanACutlerJPrineasRJLangfordHHooperFJ. The hypertension prevention trial: Assessment of the quality of blood pressure measurements. Am J Epidemiol.1991;4:379–392.
3.
ZelenMSeveroN. Probability functions. In: AbramowitzMStegunIA, eds. Handbook of mathematical functions.New York: Dover Publications; 1965: 925–964 (equation numbers 26.2.17, 26.2.23, and 26.4.17).
4.
HeerenTD'AgostinoR. Robustness of the two independant samples t-test when applied to ordinal scaled data. Stat Med.1987;6:79–90.
