A pharmacological manufacturer is concerned that a new drug

A pharmacological manufacturer is concerned that a new drug used to control hypertension may alter fasting blood glucose (FBG). What sample size would he or she need in a randomized clinical trial (equal numbers of subjects given the new drug or placebo) to have 80% power to detect a 5 point difference in FBG if the standard deviation of FBG in the population is 19?

Solution

Compute Sample Size
n = (Z a/2 * S.D / ME ) ^2
Z/2 at 0.2% LOS is = 1.28 ( From Standard Normal Table )
Standard Deviation ( S.D) = 19
ME =5
n = ( 1.28*19/5) ^2
= (24.32/5 ) ^2
= 23.658 ~ 24