Skip to main content
. Author manuscript; available in PMC: 2016 Jun 1.
Published in final edited form as: Ther Drug Monit. 2015 Jun;37(3):389–394. doi: 10.1097/FTD.0000000000000168

Figure 3.

Figure 3

Plot of the standard error of the estimate of the true sample SD versus number of sample replicates [4,5]. Probably at least 5 replicates should be measured, the more the better. Nine replicates, for example, have only half the error of three replicates. The vertical line shows that for 5 replicates, the ERR is 35.3%.