- On 29 Mar 2013 at 22:36:11, sent the message

Back to the Top

Dear All,

Here is a statistical question I need help to respond: Five batches of

tablets have been produced and the average drug content (10 tablets

assayed per batch) is 99.2 mg with a standard deviation of 2.4. How many

tablets should be assayed (sample size?) in order to statistically show

that there is zero or near zero possibility that an individual tablet

produced will have a drug content higher than 110 mg? Thank you.

Konstantinos Avgoustakis - On 1 Apr 2013 at 12:49:50, "Lavigne, Jean" (jean.lavigne.-at-.celerion.com) sent the message

Back to the Top

The following message was posted to: PharmPK

Dear Konstantinos,

You have 4.5 standard deviation [=(110-99.2)/2.4].

Assuming a normality distribution, the probability of being lower or equal to

110 is 0.999996602.

You may want to do an ANOVA to include the variability between batch to be more

precise.

You already have a sample size of 50 (10 tablet per batch), increasing the

sample size will just increase the power (more precise mean and variability of

the "true" distribution), it will not change the probability of having an

individual tablet above 110 mg.

Other non-parametric estimation is to calculate the proportion of individual

tablet that are above 110 mg in a very large sample size.

Jean - On 1 Apr 2013 at 08:41:53, David Bourne (david.aaa.boomer.org) sent the message

Back to the Top

Dear Avgoustakis,

Please check you want to study according USP or B.P. and the follow that book details.

Dr Zafar

Want to post a follow-up message on this topic?
If this link does not work with your browser send a follow-up message to PharmPK@lists.ucdenver.edu with "Tablet content uniformity" as the subject |

Copyright 1995-2014 David W. A. Bourne (david@boomer.org)