MGR
★    

India,
2015-11-13 08:43
(3454 d 08:43 ago)

Posting: # 15634
Views: 7,356
 

 Inter CV calculation for parallel study [Power / Sample Size]

Hi all,

How to calculate Inter CV of a parallel study from the values of Confidence interval, Ratio and N?

For Example:

CI lower = 0.876
CI Upper = 1.02
Ratio = 0.96
N = 122

The above results are from a Parallel study.

Please suggest how to calculate the Inter CV from the above data.

Thanks in advance,

Regards,
MGR
d_labes
★★★

Berlin, Germany,
2015-11-13 12:13
(3454 d 05:13 ago)

@ MGR
Posting: # 15635
Views: 5,859
 

 Total CV for parallel study from CI

Dear MGR,

it is only possible to get the total (inter+intra) CV from a parallel group study.

With this in mind and assuming 90% CI you can do in the software R :cool::
library(PowerTOST)
CVfromCI(lower=0.876, upper=1.02, n=122, design="parallel")

gives you a CV = 0.258 (25.8%).

If you don't have R you can do the algebra behind by hand. It's not so hard. See Helmut's lectures about "sample size estimation". Change degrees of freedom and design constant according to the parallel group design.

Better install R, it's free. And use the "gold standard" package PowerTOST :-D.

Regards,

Detlew
UA Flag
Activity
 Admin contact
23,424 posts in 4,927 threads, 1,673 registered users;
79 visitors (0 registered, 79 guests [including 6 identified bots]).
Forum time: 18:26 CEST (Europe/Vienna)

There are two possible outcomes: if the result confirms the
hypothesis, then you’ve made a measurement. If the result is
contrary to the hypothesis, then you’ve made a discovery.    Enrico Fermi

The Bioequivalence and Bioavailability Forum is hosted by
BEBAC Ing. Helmut Schütz
HTML5