avrahan
☆    

2014-09-17 23:40
(3479 d 19:18 ago)

Posting: # 13530
Views: 9,214
 

 CV calculation [Power / Sample Size]

Hi

I have found an old study which the ISCV is not stated in the results. Is it possible to calculate this parameter using IC90 and sample size?

The study was performed with 24 subjects - 22 finalized

IC90:
Cmax: 92.08 - 123.44
AUC0-t 93.08 - 113.87

Can anybody help me on this?

Thanks

Regards
Helmut
★★★
avatar
Homepage
Vienna, Austria,
2014-09-18 03:21
(3479 d 15:36 ago)

@ avrahan
Posting: # 13531
Views: 7,538
 

 CV calculation

Hi avrahan,

❝ I have found an old study which the ISCV is not stated in the results. Is it possible to calculate this parameter using IC90 and sample size?


If you mean CI90, yes. Any of my presentations dealing with sample size estimation will give you the required formulas. Then you can calculate the CV manually. More convenient is R / package PowerTOST / function CVfromCI().

❝ The study was performed with 24 subjects - 22 finalized

❝ Cmax:  92.08 - 123.44

❝ AUC0-t 93.08 - 113.87


library(PowerTOST)
CVfromCI(lower=0.9208, upper=1.2344, n=22, design="2x2", alpha=(1-0.9)/2)
[1] 0.2875014
CVfromCI(lower=0.9308, upper=1.1387, n=22, design="2x2", alpha=(1-0.9)/2)
[1] 0.1956711

Dif-tor heh smusma 🖖🏼 Довге життя Україна! [image]
Helmut Schütz
[image]

The quality of responses received is directly proportional to the quality of the question asked. 🚮
Science Quotes
BRN
☆    

Turkey,
2015-08-26 18:52
(3137 d 00:05 ago)

@ Helmut
Posting: # 15342
Views: 6,153
 

 CV calculation

Hi all,

I have intra and inter-cv, is there an easy way to calculate the total cv? An R code for example or any other suggestions are appreciated.

Thank you...

Regards,
BRN
d_labes
★★★

Berlin, Germany,
2015-08-27 10:48
(3136 d 08:10 ago)

@ BRN
Posting: # 15349
Views: 6,176
 

 CV(total) from CV(intra) and CV(inter)

Dear BRN!

❝ I have intra and inter-cv, is there an easy way to calculate the total cv? An R code for example or any other suggestions are appreciated.


Have a look into Helmut's lectures, f.i. the Moscow lecture about sample size estimation, slide 18. If your design was 2x2x2 which gave you the intra and inter-CV, and if you obtained the CV's from log-transformed analysis.

Using the world-famous R package PowerTost :cool: you may use:

library(PowerTOST)
# Methylphenidate on slide 19, Helmut's Moscow lecture
# CV's as ratio

CVintra <- 0.070
CVinter <- 0.191
CVtotal <- mse2CV(CV2mse(CVintra)+CV2mse(CVinter))
print(CVtotal)


will give 0.2038621, i.e. 20.4%.

Regards,

Detlew
UA Flag
Activity
 Admin contact
22,957 posts in 4,819 threads, 1,638 registered users;
93 visitors (1 registered, 92 guests [including 10 identified bots]).
Forum time: 17:58 CET (Europe/Vienna)

Nothing shows a lack of mathematical education more
than an overly precise calculation.    Carl Friedrich Gauß

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