Outlier in BE [Study As­sess­ment]

posted by ramgopi – India, 2018-03-14 12:29 (2205 d 21:31 ago) – Posting: # 18533
Views: 5,741

Dear All,

Greetings!

We have discussed enough regarding discordant outliers in BE study in the past, but we have struct with typical situation and i would like to know experts opinion on this regard.

we have a done a BE study for GCC submission with two way crossover, here one subject shows less concentration in reference product and the T/R ratio for Cmax 2.43 and AUCt 2.35, because of this subject the study failed in border, if we excluded this as a outlier the 90% CI is within the acceptance limit.

90% CI before excluding particular subject

Dependent   Ratio_  %RefCI_90_Lower  CI_90_Upper    CV%
Ln(Cmax)    115.46      106.23         125.49      19.47%
Ln(AUClast) 110.25      102.66         118.40      16.64%


90% CI After excluding particular subject

Dependent   Ratio_  %RefCI_90_Lower  CI_90_Upper    CV%
Ln(Cmax)    112.14      104.48         120.36      16.12%
Ln(AUClast) 107.34      101.29         113.75      13.27



It is evident that something happen for this subject during clinical phase but the CRO failed to notify the incident.

GCC just following EMA guidance so as per EMA this is failed study, but out of my curiosity Is there any way to scientifically justify and exclude this subject from statistical calculation.

please let me know your opinion

thanks & Regards;-)

Gopinath


Edit: Category changed; see also this post #1. Tabulators changed to spaces and BBcoded; see also this post #6[Helmut]

Complete thread:

UA Flag
Activity
 Admin contact
22,957 posts in 4,819 threads, 1,640 registered users;
72 visitors (0 registered, 72 guests [including 2 identified bots]).
Forum time: 10:01 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