hiren379
★    

India,
2012-07-28 12:56
(3185 d 19:32 ago)

(edited by hiren379 on 2012-07-28 13:43)
Posting: # 8986
Views: 5,039
 

 Formulation Effect [General Sta­tis­tics]

Hello friends,
Is it possible that my T/R is 85 and there was a significant formulation effect in ANOVA but variability was so low in BE, that 90%CI came to 81-90 (BE established). Is this possible???
:confused::confused::confused:
Helmut
★★★
avatar
Homepage
Vienna, Austria,
2012-07-28 13:42
(3185 d 18:46 ago)

@ hiren379
Posting: # 8987
Views: 4,384
 

 Formulation Effect is irrelevant

Dear Hiren!

» Is it possible that my T/R is 85 and significant formulation effect but variability in my study was so low that 90%CI came to 81-90.

Yes it is, though a significant formulation effect is irrelevant in BE (except in Denmark). If the CI does not include 100% one will always get a significant formulation effect.

Dif-tor heh smusma 🖖
Helmut Schütz
[image]

The quality of responses received is directly proportional to the quality of the question asked. 🚮
Science Quotes
hiren379
★    

India,
2012-07-28 13:49
(3185 d 18:40 ago)

@ Helmut
Posting: # 8988
Views: 4,341
 

 Formulation Effect is irrelevant

» If the CI does not include 100% one will always get a significant formulation effect.

Thanks HS...

But I am not geting how can we claim two formulation bioequivalent if there is significant formulation effect????

Just on the basis that the variability of such difference will be less (narrow CI) how can we claim BE???

If someone can throw some light
Helmut
★★★
avatar
Homepage
Vienna, Austria,
2012-07-28 16:23
(3185 d 16:06 ago)

@ hiren379
Posting: # 8989
Views: 4,822
 

 Statistically significant ≠ clinically relevant!

Dear Hiren!

» But I am not geting how can we claim two formulation bioequivalent if there is significant formulation effect????

Statistically significant does not imply clinically relevant. In BE any [≥-20.00% & ≤+25.00%] difference (log-scale ±0.2231) generally* is considered irrelevant.

» Just on the basis that the variability of such difference will be less (narrow CI) how can we claim BE???

[image]Since the CI is within the acceptance range. BE is de­fined as ARlo ≤CLlo and CLhi ≤ARhi; nothing else. If we in­crease the sample size (keep­ing the CV constant) sooner or later any (!) formulation will show a statistically significant difference – if the PE ≠ 100%. Have a look at this slide: The minimum sample size according to many guidelines is 12. With T/R 0.95 and a CV of 15% we expect already a power of 83% (the CI will be 85.07 – 106.09%). With 48 sub­jects the upper CL drops below 100% and we will get a statistical significant difference (CI 90.27 – 99.98%).

Or, if we keep the sample size at 12 and our CV is even lower, the power will increase – and there­fore, also the chance to get a significant difference (exemplified by the light blue curve in the linked presentation). With a CV% of 10% power will be 98.8% and with 5% 99.99999995%. :-D

May I ask you for the sample size in your study?


  • Except some NTIDs ([≥-10.00% & ≤+11.11%] = log-scale ±0.1054) or HVDs/HVDPs where the AR may be wider.

Dif-tor heh smusma 🖖
Helmut Schütz
[image]

The quality of responses received is directly proportional to the quality of the question asked. 🚮
Science Quotes
hiren379
★    

India,
2012-08-14 14:51
(3168 d 17:37 ago)

@ Helmut
Posting: # 9062
Views: 4,002
 

 Statistically significant ≠ clinically relevant!

Thank You HS...
Very nicely explained sir

» May I ask you for the sample size in your study?

Actually this was just a question arised in my mind. There is no practical case faced.

But really good explanation... :ok:
Activity
 Admin contact
21,419 posts in 4,475 threads, 1,510 registered users;
online 10 (0 registered, 10 guests [including 3 identified bots]).
Forum time: Sunday 08:29 CEST (Europe/Vienna)

Nothing fails like success because you do not learn anything from it.
The only thing we ever learn from is failure.
Success only confirms our superstitions.    Kenneth E. Boulding

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