durga09
☆    

India,
2023-09-08 12:21
(391 d 21:18 ago)

Posting: # 23712
Views: 3,480
 

 Tmax 90% confidence interval [Regulatives / Guidelines]

Dear All,

Could anyone please help me with example or article or program, on how to calculate below point as per Ibuprofen EMA guideline.

1) 90% confidence interval: Comparable median (≤ 20% difference, 80.00–125.00%) and range for Tmax.

Regards,
Durga
Achievwin
★★  

US,
2023-09-09 14:44
(390 d 18:55 ago)

@ durga09
Posting: # 23714
Views: 3,040
 

 Tmax 90% confidence interval

❝ Could anyone please help me with example or article or program, on how to calculate below point as per Ibuprofen EMA guideline.


❝ 1) 90% confidence interval: Comparable median (≤ 20% difference, 80.00–125.00%) and range for Tmax.


Helmut responded to your question awhile ago, the following paper discuss these details.

ADJUSTING PAIRWISE NONPARAMETRIC EQUIVALENCE HYPOTHESIS TESTS AND CONFIDENCE INTERVALS FOR PERIOD EFFECTS IN 3×3 CROSSOVER TRIALS

Luc Duchateau, Paul Janssen, Roel Straetemans & Christian Otoul, Journal of Biopharmaceutical Statistics Volume 12, 2002 - Issue 2 Pages 149-160 | Received 01 Mar 2002, Accepted 01 May 2002, Published online: 05 Oct 2011 (what is interesting is that this paper was accepted in 2002 and published in 2011 - like some of our harmonization guidance :-D)

Coming to your question there is a sas code on how to non parametric estimates and calculate difference and confidence, (not sure how to attach the file). Before all this was known we did parwaise rank order comparison followed by Wilcoxon t-test for tmax, t1/2 etc.

Hope this helps and Best

AchievWin
mittyri
★★  

Russia,
2023-09-10 21:55
(389 d 11:43 ago)

@ Achievwin
Posting: # 23715
Views: 3,000
 

 link to the post of BEBAC golden collection

Dear AchievWin, Dear Durga,

I would point to the classical post (I'd say golden collection of this forum) provided by Detlew and Helmut here.
It is 13 years old, but it is still the best. And the article mentioned there is 33 years old and also no one provided something better:-D)
durga09
☆    

India,
2023-10-10 12:43
(359 d 20:56 ago)

@ mittyri
Posting: # 23748
Views: 2,656
 

 link to the post of BEBAC golden collection

❝ I would point to the classical post (I'd say golden collection of this forum) provided by Detlew and Helmut here.

❝ It is 13 years old, but it is still the best. And the article mentioned there is 33 years old and also no one provided something better:-D)


Thank you AchievWin and mittyri.

Need a small help in the Output. In output I am getting Confidence intervals as

Hodges-Lehmann Estimation:
Type               90% Confidence Limits
Asymptotic (Moses)        -0.5000 1.5000
Exact                     -0.5000 1.5000


But as per guideline Tmax 90% CI should me 0.80 to 1.25 by this point does the study "pass" or "fail"

How can interpret the results?


Edit: Full quote removed. Please delete everything from the text of the original poster which is not necessary in understanding your answer; see also this post #5. Tabulators changed to spaces and BBcoded; see also this post #6[Helmut]
mittyri
★★  

Russia,
2023-10-11 14:55
(358 d 18:44 ago)

@ durga09
Posting: # 23750
Views: 2,606
 

 CI for difference in Tmax

Dear Durga!

❝ Need a small help in the Output. In output I am getting Confidence intervals as


Hodges-Lehmann Estimation:

❝ Type               90% Confidence Limits

❝ Asymptotic (Moses)        -0.5000 1.5000

❝ Exact                     -0.5000 1.5000


❝ But as per guideline Tmax 90% CI should me 0.80 to 1.25 by this point does the study "pass" or "fail"


❝ How can interpret the results?


I've never seen any acceptance limits for Tmax in any guidelines. Could you please educate me - where is it from?
Note that we are comparing the differences in Tmax, so usual limits could not be applied for Tmax comparison.
From your results, since CI includes zero, one may conclude that the null hypothesis of statistical difference of T and R Tmax could not be rejected with given significance level.

Kind regards,
Mittyri
Helmut
★★★
avatar
Homepage
Vienna, Austria,
2023-10-12 08:55
(358 d 00:44 ago)

@ durga09
Posting: # 23751
Views: 2,558
 

 Tmax problems

Hi Durga,

❝ But as per guideline Tmax 90% CI should me 0.80 to 1.25 by this point does the study "pass" or "fail"


See this presentation as a starter. I guess you are referring the EMA’s product specific guidances on ibuprofen, paracetamol, and tadalafil.
Adding to what Mittyri wrote, perhaps this article helps.

Jiří Hofmann gave a presentation about tmax and partial AUCs at this year’s BioBridges conference (Prague, 21/22 September). It’s not online yet. Check the Archive till the 2023 link will appear.

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
UA Flag
Activity
 Admin contact
23,240 posts in 4,884 threads, 1,652 registered users;
63 visitors (2 registered, 61 guests [including 5 identified bots]).
Forum time: 09:39 CEST (Europe/Vienna)

[The] impatience with ambiguity can be criticized in the phrase:
absence of evidence is not evidence of absence.    Carl Sagan

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