Ahikal
☆    

Egypt,
2022-02-11 18:34
(137 d 23:00 ago)

Posting: # 22773
Views: 1,177
 

 statistical analysis of William's Design [Study As­sess­ment]

Dear all, I did a bioequivalence project using William's design (3 treatment, 3 period, 6 sequence), 2 test products against one reference. I analyzed the data as 3-way, and also separated the test products, each with a reference, and analyzed them. My question: should I get the same result?

Best Regards
Ahmed


Edit: Category changed; see also this post #1[Helmut]
Helmut
★★★
avatar
Homepage
Vienna, Austria,
2022-02-11 19:07
(137 d 22:27 ago)

@ Ahikal
Posting: # 22774
Views: 1,033
 

 statistical analysis of William's Design

Hi Ahmed,

» […] William's design (3 treatment, 3 period, 6 sequence), 2 test products against one reference. I analyzed the data as 3-way, and also separated the test products, each with a reference, and analyzed them. My question: should I get the same result?

Extremely unlikely. In the separate evaluations (as Incomplete Block Designs) you get two estimates of the within-subject variances (one in the comparison of T1 vs R and the other in the comparison of T2 vs R). Even if they would be identical, you have different degrees of freedom in the analyses. In each of the IBDs you have \(\small{df=n-2}\) and in the pooled ANOVA \(\small{df=2\times n-4}\), where \(\small{n}\) is the total number of subjects. Although the point estimates might be the same, the confidence intervals will not.

Dif-tor heh smusma 🖖 [image]
Helmut Schütz
[image]

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

Egypt,
2022-02-11 19:43
(137 d 21:51 ago)

@ Helmut
Posting: # 22775
Views: 1,015
 

 statistical analysis of William's Design

Thank you much, Helmut, for clarifying the issue.

Sincerely
Ahmed
Ahikal
☆    

Egypt,
2022-02-12 14:58
(137 d 02:36 ago)

@ Helmut
Posting: # 22776
Views: 978
 

 statistical analysis of William's Design

Now a question arises, which way should be submitted to regulatory authorities?
Helmut
★★★
avatar
Homepage
Vienna, Austria,
2022-02-12 15:02
(137 d 02:32 ago)

@ Ahikal
Posting: # 22777
Views: 972
 

 statistical analysis of William's Design

Hi Ahmed,

» Now a question arises, which way should be submitted to regulatory authorities?

Simple: The one you stated in the protocol.

Dif-tor heh smusma 🖖 [image]
Helmut Schütz
[image]

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

Egypt,
2022-02-12 15:41
(137 d 01:52 ago)

@ Helmut
Posting: # 22778
Views: 979
 

 statistical analysis of William's Design

Thanks again
Ahmed
Ahikal
☆    

Egypt,
2022-02-17 22:16
(131 d 19:17 ago)

@ Helmut
Posting: # 22792
Views: 891
 

 statistical analysis of William's Design

Hi Helmut,
One last question, if you separate the two test products, do you maintain three periods or make it as two period?

Best Regards
Ahmed
Helmut
★★★
avatar
Homepage
Vienna, Austria,
2022-02-17 22:33
(131 d 19:01 ago)

@ Ahikal
Posting: # 22794
Views: 846
 

 Two at a Time (Incomplete Blocks)

Hi Ahmed,

» One last question, if you separate the two test products, do you maintain three periods or make it as two period?

You have to keep the codes (sequence, period). See here (scroll down to David Brown’s slides) and there.

Dif-tor heh smusma 🖖 [image]
Helmut Schütz
[image]

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

Egypt,
2022-02-17 23:45
(131 d 17:48 ago)

@ Helmut
Posting: # 22796
Views: 868
 

 Two at a Time (Incomplete Blocks)

Hi Helmut,

Thanks a million

Best Regards
Ahmed
dshah
★    

India/United Kingdom,
2022-02-18 10:26
(131 d 07:07 ago)

(edited by dshah on 2022-02-18 16:27)
@ Ahikal
Posting: # 22797
Views: 840
 

 statistical analysis of William's Design

Dear Ahmed!

Particularly for EMA as per the guideline: - "In studies with more than two treatment arms (e.g. a three period study including two references, one from EU and another from USA, or a four period study including test and reference in fed and fasted states), the analysis for each comparison should be conducted excluding the data from the treatments that are not relevant for the comparison in question."
So you will need to show the calculations separately.
Regards,
Dshah
Ahikal
☆    

Egypt,
2022-02-25 13:42
(124 d 03:52 ago)

@ dshah
Posting: # 22805
Views: 702
 

 statistical analysis of William's Design

Dear Dshah:
Thank you, this is how our regulatory committee wanted me to do it, and I was fighting them

Best Regards
Ahmed
Ahikal
☆    

Egypt,
2022-02-25 14:22
(124 d 03:12 ago)

@ dshah
Posting: # 22806
Views: 719
 

 statistical analysis of William's Design

Dear Dshah;

» Particularly for EMA as per the guideline"

Would you please provide me with a reference to this

Best Regards
Ahmed
Helmut
★★★
avatar
Homepage
Vienna, Austria,
2022-02-25 14:37
(124 d 02:57 ago)

@ Ahikal
Posting: # 22807
Views: 696
 

 Do your homework first

Hi Ahikal,

see there #3 and Guidelines on top of the page.

Dif-tor heh smusma 🖖 [image]
Helmut Schütz
[image]

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

Egypt,
2022-02-26 09:54
(123 d 07:39 ago)

@ Helmut
Posting: # 22808
Views: 693
 

 Do your homework first

Dear Helmut:

Got it, my apology

Sincerely
Ahmed
UA Flag
Activity
 Admin contact
22,181 posts in 4,647 threads, 1,572 registered users;
online 5 (0 registered, 5 guests [including 3 identified bots]).
Forum time: Wednesday 18:34 CEST (Europe/Vienna)

Nerds don’t just happen to dress informally.
They do it too consistently.
Consciously or not, they dress informally
as a prophylactic measure against stupidity.    Paul Graham

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