Log in
Register|
jag009 ★★★ NJ, 2013-02-18 16:47 (4468 d 07:21 ago) Posting: # 10050 Views: 5,352 |
|
|
Hi all, Question. In a 3-way partial replicate study, how do you handle subjects in terms of statistics?
For #1, subject should be kept for all statistics. Agree? Thanks John Edit: Category changed. [Helmut] |
|
Helmut ★★★   Vienna, Austria, 2013-02-19 13:51 (4467 d 10:17 ago) @ jag009 Posting: # 10055 Views: 4,215 |
|
|
Hi John, good points! ❝ For #2, I spoke with one CRO and they said they do not include those subjects in the overall BE statistics (SABE or BE). However, they said the subjects data will be included in determining the withinsubject standard deviation (variation). I think we should not include those subjects at all or their data should be included in all stats if they are included in the determination of witinsubject variaton. Suggestion? Including subjects with only RR data would probably give a more precise estimate of CVWR. However, personally I would not include them (see below). ❝ For #1, subject should be kept for all statistics. Agree? I can only speak from the European perspective. Ideally, all treated subjects should be included in the statistical analysis. However, subjects in a crossover trial who do not provide evaluable data for both of the test and reference products […] should not be included. — Dif-tor heh smusma 🖖🏼 Довге життя Україна! ![[image]](https://static.bebac.at/pics/Blue_and_yellow_ribbon_UA.png) Helmut Schütz ![[image]](https://static.bebac.at/img/CC by.png) The quality of responses received is directly proportional to the quality of the question asked. 🚮 Science Quotes |
|
jag009 ★★★ NJ, 2013-02-19 21:31 (4467 d 02:37 ago) @ Helmut Posting: # 10067 Views: 4,191 |
|
|
Hi Helmut, ❝ ❝ For #1, subject should be kept for all statistics. Agree? ❝ I can only speak from the... Ideally, all treated subjects should be included in the statistical analysis. However, subjects in a crossover trial who do not provide evaluable data for both of the test and reference products […] should not be included. I agree to that for a 2-way (T vs R) crossover study but not for a full/partial replicate study if the subject has data from 1 test arm and 1 reference arm or 2 test arms and 1 reference arm or 1 test arms and 2 reference arms. Correct me if I am wrong... John |
|
Helmut ★★★ Vienna, Austria, 2013-02-19 21:37 (4467 d 02:31 ago) @ jag009 Posting: # 10068 Views: 4,284 |
|
|
Hi John, ❝ ❝ Ideally, all treated subjects should be included in the statistical analysis. However, subjects in a crossover trial who do not provide evaluable data for both of the test and reference products […] should not be included. ❝ ❝ I agree to that for a 2-way (T vs R) crossover study but not for a full/partial replicate study if the subject has data from 1 test arm and 1 reference arm or 2 test arms and 1 reference arm or 1 test arms and 2 reference arms. This is what the GL essentially says (maybe the wording is ambiguous – EMA does not require complete data): At least one test and one reference arm. All your examples are included, whereas only two arms of the reference are not. — Dif-tor heh smusma 🖖🏼 Довге життя Україна! Helmut Schütz The quality of responses received is directly proportional to the quality of the question asked. 🚮 Science Quotes |
Ing. Helmut Schütz