2-stage design with interim sample size estimation [Two-Stage / GS Designs]
Dear d_labes,
the reason I call this a one-stage design is that I would not formally test for equivalence at the time were one does the sample size re-estimation. Hence one would not need to spend any alpha at this time (as no testing is done and hence the EMA guide is not relevant) and hence no risk of the awkward situation that one could have to stop the trial early.
This is also the reason why doing the sample size re-estimation in a blinded fashion can make sense as using unblinded data will question the one-stage design.
As for the question: "Can we expect to prove BE with a Nmax of 120 subjects with some pre-specified power?"
I dont really see the problem there. You are not arriving at a test decision about BE if you decide to stop because you would need more resources than you have and hence it is not impacting your type-I-error. Having such a rule has therefore no bearing on the formal testing.
Finally, I agree that results from superiority trials will not apply directly they do, however, often contain useful ideas how one can tackle a problem in equivalence from first principle.
the reason I call this a one-stage design is that I would not formally test for equivalence at the time were one does the sample size re-estimation. Hence one would not need to spend any alpha at this time (as no testing is done and hence the EMA guide is not relevant) and hence no risk of the awkward situation that one could have to stop the trial early.
This is also the reason why doing the sample size re-estimation in a blinded fashion can make sense as using unblinded data will question the one-stage design.
As for the question: "Can we expect to prove BE with a Nmax of 120 subjects with some pre-specified power?"
I dont really see the problem there. You are not arriving at a test decision about BE if you decide to stop because you would need more resources than you have and hence it is not impacting your type-I-error. Having such a rule has therefore no bearing on the formal testing.
Finally, I agree that results from superiority trials will not apply directly they do, however, often contain useful ideas how one can tackle a problem in equivalence from first principle.
Complete thread:
- 2-stage design with interim sample size estimation d_labes 2010-10-05 15:09
- 2-stage design with interim sample size estimation Jack 2010-10-25 18:20
- Null = bioINequivalence Helmut 2010-10-25 19:16
- 2-stage design with interim sample size estimation d_labes 2010-10-26 13:28
- 2-stage design with interim sample size estimationJack 2010-10-26 18:26
- Blind or not, Indecisions or Decisions d_labes 2010-10-27 16:01
- Blind or not, Indecisions or Decisions Jack 2010-10-27 18:14
- Blind ? Ohlbe 2010-10-27 23:37
- Blind ? Jack 2010-10-28 10:24
- Blind 2Stage Astea 2019-05-30 10:37
- Blind 2Stage Helmut 2019-05-30 12:56
- Blind 2Stage and an elephant Astea 2019-05-31 14:36
- Which elephant? Helmut 2019-06-02 20:14
- Blind interim in parallel design? Astea 2019-06-03 01:47
- Blind men d_labes 2019-06-05 12:23
- The Blind Leading the Blind Astea 2019-06-06 00:55
- Blind men d_labes 2019-06-05 12:23
- Blind interim in parallel design? Astea 2019-06-03 01:47
- Which elephant? Helmut 2019-06-02 20:14
- Blind 2Stage and an elephant Astea 2019-05-31 14:36
- Blind 2Stage Helmut 2019-05-30 12:56
- Blind 2Stage Astea 2019-05-30 10:37
- Blind ? Jack 2010-10-28 10:24
- Blind ? Ohlbe 2010-10-27 23:37
- Blind or not, Indecisions or Decisions Jack 2010-10-27 18:14
- Blind or not, Indecisions or Decisions d_labes 2010-10-27 16:01
- 2-stage design with interim sample size estimationJack 2010-10-26 18:26
- 2-stage design with interim sample size estimation Jack 2010-10-25 18:20