Strong Type I Error control + CI: Not yet… [Two-Stage / GS Designs]
❝ I am wondering whether the following publication made it to your attention: …
No.
❝ I was the opinion that only simulation-based methods (Fuglsang 2014) are currently available/acceptable for parallel group designs due to the complexity of contructing repeated confidence intervals allowing for unequal variances between groups (a requirement for parallel designs according to FDA guidelines).
Right. I had serious problems convincing European regulators even with extensive simulations (unequal variances and/or group sizes due to dropouts). Note that the FDA is fine with simulation-based methods (5th GBHI workshop*).
❝ However, in the publication repeated confidence intervals were constructed using the Fisher combination test assuming equal variances (3 parallel treatment arms were analysed using ANOVA). What do you think about it?
Equal variances are a rather strong assumption, right? Very – very! – unlikely in practice. The t-test is sensitive (i.e., liberal) to unequal variances and – to a minor extent – to unequal group sizes. Not by any chance the Welch-test is the default in R and SAS.
Was in the paper an ANOVA (with all arms) used? A pooled variance is just crap. Follow the “Two-at-a-Time” approach, i.e., two analyses with pairwise comparisons. That’s recommended in the latest guidelines (FDA, EMA, ICH M13A).
❝ As there seems to be no solution currently avaiable for adaptive parallel group designs that analytically controls the type-I-error using the confidence interval inclusion approach and allows for unequal variances, …
Right.
❝ … wouldn't it be acceptable to use a hypothesis test like in (Maurer 2016) only?
Unlikely, though that’s a Radio Yerewan question.
❝ In that case, we cannot construct confidence intervals consistent with the hypothesis test but the decision for BE=Y/N can be answered, right?
When we had a poster about this stuff (doi:10.1186/1745-6215-16-S2-P218), Franz said “it’s doable in principle”. Well roared, lion. It’s on the todo-list of Benjamin Lang (main author of the inverse normal method in the package
Power2Stage
). Difficult… ❝ I know that FDA guidelines state that it needs to be done by the confidence interval but is this less preferable than using Potvin's algorithm (not strictly controlling type-I-error)?
I don’t think that any agency will accept a study without a CI.
BTW, the EMA ❤️ a stage-term in the final analysis. Calls for an ANOVA, right? That’s like deciding between Skylla (ANOVA ignoring unequal variances to make regulators happy) and Charybdis (Welch-test given regulators headaches). Michael Tomashevskiy suggested some code a while ago but it’s not implemented in the function
power.tsd.p()
yet.- Mehta M, Schug B, Blume HH, Beuerle G, Jiang W, Koenig J, Paixão P, Tampal N, Tsang Y-C, Walstab J, Wedemeyer R, Welink J. The Global Bioequivalence Harmonisation Initiative (GBHI): Report of the fifth international EUFEPS/AAPS conference. Europ. J. Pharm. Sci. 15 August 2023. doi:10.1016/j.ejps.2023.106566. Open access PDF.
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
Complete thread:
- Parallel Group Adaptive Designs Alex 2023-12-22 10:08 [Two-Stage / GS Designs]
- Strong Type I Error control + CI: Not yet…Helmut 2023-12-22 12:01
- Strong Type I Error control + CI: Not yet… Alex 2024-01-08 16:22
- Strong Type I Error control + CI: Not yet… Helmut 2024-01-09 09:48
- Strong Type I Error control + CI: Not yet… roman_max 2024-04-04 15:18
- Parallel design: Only simulation-based methods so far Helmut 2024-04-04 20:16
- Parallel design: Only simulation-based methods so far roman_max 2024-04-15 21:46
- Parallel design: Only simulation-based methods so far Helmut 2024-04-04 20:16
- Strong Type I Error control + CI: Not yet… Alex 2024-01-08 16:22
- Parallel Group Adaptive Designs Achievwin 2024-01-05 11:53
- Simulations highly recommended Helmut 2024-01-05 12:40
- Simulations highly recommended Achievwin 2024-01-08 16:55
- Simulations mandatory Helmut 2024-01-09 09:31
- Simulations mandatory Achievwin 2024-01-09 21:11
- Reviews are confidential Helmut 2024-01-09 22:10
- Reviews are confidential Achievwin 2024-01-19 15:11
- Not accepted and for a reason… Helmut 2024-04-04 20:22
- Quod licet Iovi mittyri 2024-04-05 20:33
- Non licet bovi Helmut 2024-04-05 21:50
- Non licet bovi mittyri 2024-04-05 22:21
- Quod licet bove? Helmut 2024-04-06 07:21
- Non licet bovi mittyri 2024-04-05 22:21
- Non licet bovi Helmut 2024-04-05 21:50
- Quod licet Iovi mittyri 2024-04-05 20:33
- Not accepted and for a reason… Helmut 2024-04-04 20:22
- Reviews are confidential Achievwin 2024-01-19 15:11
- Reviews are confidential Helmut 2024-01-09 22:10
- Simulations mandatory Achievwin 2024-01-09 21:11
- Simulations mandatory Helmut 2024-01-09 09:31
- Simulations highly recommended Achievwin 2024-01-08 16:55
- Simulations highly recommended Helmut 2024-01-05 12:40
- Strong Type I Error control + CI: Not yet…Helmut 2023-12-22 12:01