## EEU-rules, TSD-methods (lengthy question) [Two-Stage / GS Designs]

Dear all!

Elena777, I guess I misunderstood something. Did you mean aposteriory power or interim power? If interim is 30% go to the next step by the decision tree.

Helmut, what was the final conclusions on the post?

Are there any suggestions on how to deal with two metrics in adaptive trials?

For example: a). Let us consider Type II design: first step - estimated power is less than target (80%) for C

1). We calculate 100(1-2α

2). Suppose further we go to the 2

Another example: b). First step - estimated power is less than target (80%) for both metrics and adjusted level CI is outside the range. Should we use the largest observed CV to calculate the total sample size? Would the study be overpowered for the second PK metric? Would it affect the TIE?

To conclude: what is the best strategy to follow in this situation in order to avoid inflation of the TIE and the loss of power?

(Some mad idea: is it possible to make some hybrid monster to combine both C

What ANOVA model should be used for the second stage? By the way, what about the code on R for the full decision tree?

Elena777, I guess I misunderstood something. Did you mean aposteriory power or interim power? If interim is 30% go to the next step by the decision tree.

❝ It is difficult to predict how regulators of the EEU interpret their own guideline

*Words are chameleons, which reflect the color of their environment*" (Learned Hand)Helmut, what was the final conclusions on the post?

Are there any suggestions on how to deal with two metrics in adaptive trials?

For example: a). Let us consider Type II design: first step - estimated power is less than target (80%) for C

_{max}and more than target for AUC, besides 90%CI for AUC is OK.1). We calculate 100(1-2α

_{adj}) CI for C_{max}, should we also do it for AUC? It can fail.2). Suppose further we go to the 2

^{nd}stage. Should we use data from the 2^{nd}stage to estimate CI for AUC the second time? If yes, it possibly can fail, if not - how to explain the fact that we do not use the data?Another example: b). First step - estimated power is less than target (80%) for both metrics and adjusted level CI is outside the range. Should we use the largest observed CV to calculate the total sample size? Would the study be overpowered for the second PK metric? Would it affect the TIE?

To conclude: what is the best strategy to follow in this situation in order to avoid inflation of the TIE and the loss of power?

(Some mad idea: is it possible to make some hybrid monster to combine both C

_{max}and AUC in the same test for adaptive designs? Something like C_{max}/AUC but with more powerful reflection of the situations (I dealt with a plenty of studies (BE and not proven BE) with C_{max}/AUC as an additional metric, only once it was outside the range)❝ Furthermore, a formulation-by-stage interaction term in the model is considered nonsense in the EMA’s Q&A.

What ANOVA model should be used for the second stage? By the way, what about the code on R for the full decision tree?

—

"Being in minority, even a minority of one, did not make you mad"

"Being in minority, even a minority of one, did not make you mad"

### Complete thread:

- Appropriate wording for a protocol Elena777 2019-09-09 19:34 [Two-Stage / GS Designs]
- Appropriate wording for a protocol ElMaestro 2019-09-09 21:39
- Appropriate wording for a protocol Helmut 2019-09-09 23:27
- Appropriate wording for a protocol Ohlbe 2019-09-10 10:27

- Which country? Helmut 2019-09-09 23:17
- Which country? Elena777 2019-09-11 20:24
- EEU-rules, TSD-methods (lengthy answer) Helmut 2019-09-12 01:31
- EEU-rules, TSD-methods (lengthy question)Astea 2019-09-14 14:56
- n2 based on PK metric with higher CV Helmut 2019-09-16 11:50
- Q&A ref Astea 2019-09-16 18:28
- The omniscient oracle has spoken Helmut 2019-09-17 12:27
- The omniscient oracle has spoken Astea 2019-09-17 20:34
- OT: Булга́ков Helmut 2019-09-18 12:12

- The omniscient oracle has spoken Astea 2019-09-17 20:34

- The omniscient oracle has spoken Helmut 2019-09-17 12:27
- n2 based on PK metric with higher CV Elena777 2019-09-16 19:48
- AUC passes with 0.05 and Cmax with 0.0294 Helmut 2019-09-16 23:30
- AUC passes with 0.05 and Cmax with 0.0294 Mikalai 2019-09-18 16:56
- Hybrid B/C Helmut 2019-09-18 17:09

- AUC passes with 0.05 and Cmax with 0.0294 Elena777 2019-09-19 08:34
- Use data of all dosed subjects Helmut 2019-09-19 15:16
- Use data of all dosed subjects Elena777 2019-09-19 15:27
- ‘Method C’ ⇒ risky Helmut 2019-09-19 16:15

- Use data of all dosed subjects Elena777 2019-09-19 15:27

- Use data of all dosed subjects Helmut 2019-09-19 15:16

- AUC passes with 0.05 and Cmax with 0.0294 Mikalai 2019-09-18 16:56

- AUC passes with 0.05 and Cmax with 0.0294 Helmut 2019-09-16 23:30

- Q&A ref Astea 2019-09-16 18:28
- EEU-rules, TSD-methods (lengthy question) Elena777 2019-09-16 19:35
- apple tree for two-stage Astea 2019-09-16 20:39
- overripe apples Helmut 2019-09-16 23:37
- override apples Astea 2019-09-17 06:14

- overripe apples Helmut 2019-09-16 23:37

- apple tree for two-stage Astea 2019-09-16 20:39

- n2 based on PK metric with higher CV Helmut 2019-09-16 11:50

- EEU-rules, TSD-methods (lengthy question)Astea 2019-09-14 14:56

- EEU-rules, TSD-methods (lengthy answer) Helmut 2019-09-12 01:31

- Which country? Elena777 2019-09-11 20:24

- Appropriate wording for a protocol ElMaestro 2019-09-09 21:39