Bioequivalence and Bioavailability Forum • Potvin method B subtleties

Potvin method B subtleties [Two-Stage / GS Designs]

posted by d_labes – Berlin, Germany, 2011-01-31 15:24 (5200 d 12:33 ago) – Posting: # 6520
Views: 28,530

Dear All,

in the description of group-sequential designs with interim sample size estimation Potvin et.al.¹⁾ describe a Method B.

Because they use the same nominal alpha=0.0294 in both evaluation stages I wonder how their decision scheme reads if one attempt to use some more extreme alpha-spending values, say for instance O'Brien-Fleming boundaries with alpha1=0.005 and alpha2=0.048.

I guess the Method B decision scheme then reads:

  Evaluate BE at stage 1 

   at alpha=alpha1=0.005

      |              |

      v              v

if BE met:        if BE not met:

stop: success     evaluate power with alpha=0.005

                  at GMR=0.95

                     |                |

                     v                v  

                if power>80%  if power<80%

                stop: fail    calculate sample size with

                              alpha=0.048 and variance from stage1

                                       |

                                       v

                              continue to stage 2

                              evaluate after stage 2 with alpha=0.048

                              using data from both stages

                              success or fail

Q1: Do you think I have inserted the right alpha values?
Q2: If yes in Q1: It may happen that in the sample size estimation step the resulting N may be lower then the sample size at stage 1, i.e. there is no stage 2 necessary. What to do then? Evaluate via stage 1 model but with alpha=alpha2=0.048 ?
Q3: Do you think that the power calculation makes sense if executed with the point estimate from stage 1 instead of GMR=0.95?
Q4: Do you think Method B is nearer then Method C to the sentence "... The analysis of the first stage data should be treated as an interim analysis and both analyses conducted at adjusted significance levels (with the confidence intervals accordingly using an adjusted coverage probability which will be higher than 90%) ..." from the EMA guideline?

¹⁾Potvin D, Diliberti CE, Hauck WW, Parr AF, Schuirmann DJ, and RA Smith
Sequential design approaches for bioequivalence studies with crossover designs
Pharmaceut. Statist. 7/4, 245-262 (2008), DOI: 10.1002/pst.294
Online abstract

—
Regards,

Detlew

Complete thread:

Potvin method B subtletiesd_labes 2011-01-31 14:24 [Two-Stage / GS Designs]
- Potvin method B subtleties jdetlor 2011-02-01 17:17
  - Potvin method B subtleties d_labes 2011-02-02 09:15
    - Potvin method B subtleties jdetlor 2011-02-02 16:08
      - Gould d_labes 2011-02-02 16:25
        
        Gould jdetlor 2011-02-02 17:02
- Another one ... d_labes 2011-02-07 14:32
  - Oops! Helmut 2011-02-07 15:24
    - Oops! d_labes 2011-02-07 16:29
      - Oops! Helmut 2011-02-07 16:47
        
        Oops! ElMaestro 2011-02-07 17:06
        
        Oops! Helmut 2011-02-07 17:17
        
        Oops! ElMaestro 2011-02-07 18:35
        
        Simul'ants in my pants d_labes 2011-02-08 09:07
        
        Need for speed... ElMaestro 2011-02-13 10:57
        
        Need for speed... d_labes 2011-02-15 14:06
        
        Need for speed... ElMaestro 2011-02-15 17:39
        
        Pocock alpha's d_labes 2011-02-16 09:18
        
        ElMaestro's brain ElMaestro 2011-02-16 09:32
        
        ElMaestro's brain d_labes 2011-02-16 10:05
        
        ElMaestro's brain ElMaestro 2011-02-16 12:07
        
        Numbers d_labes 2011-02-16 13:45
- Bonus counter-question ElMaestro 2011-02-07 23:44
  - Speed is the question d_labes 2011-02-08 08:36
- New paper (method D for PE 0.90) Helmut 2011-04-18 12:58
  - New paper (method D for PE 0.90) d_labes 2011-04-19 08:58
    - New paper (method D for PE 0.90) Helmut 2011-04-19 14:30
    - New paper (method D for PE 0.90) ElMaestro 2011-04-19 14:49
      - Stopping criterion # futility rule Helmut 2011-04-19 15:28