Bioequivalence and Bioavailability Forum

1–2α CI and TOST at α 0.05 [General Statistics]

posted by ElMaestro – Denmark, 2017-03-28 15:12 (3023 d 05:03 ago) – Posting: # 17192
Views: 10,521

Hi DavidManteigas,

❝ If the 90% CI is significantly different from 1, then the p-value for "formulation" should also be significant at the 10% significance level. Maybe you're using a different denominator than expected...

(...) the p-value for "formulation" should also be significant at the 5% significance level assuming we work with alpha=5% and therefore 90% CI's.
Alpha is alpha, unless we talk two-stage approaches and the like.

—
Pass or fail!
ElMaestro

Complete thread:

Relationship between calculated 90% CI and sign. treatment effect in BE GM 2017-03-27 19:40 [General Statistics]
- 1–2α CI and TOST at α 0.05 Helmut 2017-03-27 23:47
  - 1–2α CI and TOST at α 0.05 GM 2017-03-28 06:50
    - 1–2α CI and TOST at α 0.05 DavidManteigas 2017-03-28 11:48
      - 1–2α CI and TOST at α 0.05ElMaestro 2017-03-28 13:12
        
        alpha TOST is not alpha 2-sided d_labes 2017-03-28 15:12
        
        Interesting! ElMaestro 2017-03-28 21:10
        
        Google has the answer d_labes 2017-03-29 08:20
        Interesting! DavidManteigas 2017-03-29 11:16
        
        Interesting! ElMaestro 2017-03-29 11:20
        
        Interesting! DavidManteigas 2017-03-29 12:28
        
        95% CI for a test on difference d_labes 2017-03-29 14:24
        Interesting! GM 2017-03-29 20:06
        
        Interesting! nobody 2017-03-30 08:24
      - Relationship between calculated 90% CI and sign. treatment effect in BE GM 2017-03-29 12:11
        
        Relationship between calculated 90% CI and sign. treatment effect in BE DavidManteigas 2017-03-29 12:30

1–2α CI and TOST at α 0.05 [General Sta­tis­tics]

Complete thread:

1–2α CI and TOST at α 0.05 [General Statistics]