Bioequivalence and Bioavailability Forum • randomization: validation

randomization: validation [Regulatives / Guidelines]

posted by ElMaestro – Denmark, 2012-06-16 15:31 (5112 d 12:09 ago) – Posting: # 8754
Views: 15,234

Hi HS,

I don't think I would use a runs test prior to releasing a randomisation scheme. This screws the principle of randomness; even random sequences will have a significant runs test occasionally and still be 'random' whatever that words means.

ElMaestro's approach:

Populate an array will RT and TR in equal numbers. E.g. index 1-12 are RT and 13-24 are TR if we have 24 subjects.
Loop through all entries 1-24 and swap each exactly once with a random index between 1 and 24. The random index must come from a uniform distribution. A NLYW dancing around a hat with 24 coloured and numbered balls may be used; but be advised that NLYW's may display unpredictable behaviour and variations in time and space as regards willingness to dance around hats and draw balls.
Release scheme without testing for randomness.

—
Pass or fail!
ElMaestro

Complete thread:

USFDA requirement for randomization Ravi 2012-06-15 13:39 [Regulatives / Guidelines]
- randomization: validation Helmut 2012-06-15 17:39
  - randomization: runs test? validation? d_labes 2012-06-16 13:10
    - randomization: runs test? validation? Helmut 2012-06-16 14:00
      - probability nearly zero? d_labes 2012-06-16 16:11
        
        probability nearly zero! Helmut 2012-06-16 17:08
        
        R-package randomizeBE d_labes 2012-07-06 09:54
        
        R-package randomizeBE Helmut 2012-07-06 12:51
  - randomization: validationElMaestro 2012-06-16 13:31
    - randomization: runs test Helmut 2012-06-16 14:42
      - randomization: runs test ElMaestro 2012-06-16 14:48
        
        randomization: runs test Helmut 2012-06-16 15:10
      - very cool coding style ElMaestro 2012-06-16 19:12
        
        Better a good steal than a bad reinvention Helmut 2012-06-17 13:22
        
        Better a good steal than a bad reinvention ElMaestro 2012-06-17 19:58
        
        Sorry! Helmut 2012-06-18 13:26
        
        Sorry! ElMaestro 2012-06-18 15:19
        
        Dancing with the dice d_labes 2012-06-18 15:38
        
        Silly's randomization 2x2 xover d_labes 2012-06-18 16:30
        
        Silly's randomization 2x2 xover Helmut 2012-06-18 17:14
        
        Clumsy code Helmut 2012-06-18 17:42
        
        Clumsy code ElMaestro 2012-06-18 18:01
        
        Speed kills Helmut 2012-06-18 18:56
        
        Speed kills jag009 2012-09-17 21:46