Results 1 to 3 of 3

Thread: Experimental statistics help

  1. #1 Experimental statistics help 
    Forum Radioactive Isotope MagiMaster's Avatar
    Join Date
    Jul 2006
    I'm trying to work out some details concerning experimental design. I have two tests that I want to compare. I've been told that the following will not work because it confounds the test results and any ordering effect that exists.
    - Take n subjects and have them take test A followed by test B
    - Take another n subjects and have them take test B followed by test A

    I thought the whole point of splitting the subjects into such groups would be to deal with such ordering effects.

    Reply With Quote  


  3. #2  
    Forum Professor
    Join Date
    Jul 2008
    New York State
    If you are intending to test the ordering effects, you are on the right track.

    Reply With Quote  

  4. #3  
    Forum Radioactive Isotope MagiMaster's Avatar
    Join Date
    Jul 2006
    Having discussed this with a professor specializing in such things, the problem isn't actually that this set up can't test for ordering effects, but that if there is a significant interaction between the ordering effect and the main effect, this test can't tell you anything further.
    Reply With Quote  

Similar Threads

  1. Replies: 3
    Last Post: March 4th, 2014, 05:17 PM
  2. Re: IQ statistics
    By Hominy in forum General Discussion
    Replies: 0
    Last Post: December 27th, 2012, 05:44 PM
  3. Replies: 1
    Last Post: October 3rd, 2012, 12:21 PM
  4. I need some help with statistics
    By Blackened in forum Mathematics
    Replies: 3
    Last Post: January 2nd, 2012, 07:16 PM
  5. Experimental 3D Gravity Simulator
    By Leuke Gast in forum Links
    Replies: 2
    Last Post: November 14th, 2006, 05:06 PM
Posting Permissions
  • You may not post new threads
  • You may not post replies
  • You may not post attachments
  • You may not edit your posts