+ Reply to Thread
Results 1 to 2 of 2

Thread: How to analyze this design?

  1. #1
    Points: 277, Level: 5
    Level completed: 54%, Points required for next Level: 23

    Posts
    1
    Thanks
    0
    Thanked 0 Times in 0 Posts

    How to analyze this design?




    Let's say you're measuring performance on a test under these conditions:

    A- Control, unstressed
    B- Under stress
    C- 1 hour after stress occurred
    D- 4 hours after stress occurred
    E- 1 day after stress occurred
    F- 2 days after stress occurred

    Every group is an independent sample set. Not a longitudinal design.

    You expect a difference between A and B, but you are not expecting any of the other groups to be different from the control. Indeed this is what you find. How do you analyze?

    Do you decide in advance to make planned comparisons, comparing each experimental group to the control and that's all? Or do you run a one-way ANOVA, then perform post-hoc comparisons? Would this design make it more difficult to detect a significant effect using ANOVA even if there's an A-B difference, since there are so many groups equivalent and indeed hypothesized to be so?

  2. #2
    TS Contributor
    Points: 5,705, Level: 48
    Level completed: 78%, Points required for next Level: 45

    Location
    Nottingham
    Posts
    681
    Thanks
    0
    Thanked 27 Times in 27 Posts

    Re: How to analyze this design?


    For each condition you have asked different people? The performance you measure is continuous? Numbers right?

+ Reply to Thread

           




Posting Permissions

  • You may not post new threads
  • You may not post replies
  • You may not post attachments
  • You may not edit your posts






Advertise on Talk Stats