GLM repeated measures concern/question

Discussion in 'SPSS' started by dave walsh, Dec 27, 2011.

  1. dave walsh

    dave walsh Guest


    We have a potential concern with analyzing our data:

    Quick Backgroud: Research Design is 2x2 Mixed Model involving the
    effects of central blind spots on Visual Search. The subjects are
    searching for a target (O) embedded among distracters (C’s). The set
    sizes we have used are 1, 8, and 32 (1 stimuli on screen =1set size; 8
    stimuli on screen= 8 set size and so forth).

    Problem: The potential concern is the set sizes (predictor variables)
    are NON-LINEAR in spacing (unequal). Our plan is to use GLM Repeated
    Measures to analyze the data, but we’re wondering if this GLM model
    can be used with the set size non-linearity…………another words does the
    GLM model implicitly assume linear spacing with its analyses?

    If yes, what are the potential solutions?

    dave walsh, Dec 27, 2011
    1. Advertisements

  2. dave walsh

    Jeff Guest

    The GLM does not assume linear spacing of the different values of
    the predictor variable. In some versions, it does assume that the
    dependent variable is linearly related to the predictor variable
    (subject to some random error), which may or may not be a
    realistic assumption in your case.

    Jeff, Dec 31, 2011
    1. Advertisements

Ask a Question

Want to reply to this thread or ask your own question?

You'll need to choose a username for the site, which only take a couple of moments (here). After that, you can post your question and our members will help you out.