+ Reply to Thread
Results 1 to 2 of 2

Thread: How to compare 4 related, non-parametric, categorical means.

  1. #1
    Points: 4, Level: 1
    Level completed: 7%, Points required for next Level: 46

    Thanked 0 Times in 0 Posts

    How to compare 4 related, non-parametric, categorical means.

    A friend of mine did a study where she implanted 4 different types of surgical mesh into 10 rats. She then meassured adhesion formation index on a scale from 0 to 4.

    We want to compare the mean adhesion index between all 4 groups, now, my question is what kind of test you think we should use. I think ANOVA is no good because of correlation between groups (samples sharing the same rat, I know its a mess), and also because the variable is categorical. Running multiple paired ttests would yield a high alfa error.

    Does someone know what kind of test could be useful? Ill be using SPSS btw.

    Thank you in advance

  2. #2
    Omega Contributor
    Points: 38,303, Level: 100
    Level completed: 0%, Points required for next Level: 0
    hlsmith's Avatar
    Not Ames, IA
    Thanked 1,185 Times in 1,146 Posts

    Re: How to compare 4 related, non-parametric, categorical means.

    If the 0 to 4 is a scale variable, you could use Kruskal Wallis test. It is the nonparametric equivalent to ANOVA. Though, if the test reveals significance you would want to run pairwise Wilcoxon rank sum tests (nonparametric equivalents to ttest). And yes, you would want to correct the p-values or alpha for multiplicity. In these tests, many people will use the medians instead of means due to data dispersion issues.
    Stop cowardice, ban guns!

+ 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