+ Reply to Thread
Page 2 of 2 FirstFirst 1 2
Results 16 to 17 of 17

Thread: Non-parametric equivalent of a factorial anova (not repeated measures)?

  1. #16
    Points: 539, Level: 10
    Level completed: 78%, Points required for next Level: 11

    Posts
    8
    Thanks
    1
    Thanked 0 Times in 0 Posts

    Re: Non-parametric equivalent of a factorial anova (not repeated measures)?




    I think the explanations are a bit above my level, for analysis purposes we (those on my course) have only ever been shown to carry out a normality test on the data in spss (using shaprio-wilk) or minitab (anderson darling) and then interpret from the the p value whether the data is normally distributed. Then eithr select the parametric or equivalent test needed. I am sure this seems very simplistic (or maybe even inaccurate) but it is all I have ever been shown to do (and passed previous assignments with). As I said I am studying animal welfare so not a maths/business subject etc. Literally my problem was that where in my previous analysis I was used Kruskal-Wallis instead of one way-anovas now that I am looking at interactive effects of two independents I can't seem to find what test I need as a non-para equivalent to the two-way anova. Sorry if I just keep repeating myself but I just seem to have spent all day getting more and more lost over it all!

    I do really appreciate everyones help.
    Last edited by chegginson; 12-03-2011 at 02:52 PM.

  2. #17
    TS Contributor
    Points: 22,432, Level: 93
    Level completed: 9%, Points required for next Level: 918
    spunky's Avatar
    Location
    vancouver, canada
    Posts
    2,135
    Thanks
    166
    Thanked 537 Times in 431 Posts

    Re: Non-parametric equivalent of a factorial anova (not repeated measures)?


    Quote Originally Posted by trinker View Post
    You may have to type syntax to do this (not sure SPSS isn't my program of choice)
    nah, AVOID SPSS' syntax whenever you can. it's horribly, horribly unintuitve...

    from the menu section do:

    Analyze ---> General Linear Model ----> Univariate

    and once you've declared your dependent variable and your factors (putting them in the right boxes) click on "Save" and where it says "Residuals" just click the box that says "Standardized" (just because it's good to have things standardized) and SPSS will create a column with the residuals. do the Shapiro-Wilks test on that and that's what you should worry about.
    for all your psychometric needs! https://psychometroscar.wordpress.com/about/

+ Reply to Thread
Page 2 of 2 FirstFirst 1 2

           




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