Advertisement
If you have a new account but are having problems posting or verifying your account, please email us on hello@boards.ie for help. Thanks :)
Hello all! Please ensure that you are posting a new thread or question in the appropriate forum. The Feedback forum is overwhelmed with questions that are having to be moved elsewhere. If you need help to verify your account contact hello@boards.ie
Hi there,
There is an issue with role permissions that is being worked on at the moment.
If you are having trouble with access or permissions on regional forums please post here to get access: https://www.boards.ie/discussion/2058365403/you-do-not-have-permission-for-that#latest

supermarket intervention which analyses in spss

  • 07-01-2009 1:19pm
    #1
    NanoNano
    Closed Accounts Posts: 29 ✭


    For my thesis I have data for a supermarket intervention to see if the fruit ,vegetables and fat consumption changed.
    My tutor said I had to test at least 1 of the hypothesis with repeated measures. I tried that but get very confused with the sphericity problem as I have only a pre-test and post test design and then sphericity can't be applied. Is it possible to do a repeated measure? A Manova seems more appropriate if I understand the theory behind it correctly.
    The main problem is whatever analysis I have to do, I don't know how to interpreted it. Does anyone know which analysis would be suitable and are there guidelines in how to explain the findings?

    I have SPSS 16 and my hypothesis are: 1. The supermarket intervention will lead to a higher consumption of fruit and vegetables intake.
    The supermarket intervention will lead to a lower consumption of fat intake.

    I hope someone can help.
    Thanks


Comments

  • #2
    2Scoops
    Registered Users, Registered Users 2 Posts: 1,845 ✭✭✭2Scoops


    NanoNano wrote: »
    For my thesis I have data for a supermarket intervention to see if the fruit ,vegetables and fat consumption changed.
    My tutor said I had to test at least 1 of the hypothesis with repeated measures.

    That makes sense - a pre/post design lends itself to RM analysis.
    NanoNano wrote: »
    I tried that but get very confused with the sphericity problem as I have only a pre-test and post test design and then sphericity can't be applied. Is it possible to do a repeated measure?

    When there are only two variables, calculating sphericity isn't as big a deal. A a paired t-test is still a repeated measures model.
    NanoNano wrote: »
    A Manova seems more appropriate if I understand the theory behind it correctly.

    MANOVA is a non-parametric alternative that doesn't rely on as many assumptions, such as sphericity. Both will work but the parametric test will have greater power, assuming sphericity etc. isn't a problem.
    NanoNano wrote: »
    The main problem is whatever analysis I have to do, I don't know how to interpreted it. Does anyone know which analysis would be suitable and are there guidelines in how to explain the findings?

    Both approaches could be used. I'm familiar with both. If you want to describe your output and what you don't understand, I can look over it for you.


  • #3
    NanoNano
    Closed Accounts Posts: 29 ✭NanoNano


    Thanks 2scoops. Don't have my laptop now. Will post output tomorrow. I'm relieved that there is somebody out there that knows what to do.


  • #4
    2Scoops
    Registered Users, Registered Users 2 Posts: 1,845 ✭✭✭2Scoops


    No worries :pac: If you post anything, make sure to black out any sensitive information if you don't want anyone seeing it before your thesis is complete, or if you intend to publish the results elsewhere in the future.


  • #5
    2Scoops
    Registered Users, Registered Users 2 Posts: 1,845 ✭✭✭2Scoops


    I've attached a short video of how run MANOVA and RM ANOVA through SPSS. It should help you complete your analysis. There is also a file that briefly explains the output.

    You can't run RM ANOVA on the nominal variables like attitude etc. You will need MANOVA or chi square.

    Your control group is different to your other groups in certain variables like age. These can be included as covariates in your RM ANOVA to help rule out their influence.


Advertisement