+ Reply to Thread
Results 1 to 5 of 5

Thread: Really stuck with moderated regression...

  1. #1
    Points: 211, Level: 4
    Level completed: 22%, Points required for next Level: 39

    Posts
    3
    Thanks
    0
    Thanked 0 Times in 0 Posts

    Really stuck with moderated regression...




    I have used a hierarchical regression analysis in SPSS, however the analysis isn't producing any significant interactions
    • The criterion variable = General well-being.
    • Control variables = age/gender/illness status.
    • Predictor variables = Coping (5 scales)/Social Support (2 scales).

    I centred all of the predictors (continuous variables) and recoded the categorical variables (gender and illness status). I then created my interaction terms.

    Aftr entering the DV (general well-being), I entered the controls in block 1, the predictors in block 2, and the interaction terms in block 3.

    Where am I going wrong? Really need some help please!

  2. #2
    TS Contributor
    Points: 17,779, Level: 84
    Level completed: 86%, Points required for next Level: 71
    Karabiner's Avatar
    Location
    FC Schalke 04, Germany
    Posts
    2,542
    Thanks
    56
    Thanked 640 Times in 602 Posts

    Re: Really stuck with moderated regression...

    however the analysis isn't producing any significant interactions
    Why does it have to?

    By the way, one of the most important information (sample size) is missing.

    I then created my interaction terms.
    So there were (at least) 21 interaction terms?

    interaction terms in block 3
    And there was no significant R change?

    Kind regards

    K.

  3. #3
    Points: 211, Level: 4
    Level completed: 22%, Points required for next Level: 39

    Posts
    3
    Thanks
    0
    Thanked 0 Times in 0 Posts

    Re: Really stuck with moderated regression...

    Hi,

    The sample consists of 110 participants. I'm convinced I've gone wrong as the data was provided by Uni, so I'm sure there should be some significant interactions.

    The interaction terms consist of:

    Cope1*Support1
    Cope1*Support2
    Cope2*Support1
    ...etc.

    In total there are 10 interaction terms, should I have included something else?

    Thanks

  4. #4
    TS Contributor
    Points: 17,779, Level: 84
    Level completed: 86%, Points required for next Level: 71
    Karabiner's Avatar
    Location
    FC Schalke 04, Germany
    Posts
    2,542
    Thanks
    56
    Thanked 640 Times in 602 Posts

    Re: Really stuck with moderated regression...

    20 predictors with just 110 participants is a bit too many.
    What was the exact task formulation?
    so I'm sure there should be some significant interactions.
    This is not yet convincing.

    Kind regards

    K.

  5. #5
    Points: 211, Level: 4
    Level completed: 22%, Points required for next Level: 39

    Posts
    3
    Thanks
    0
    Thanked 0 Times in 0 Posts

    Re: Really stuck with moderated regression...


    Quote Originally Posted by Karabiner View Post
    20 predictors with just 110 participants is a bit too many.
    What was the exact task formulation?

    This is not yet convincing.

    Kind regards

    K.
    Hmmm... the instructions for this assignment are sooo vague. For this part I'm trying to work out, I basically have to answer the question... Which factors predict well-being? 'Hierarchical regression' and 'mediators/moderators' are mentioned very briefly in the instruction sheet. I am so confused

    Thanks

+ 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