+ Reply to Thread
Results 1 to 3 of 3

Thread: Comparing effect sizes of two longitudinal linear relationships

Hybrid View

  1. #1

    Comparing effect sizes of two longitudinal linear relationships

    Is there a way to determine if one longitudinal linear relationship is significantly stronger than another? I was planning on using regression (moderated multiple regression with PROCESS macro for SPSS because I have two groups and covariates) and simply looking at the R squared values, but my adviser wanted me to make sure there was not a way to test this.

    In model 1: x= change in variable A from time 1 to time 2, y= variable B at time 3.

    In model 2: x= variable B at time 2, y= change in variable A from time 2 to time 3.

    (change in variable A will be residualized change scores)

    Any ideas you might have would be appreciated.

  2. #2
    TS Contributor
    Points: 18,889, Level: 87
    Level completed: 8%, Points required for next Level: 461
    CowboyBear's Avatar
    Location
    New Zealand
    Posts
    2,062
    Thanks
    121
    Thanked 427 Times in 328 Posts

    Re: Comparing effect sizes of two longitudinal linear relationships

    Hi there

    I guess I would wonder here what it is that you're really trying to find out. Given that your two models estimate quite different things, it's sort of obvious that the two population slopes won't be exactly the same. (And that's all a significance test would be trying to establish - whether the two slopes are exactly the same in the population). So how have you come to be interested in making this comparison?
    Matt aka CB | twitter.com/matthewmatix

  3. #3
    Points: 1,741, Level: 24
    Level completed: 41%, Points required for next Level: 59

    Posts
    230
    Thanks
    37
    Thanked 68 Times in 59 Posts

    Re: Comparing effect sizes of two longitudinal linear relationships

    Quote Originally Posted by CowboyBear View Post
    Hi there

    I guess I would wonder here what it is that you're really trying to find out. Given that your two models estimate quite different things, it's sort of obvious that the two population slopes won't be exactly the same. (And that's all a significance test would be trying to establish - whether the two slopes are exactly the same in the population). So how have you come to be interested in making this comparison?
    Worth adding that the dependent variables are different, so you can't compare R-square values, either.

+ Reply to Thread

           




Tags for this 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