+ Reply to Thread
Results 1 to 2 of 2

Thread: Subadditivity?

  1. #1
    Points: 998, Level: 16
    Level completed: 98%, Points required for next Level: 2

    Location
    Winnipeg, Manitoba, Canada
    Posts
    6
    Thanks
    0
    Thanked 0 Times in 0 Posts

    Subadditivity?




    I am being asked whether certain interactions in a multiple logistic regression model with are subadditive or not. I was told to use a graph to demonstrate this. What is the best way to demonstrate that interaction terms are subadditive. My first guess is that I make a 2 d graph with one of the variables on x and my binomial response variable on y and gradually change the other effect (which is interacting with the variable on x) in this model to show that the loglinear curve is not flipping in the other direction at any particular point.

    I am also having a lot of trouble visualizing what the model would look like if the interaction effects were not subadditive (would this be superadditive?). Does anyone know of any literature on this topic? I'm finding this extremely frustrating and I don't know where to turn. I just keep getting told that I need to understand the relationship between my variables better.

    Any help would be greatly appreciated,

    Adam

  2. #2
    Points: 998, Level: 16
    Level completed: 98%, Points required for next Level: 2

    Location
    Winnipeg, Manitoba, Canada
    Posts
    6
    Thanks
    0
    Thanked 0 Times in 0 Posts

    Re: Subadditivity?


    please disregard the *with in the first sentence.

+ 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