+ Reply to Thread
Results 1 to 3 of 3

Thread: Accounting for other variables when looking for main effects (regression)

  1. #1
    Points: 1,426, Level: 21
    Level completed: 26%, Points required for next Level: 74

    Posts
    14
    Thanks
    0
    Thanked 0 Times in 0 Posts

    Accounting for other variables when looking for main effects (regression)




    I am doing a negative binomial regression, to look for interactions between categorical and continuous predictors. I am currently reporting main effects for both predictors, but am wondering whether I should account for the other predictor when doing so.

    So, if lang2 & BDCSBI are the predictors and sdq_conduct is the outcome, should my code look like:
    svy: nbreg sdq_conduct lang2 BDCSBI
    or
    svy: nbreg sdq_conduct lang2

    So effectively, should I include both predictors in the code when searching for the main effect of just one?

    Also, what is the difference between simple and main effects?
    Thanks for any help.

  2. #2
    Points: 13, Level: 1
    Level completed: 25%, Points required for next Level: 37

    Posts
    3
    Thanks
    0
    Thanked 0 Times in 0 Posts

    Re: Accounting for other variables when looking for main effects (regression)

    Not interested in any interaction effects? Main effect - the effect of an IV on the DV ignoring all other IVs. Following an interaction, a simple effect is the effect of an IV on a particular level of another IV.

  3. #3
    Omega Contributor
    Points: 38,396, Level: 100
    Level completed: 0%, Points required for next Level: 0
    hlsmith's Avatar
    Location
    Not Ames, IA
    Posts
    7,001
    Thanks
    398
    Thanked 1,186 Times in 1,147 Posts

    Re: Accounting for other variables when looking for main effects (regression)


    If you have significant interaction terms in your model, you no longer look at the main effects of the terms that are in the interaction. This is because those main effects are conditional on another term. Multiplicative interaction term model should look like:


    Y = X1 + X2 + X1*X2
    Stop cowardice, ban guns!

+ 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