+ Reply to Thread
Results 1 to 5 of 5

Thread: Interaction effect

  1. #1
    Points: 78, Level: 1
    Level completed: 56%, Points required for next Level: 22

    Posts
    7
    Thanks
    1
    Thanked 0 Times in 0 Posts

    Interaction effect




    Hey guys,

    I would like to investigate effect of a treatment in randomized control trial. Also, I would like to investigate the moderating effect of motivation (of the participants who are included in the treatment group).

    I wanted to use a multiple linear regression with an interaction term in this way:

    y= alpha + beta_1 * treatment dummy + beta_2* motivation + beta_3* treatment dummy * motivation

    Then, I realized that motivation will not be measured for the participants who are only in the control group.

    Would it be possible to use the following model instead?

    y= alpha + beta_1 * treatment dummy + beta_2* treatment dummy * motivation (setting motivation zero for the control group)

    Cheers,
    floriisco

  2. #2
    Devorador de queso
    Points: 95,705, Level: 100
    Level completed: 0%, Points required for next Level: 0
    Awards:
    Posting AwardCommunity AwardDiscussion EnderFrequent Poster
    Dason's Avatar
    Location
    Tampa, FL
    Posts
    12,931
    Thanks
    307
    Thanked 2,629 Times in 2,245 Posts

    Re: Interaction effect

    How many treatments are there?
    I don't have emotions and sometimes that makes me very sad.

  3. #3
    Points: 78, Level: 1
    Level completed: 56%, Points required for next Level: 22

    Posts
    7
    Thanks
    1
    Thanked 0 Times in 0 Posts

    Re: Interaction effect

    Only one treatment. The treatment dummy variable would take value 1, if the participant is in the treatment group and 0 otherwise

  4. #4
    Devorador de queso
    Points: 95,705, Level: 100
    Level completed: 0%, Points required for next Level: 0
    Awards:
    Posting AwardCommunity AwardDiscussion EnderFrequent Poster
    Dason's Avatar
    Location
    Tampa, FL
    Posts
    12,931
    Thanks
    307
    Thanked 2,629 Times in 2,245 Posts

    Re: Interaction effect

    If you're setting motivation to be 0 for the control group anyways then adding an interaction term in doesn't change the model at all. You don't need the interaction term. The two models you posted would be equivalent in this case.
    I don't have emotions and sometimes that makes me very sad.

  5. The Following User Says Thank You to Dason For This Useful Post:

    floriisco (08-15-2016)

  6. #5
    Points: 78, Level: 1
    Level completed: 56%, Points required for next Level: 22

    Posts
    7
    Thanks
    1
    Thanked 0 Times in 0 Posts

    Re: Interaction effect


    What I would like to find out is 1) the effect of the treatment itself and 2) whether motivation affects the magnitude of effect 1)? How can I do this?

    Like this: y= alpha + beta_1 * treatment dummy + beta_2* motivation?

+ 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