+ Reply to Thread
Results 1 to 2 of 2

Thread: interaction continuous*dummy:possible to treat continuous variable as the moderator?

  1. #1
    Points: 110, Level: 2
    Level completed: 20%, Points required for next Level: 40

    Posts
    1
    Thanks
    1
    Thanked 0 Times in 0 Posts

    interaction continuous*dummy:possible to treat continuous variable as the moderator?




    Hey everyone. This is my first post here so please be kind to me .

    For my thesis my aim is to run a moderation analysis between organizational commitment and training. My dependent variable is job satisfaction.

    Org.commitment comes from 4 5-point likert-items, therefore I calculated the median for each observation, in order to get a total measure of org.commitment and to treat this variable as continuous. Training comes from a 6-point likert item. Out of this variable, I created 2 dummy variables: high training and low training.

    Therefore, one interaction term is org.commitment * high training. I suppose that there is no point to include org. commitment *low training if I am not mistaken. The way I think it is that the effect of training is different at different levels of org.commitment.
    My question is: is it possible to think of org.commitment as the moderator variable?

    All the examples that I have found online, when interacting a continuous variable with a dummy variable, they treat the dummy variable as the moderator and not the continuous one, as I want to do.

    When running OLS analysis, the coefficient that I get is:
    Dummy variable for high training: ,153

    Org. commitment (centered): ,335

    Interaction term: Org.commitment(centered) * high training: -,022

    Does it mean that when organizational commitment increases, the effect of high training on job satisfaction decreases? Or in other words, that the positive effect of high training on job satisfaction weakens as org.commitment increases?

    When I interact commitment with low training the coefficient is: ,022.

    How should I proceed? It is obvious that I am not really good in statistics but I am searching the web literally the whole day but I have not found an answer yet. I anyone can help me I would appreciate it really really a lot!
    Thanks!!

  2. #2
    TS Contributor
    Points: 17,742, Level: 84
    Level completed: 79%, Points required for next Level: 108
    Karabiner's Avatar
    Location
    FC Schalke 04, Germany
    Posts
    2,539
    Thanks
    56
    Thanked 639 Times in 601 Posts

    Re: interaction continuous*dummy:possible to treat continuous variable as the moderat


    is it possible to think of org.commitment as the moderator variable?
    You can think of it this way, if you wish.
    Interaction term: Org.commitment(centered) * high training: -,022
    The coefficient is very small. And not statistically significant,
    I suppose, unless your sample size is very large. Do you really
    wish to interpret such a tiny effect?
    when organizational commitment increases, the effect of high training on job satisfaction decreases
    Yes, the relationship between training and satisfaction
    is (a very little bit) stronger in those with low commitment
    than in those with high commitment.

    HTH

    K.

  3. The Following User Says Thank You to Karabiner For This Useful Post:

    noodlee999 (06-20-2016)

+ 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