+ Reply to Thread
Results 1 to 2 of 2

Thread: Logistic Regression

  1. #1
    Points: 148, Level: 2
    Level completed: 96%, Points required for next Level: 2

    Posts
    2
    Thanks
    0
    Thanked 0 Times in 0 Posts

    Logistic Regression




    Hii!
    I have some, I guess, pretty basic questions regarding logistic regression.

    I collected data and my dependent variable is, whether respondents always visit the same store (AVC=0/1). In case, respondents did not always visit the same store (AVC=0), they were asked to provide reasons for that (they could choose multiple from several given reasons). Therefore, the data is completely separated.
    Now I would like to see, how my independent variables (e.g. age) relate to AVC. The direct effects are no problem, but how about if I also wanna know the interaction effects between the reasons and age, for example?

    I think I cannot include that in this model, so theoretically I would do a multinomial regression with the Reasons (Levels: Reason 1 Reason 2 Reason 3 etc.). But since my professor advised me to not use SPSS for a MNL model (and I am out of country and do not have STATA on my computer), I was wondering whether it would be useful to conduct a logistic regression each for every reason (Reason 1; 0/1 etc.), additionally to the model with AVC as the dependent variable? I know its more effort, but does it make sense?

    I appreciate every advise!!

  2. #2
    Fortran must die
    Points: 58,790, Level: 100
    Level completed: 0%, Points required for next Level: 0
    noetsi's Avatar
    Posts
    6,532
    Thanks
    692
    Thanked 915 Times in 874 Posts

    Re: Logistic Regression


    I am not sure what your dependent variable looks like. If it is 1 if they went to the same store and a reason (of which there are several apparently) if they did not then you might be able to use multinomial logistic regression. However, if there are too many reasons then in practice you will run into problems commonly if you try to run that and interpretation becomes very difficult (again this is in practice, in theory you can do it).

    Reasons can not interact with your other independent variables. Reasons is part of the dependent variable and only the independent variables can interact.
    "Very few theories have been abandoned because they were found to be invalid on the basis of empirical evidence...." Spanos, 1995

+ 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