+ Reply to Thread
Results 1 to 4 of 4

Thread: A new comer has a question about multicollinearty problem

  1. #1
    Points: 770, Level: 14
    Level completed: 70%, Points required for next Level: 30

    Posts
    2
    Thanks
    0
    Thanked 0 Times in 0 Posts

    A new comer has a question about multicollinearty problem




    I am running a OLS model with 9 IVs. The model results are good (a fitting model), but I got a high negative multicollinearity problem for two IVs (-.85), one is continuous, the other dummy.
    I tried to delete the dummy IV to improve model. It did improve. But I actually do not want to delete the dummy and even want to do an interaction between the two highly correlated IVs in the model. How should I handle this situation?
    Thanks.

  2. #2
    Points: 770, Level: 14
    Level completed: 70%, Points required for next Level: 30

    Posts
    2
    Thanks
    0
    Thanked 0 Times in 0 Posts

    Re: A new comer has a question about multicollinearty problem

    I read some articles about multicollinearty on websites. Some of them advised not to delete one of highly correlated variables that quickly. My puzzle is that if I do not delete one of them, how should I handle this situation?
    Thanks.

  3. #3
    Points: 940, Level: 16
    Level completed: 40%, Points required for next Level: 60

    Location
    Vancouver
    Posts
    18
    Thanks
    1
    Thanked 1 Time in 1 Post

    Re: A new comer has a question about multicollinearty problem

    some people will just leave it as it is.

    what do you mean by
    "I tried to delete the dummy IV to improve model. It did improve"
    what had improved?

    you can compbine two variables into 1 (take sum or product)

  4. #4
    Devorador de queso
    Points: 95,781, Level: 100
    Level completed: 0%, Points required for next Level: 0
    Awards:
    Posting AwardCommunity AwardDiscussion EnderFrequent Poster
    Dason's Avatar
    Location
    Tampa, FL
    Posts
    12,933
    Thanks
    307
    Thanked 2,629 Times in 2,245 Posts

    Re: A new comer has a question about multicollinearty problem


    What is your goal with this analysis? Are you looking for a good predictive model or are you looking to see which factors are significant?

+ 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