+ Reply to Thread
Results 1 to 2 of 2

Thread: When Logistic Regression Coefficient Increases

  1. #1
    Points: 256, Level: 5
    Level completed: 12%, Points required for next Level: 44

    Posts
    1
    Thanks
    0
    Thanked 0 Times in 0 Posts

    When Logistic Regression Coefficient Increases




    Hi All,

    I am trying to understand the relationship between naturalization (whether someone becomes a naturalized citizen or not), using data from the American Community Survey.

    My dependent variable: Naturalization (non-citizen vs. naturalized-citizen).
    My independent variables: educational attainment (x1), sex (x2), and age (x3).

    Model 1: y = x1;
    Model 2: y = x1 + x2 + x3;

    Here is the problem. From model 1 to model 2, the odds ratio of x1 increases from 1.1 to 1.7. I was expecting the odds ratio of x1 to decrease by adding x2 and x3.

    My question is, what does it mean when the odds ratio of x1 increases after adding additional predictors to the model? Any advice would be greatly appreciated. Thanks!

  2. #2
    Cookie Scientist
    Points: 13,431, Level: 75
    Level completed: 46%, Points required for next Level: 219
    Jake's Avatar
    Location
    Austin, TX
    Posts
    1,293
    Thanks
    66
    Thanked 584 Times in 438 Posts

    Re: When Logistic Regression Coefficient Increases


    It means there was some redundancy ("multicollinearity") between x1 and your other predictors x2 and x3. The effect of x1 in model 1 was being "suppressed" due to being either positively related to a predictor that has a negative association with the DV, or negatively related to a predictor that has a positive association with the DV, or some combination of both.
    “In God we trust. All others must bring data.”
    ~W. Edwards Deming

+ 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