+ Reply to Thread
Results 1 to 3 of 3

Thread: Logistic Regression

  1. #1
    Points: 328, Level: 6
    Level completed: 56%, Points required for next Level: 22

    Posts
    5
    Thanks
    0
    Thanked 0 Times in 0 Posts

    Logistic Regression




    Letís consider the logistic regression model, which we will refer to as Model 1, given by
    log(pi / [1-pi]) = 0.25 + 0.32*X1 + 0.70*X2 + 0.50*X3
    In the above formula, X3 is an indicator variable with X3=0 if the observation is from Group A and X3=1 if the observation is from Group B.

    (1) For X1=2 and X2=1 compute the log-odds for each group, i.e. X3=0 and X3=1.
    (2) For X1=2 and X2=1 compute the odds for each group, i.e. X3=0 and X3=1.
    (3) For X1=2 and X2=1 compute the probability of an event for each group, i.e. X3=0 and X3=1.

    (4) Use the odds that you found in QUESTION 2 to compute the relative odds of Group B to Group A. How does this number compare to the result in Question #5. Does this make sense?

    (5) Using the equation for Model 1, compute the relative odds associated with X3, i.e. the relative odds of Group B compared to Group A.




    I made a start below. Thanks

    1) If we set X1=2 and X2 = 1, then logit_Y = 0.25 + 0.64 + 0.7 + 0.5*X3 = 1.59 + 0.5*X3
    If we set X3 = 0, logit is then 1.59. For X3=1, logit is 2.09. And the log-odds then: 1.59/2.09 = 0.7608


    2) We can remove the log of the answer in part 1, to compute the odds instead of the log-odds. That is, via the exponential: e^(0.7608) = 2.14

  2. #2
    TS Contributor
    Points: 19,199, Level: 87
    Level completed: 70%, Points required for next Level: 151
    CowboyBear's Avatar
    Location
    New Zealand
    Posts
    2,080
    Thanks
    123
    Thanked 429 Times in 330 Posts

    Re: Logistic Regression

    Sorry for the delay releasing your post - it was caught in our spam filter for some reason.
    Matt aka CB | twitter.com/matthewmatix

  3. #3
    TS Contributor
    Points: 12,501, Level: 73
    Level completed: 13%, Points required for next Level: 349
    rogojel's Avatar
    Location
    I work in Europe, live in Hungary
    Posts
    1,491
    Thanks
    162
    Thanked 334 Times in 314 Posts

    Re: Logistic Regression


    hi,
    the definition of odds is p/(1-p) so the formula directly computes the log odds.

    regards

+ 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