+ Reply to Thread
Results 1 to 5 of 5

Thread: Logistic Regression

  1. #1
    Points: 1,522, Level: 22
    Level completed: 22%, Points required for next Level: 78

    Posts
    16
    Thanks
    0
    Thanked 0 Times in 0 Posts

    Logistic Regression




    Hello
    I am going to start building a Logistic Regression model based on medical data for the purpose of classification. My problem started with "Hosmer and Lemeshow test" and its insignificant result!, what should I do to solve this issue and what procedures should follow to make a correct analysis, rise the efficiency of the model and have the best fit for my model.
    Thank you.

  2. #2
    Omega Contributor
    Points: 38,406, Level: 100
    Level completed: 0%, Points required for next Level: 0
    hlsmith's Avatar
    Location
    Not Ames, IA
    Posts
    7,002
    Thanks
    398
    Thanked 1,186 Times in 1,147 Posts

    Re: Logistic Regression

    Tell us more a out the model, sample size, proportion with outcome, number of covariate, format of covariates, HL. value etc.
    Stop cowardice, ban guns!

  3. #3
    Points: 1,522, Level: 22
    Level completed: 22%, Points required for next Level: 78

    Posts
    16
    Thanks
    0
    Thanked 0 Times in 0 Posts

    Re: Logistic Regression

    the sample size is 600 cases,the number of variables or covariates are 26, the overall percentage is 50%, the value of HL test (Chi Square statistic) is zero.

  4. #4
    Points: 3,015, Level: 33
    Level completed: 77%, Points required for next Level: 35

    Posts
    47
    Thanks
    8
    Thanked 7 Times in 7 Posts

    Re: Logistic Regression

    Hi osamastat,

    Hosmer-Lemeshow is a measure of calibration. Whilst it is important, there are other measures, such as discrimination, which which are important to describe when looking a a model. It may be that the model still has some useful application even if its calibration is not great, but it has excellent discrimination.

    Can you tell us a bit more about what the model is for and how it has been developed? Are you trying to validate a model that has already been developed?

  5. #5
    Points: 1,522, Level: 22
    Level completed: 22%, Points required for next Level: 78

    Posts
    16
    Thanks
    0
    Thanked 0 Times in 0 Posts

    Re: Logistic Regression


    Hello
    my question is should i delete some variables or make some transformation or do any ad hoc method to make the model fit??

+ 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