+ Reply to Thread
Results 1 to 6 of 6

Thread: B Coefficient

  1. #1
    Points: 983, Level: 16
    Level completed: 83%, Points required for next Level: 17

    Posts
    29
    Thanks
    0
    Thanked 0 Times in 0 Posts

    B Coefficient




    I'm having some difficulty making sense of a logistic regression.

    I think I have the interpretation right based on a university tutorial on how to interpret data.

    The outcome being observed is visual acuity change after surgery (day 1).

    Is it correct to say that with each increase in age (10 years) there is a decrease in 0.05 units?

    The categorical variables confuse me a bit more.

    Do residents of the South experience fewer gains, specifically 0.02 unit less compared to those living in the North?

    Should the intercept be reported? Or can it be ignored in some circumstances?
    Attached Images  
    Last edited by jle; 02-12-2015 at 12:46 AM.

  2. #2
    Omega Contributor
    Points: 38,374, Level: 100
    Level completed: 0%, Points required for next Level: 0
    hlsmith's Avatar
    Location
    Not Ames, IA
    Posts
    6,998
    Thanks
    398
    Thanked 1,186 Times in 1,147 Posts

    Re: B Coefficient

    Are you sure you are looking at logistic regression?
    Stop cowardice, ban guns!

  3. #3
    Points: 983, Level: 16
    Level completed: 83%, Points required for next Level: 17

    Posts
    29
    Thanks
    0
    Thanked 0 Times in 0 Posts

    Re: B Coefficient

    Sorry I meant linear regression

  4. #4
    Omega Contributor
    Points: 38,374, Level: 100
    Level completed: 0%, Points required for next Level: 0
    hlsmith's Avatar
    Location
    Not Ames, IA
    Posts
    6,998
    Thanks
    398
    Thanked 1,186 Times in 1,147 Posts

    Re: B Coefficient

    Your interpretations seem correct for the most part. You would want to include the intercept unless you standardized the beta coefficients. South experiences on average a 0.02 decrease in visual acuity compared to the North.
    Stop cowardice, ban guns!

  5. #5
    Points: 983, Level: 16
    Level completed: 83%, Points required for next Level: 17

    Posts
    29
    Thanks
    0
    Thanked 0 Times in 0 Posts

    Re: B Coefficient

    Thanks hlsmith, could you explain to me how the intercept is taken into the interpretation?

    Is is something that can be excluded from academic writing or should it always be included for completeness?

  6. #6
    Omega Contributor
    Points: 38,374, Level: 100
    Level completed: 0%, Points required for next Level: 0
    hlsmith's Avatar
    Location
    Not Ames, IA
    Posts
    6,998
    Thanks
    398
    Thanked 1,186 Times in 1,147 Posts

    Re: B Coefficient


    You are actually constructing a linear combination. So you are plotting a combination of the covariates in relationship to the dependent variable, so picture a line on a 2 axes graph. Now the intercept tells you where the line crosses (intercepts) the y-axis. Now if you wanted to interpret your model in a picture you would take the intercept plus all of the beta coefficients(multiplied by the value of interest) to get the slope of the line that predicts y.

    This probably does a better job of describing whether you should include it depending on the purpose of the analysis.

    http://blog.minitab.com/blog/adventu...nt-y-intercept
    Stop cowardice, ban guns!

+ 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