+ Reply to Thread
Results 1 to 3 of 3

Thread: Repeatability and Logistic Regression?

  1. #1
    Points: 566, Level: 11
    Level completed: 32%, Points required for next Level: 34

    Posts
    14
    Thanks
    1
    Thanked 0 Times in 0 Posts

    Repeatability and Logistic Regression?




    Hi all, my stats knowledge is quite basic so I would appreciate any help you can provide! I am working on a study looking at inter-grader and intra-grader repeatability. Two masked graders are measuring tissue thickness on a scan. I'm using intraclass correlation coefficients, coefficients of repeatability, and Bland-Altman plots to evaluate the repeatability.

    The tissue that we're looking at contains different kinds of fluid. I'd like to know whether and which type of fluid affects the repeatability. What should I use as the dependent variable (ICC or CR)? Since the dependent variable is continuous, what kind of regression is best suited for this?

    Thank you for your help!

  2. #2
    Omega Contributor
    Points: 38,303, Level: 100
    Level completed: 0%, Points required for next Level: 0
    hlsmith's Avatar
    Location
    Not Ames, IA
    Posts
    6,993
    Thanks
    397
    Thanked 1,185 Times in 1,146 Posts

    Re: Repeatability and Logistic Regression?

    Well your dependent is not binary, so you would likely not be interested in logistic regression. Can you remind use how ICC and CR are formatted? Are they a number between 0 and 1.00?
    Stop cowardice, ban guns!

  3. #3
    Points: 566, Level: 11
    Level completed: 32%, Points required for next Level: 34

    Posts
    14
    Thanks
    1
    Thanked 0 Times in 0 Posts

    Re: Repeatability and Logistic Regression?


    Yes, I agree that a logistic regression would probably not work. It was suggested to me by a mentor but he was not sure himself.

    ICC is between 0 and 1.00. CR is based on the actual measurement. For example, the range of values is about 100-400, and I am getting CRs of approximately 50-150. I am interpreting this to mean that any difference greater than the CR represents a true difference rather than grading variability. Thank you!

+ 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