+ Reply to Thread
Results 1 to 2 of 2

Thread: What type of regression I need to use?

  1. #1
    Points: 4, Level: 1
    Level completed: 7%, Points required for next Level: 46

    Posts
    1
    Thanks
    0
    Thanked 0 Times in 0 Posts

    Question What type of regression I need to use?






    I am doing a medical research in which I am going to compare two methods of calculation of RBC life span. The older method is a difficult to do, but the results are certain. we want to validate new method based on older method. I want to find a statistical method to find any correlation between old and new method. I also would like to do regression to have a model analysis. what kind of regression would be approperiate?

  2. #2
    TS Contributor
    Points: 14,811, Level: 78
    Level completed: 91%, Points required for next Level: 39
    Miner's Avatar
    Location
    Greater Milwaukee area
    Posts
    1,171
    Thanks
    34
    Thanked 405 Times in 363 Posts

    Re: What type of regression I need to use?


    Do you have continuous data for both tests?

    Comparing test methods does not meet one assumption for simple linear regression, namely that there is no variation in the independent variable. The IV is a measurement and therefore has variability. You would need to use Deming Regression to analyze this type of data. However, the results are difficult to interpret in the context of what you need. Ideally, perfectly interchangeable tests would have an equation of Y=X. However, you will get an intercept and a slope not equal to 1. How much change in these coefficients is acceptable?

    A better approach is a Bland-Altman plot, or a Youden plot.

+ Reply to Thread

           




Tags for this 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