+ Reply to Thread
Results 1 to 6 of 6

Thread: testing a prognostic score

  1. #1
    Points: 1,614, Level: 23
    Level completed: 14%, Points required for next Level: 86

    Posts
    3
    Thanks
    1
    Thanked 0 Times in 0 Posts

    testing a prognostic score




    Hi, can anyone please help me? I have to see to how a prognostic score correlates with patients' evolution, and by that I mean: mortality, days of hospitalization and hospitalization costs. That means correlation between a discrete variable and a categorical (mortality) and two continuous variables, right?
    I was thinking about ANOVA, but I'm not really sure.
    Help, please!

  2. #2
    TS Contributor
    Points: 17,749, Level: 84
    Level completed: 80%, Points required for next Level: 101
    Karabiner's Avatar
    Location
    FC Schalke 04, Germany
    Posts
    2,540
    Thanks
    56
    Thanked 639 Times in 601 Posts

    Re: testing a prognostic score

    How does ths score look like, on what scale is it measured? What is the study design,
    longitudinal, retrospective, or something else? How large is your sample?

    With kind regards

    K.

  3. #3
    Points: 1,614, Level: 23
    Level completed: 14%, Points required for next Level: 86

    Posts
    3
    Thanks
    1
    Thanked 0 Times in 0 Posts

    Re: testing a prognostic score

    The score is made up of 5 components (clinical and laboratory parameters) and divides the patients into 9 groups (scores of 0 to 8). It's a retrospective study and it includes 170 patients.
    Thank you!

  4. #4
    TS Contributor
    Points: 17,749, Level: 84
    Level completed: 80%, Points required for next Level: 101
    Karabiner's Avatar
    Location
    FC Schalke 04, Germany
    Posts
    2,540
    Thanks
    56
    Thanked 639 Times in 601 Posts

    Re: testing a prognostic score

    If you simply want to know whether score and the other parameters are
    significantly associated, then you could use Spearman correlation
    (for costs and lenght of stay) and a U-test (compare deceased with
    non-deceased with regards to score).

    With kind regards

    K.

  5. The Following User Says Thank You to Karabiner For This Useful Post:

    sprite (06-30-2013)

  6. #5
    Points: 1,614, Level: 23
    Level completed: 14%, Points required for next Level: 86

    Posts
    3
    Thanks
    1
    Thanked 0 Times in 0 Posts

    Re: testing a prognostic score

    I had figured it out about Spearman correlation, it was the mortality that I did not know how to correlate. I knew t-test wasn't exactly what I needed and I didn't know what u-test was all about. Looked it up, found it, got it. Thank you very much, that really helped me a lot!

  7. #6
    Omega Contributor
    Points: 38,281, Level: 100
    Level completed: 0%, Points required for next Level: 0
    hlsmith's Avatar
    Location
    Not Ames, IA
    Posts
    6,990
    Thanks
    397
    Thanked 1,185 Times in 1,146 Posts

    Re: testing a prognostic score


    Was this pre-existing score instrument or did you devise it.
    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