+ Reply to Thread
Results 1 to 3 of 3

Thread: Test sensitivity for a given category or category sensitivity?

  1. #1
    Points: 559, Level: 11
    Level completed: 18%, Points required for next Level: 41

    Posts
    11
    Thanks
    3
    Thanked 0 Times in 0 Posts

    Test sensitivity for a given category or category sensitivity?




    Hello everybody,

    I want to study several parameters (i.e. sensitivity, specificity, precision and F1-score) of a given test. To do so, I'm comparing this test with a golden standard test. There are 4 nominal categories (A, B, C, D). The findings show that, for category A, the test being studied has a sensitivity value of 90% (in comparison with the gold standard test). However, for category B, the test being studied has a sensitivity value of 60% (in comparison with the gold standard test). Something similar happens with the rest of categories (C and D) and with the other parameters (specificity, recall and F1-score).

    How can I express the results more correctly? :

    -Option A: The test under study is very sensitive / has a high sensitivity to detect items from category A, but not B (...).

    -Option B: The category A has a high sensitivity, but a low specificity (...).

    In other words, is it correct to refer to the categories as more or less sensitive/specific or do I necessarily have to refer to the test itself as more or less sensitive/specific for each category?

    If there is any better option please let me know. I'm quite new to statistics...

    Thanks in advance.

  2. #2
    Omega Contributor
    Points: 38,253, Level: 100
    Level completed: 0%, Points required for next Level: 0
    hlsmith's Avatar
    Location
    Not Ames, IA
    Posts
    6,989
    Thanks
    397
    Thanked 1,185 Times in 1,146 Posts

    Re: Test sensitivity for a given category or category sensitivity?

    You can refer to each levels metric and perhaps report an overall Accuracy level. I believe the PIOPED study had multiple groups, it would be interesting to see how they presented their results. Prospective Investigation of Pulmonary Embolism Diagnostics circa 1990.
    Stop cowardice, ban guns!

  3. The Following User Says Thank You to hlsmith For This Useful Post:

    AJLRB (07-13-2017)

  4. #3
    Points: 559, Level: 11
    Level completed: 18%, Points required for next Level: 41

    Posts
    11
    Thanks
    3
    Thanked 0 Times in 0 Posts

    Re: Test sensitivity for a given category or category sensitivity?


    Thank you very much. I'm going to read the paper you mention to find out more.

+ 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