+ Reply to Thread
Results 1 to 3 of 3

Thread: P-values with confidence intervals - where do they come from?

  1. #1
    Points: 3,286, Level: 35
    Level completed: 58%, Points required for next Level: 64

    Posts
    17
    Thanks
    1
    Thanked 0 Times in 0 Posts

    P-values with confidence intervals - where do they come from?




    Below is quoted a part of my comments in reviewing a scientific paper. I'm not a statistician so I want to make sure I'm not missing something. Do you agree with my statements?

    START OF QUOTE
    6. Inappropriate use of p-values
    The paper repeatedly reports proportions obtained in the study using the following format: Out of 298 radiographs, 58 cases had abnormalities (19.5%; 95% C.I. 0.151 to 0.244; p<0.001).

    Whereas the CIís in my view are a bit unnecessary, their use is understandable. What I donít understand is the concurrent use of p-values. P-values deal with significance and hypothesis testing. Where are the hypotheses for all the reported p-valueís?
    END OF QUOTE

  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: P-values with confidence intervals - where do they come from?

    Yeah the p -values could be construed as redundant. There use could be defined in methods section, we are a little limited in not seeing the whole paper. I would image they could have been testing the percentage is not equal to "0" or some other relevant number. I can't say they are truly redundant without seeing the whole paper or the presentation of a p -value that has a specific value not 0.001, this is because they could have tested the value = to 0 or 90, etc. We don't know, with the n -value percentage, specific pvalue and software package used we could replicate and better know what they tested.
    Stop cowardice, ban guns!

  3. #3
    TS Contributor
    Points: 17,779, Level: 84
    Level completed: 86%, Points required for next Level: 71
    Karabiner's Avatar
    Location
    FC Schalke 04, Germany
    Posts
    2,542
    Thanks
    56
    Thanked 640 Times in 602 Posts

    Re: P-values with confidence intervals - where do they come from?


    Do you agree with my statements?
    I am inclined to do so, but I haven't read the paper.
    Maybe they tested something like "equal proportion of
    normal/abnormal proportion", but it is of course up to
    the authors to clearly state their hypothesis.

    With kind regards

    K.

+ 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