+ Reply to Thread
Results 1 to 5 of 5

Thread: Equivalence test or non inferiority test for non parametric data using stata or spss

  1. #1
    Points: 222, Level: 4
    Level completed: 44%, Points required for next Level: 28

    Posts
    3
    Thanks
    0
    Thanked 0 Times in 0 Posts

    Equivalence test or non inferiority test for non parametric data using stata or spss




    I am doing a retrospective study about a new medical device, comparing it with an older device. the first group has 18 cases and the other group has 83 cases. I performed Mann-Whitney test for the data as they are non-parametric and there was no statistical difference between the two groups. and now I want to perform non-inferiority test or equivalence test to prove that the newer device is almost the same or not inferior to the older device but I don't know how??? could anyone help me in that matter???

  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: Equivalence test or non inferiority test for non parametric data using stata or s

    What is your reasoning for nonparametric? Do you have a measure of how different they can be and still similar?
    Stop cowardice, ban guns!

  3. #3
    Points: 222, Level: 4
    Level completed: 44%, Points required for next Level: 28

    Posts
    3
    Thanks
    0
    Thanked 0 Times in 0 Posts

    Re: Equivalence test or non inferiority test for non parametric data using stata or s

    I performed KS test and shapiro-Wilk test for the data

  4. #4
    Points: 1,741, Level: 24
    Level completed: 41%, Points required for next Level: 59

    Posts
    230
    Thanks
    37
    Thanked 68 Times in 59 Posts

    Re: Equivalence test or non inferiority test for non parametric data using stata or s

    Quote Originally Posted by drAmrBadawy View Post
    I performed KS test and shapiro-Wilk test for the data
    These tests are not typically strong reasons to dictate using parametric or non-parametric methods. The formal tests can reject Ho for an immaterial departure from normality (even if the sample was drawn from an underlying distribution that's normal), or similarly, they can fail to reject Ho from insufficient data (even if the data were drawn from a very nonnormal population). I would also clarify a point of terminology: data are not "parametric" vs "nonparametric", these refer to kinds of analysis.

    Would you mind clarifying some more information about your research?
    What is the variable being analyzed?
    How is it measured?
    Is it bounded?
    If it is bounded, what are the bounds?

  5. #5
    Points: 222, Level: 4
    Level completed: 44%, Points required for next Level: 28

    Posts
    3
    Thanks
    0
    Thanked 0 Times in 0 Posts

    Re: Equivalence test or non inferiority test for non parametric data using stata or s


    my research is a retrospective study with 101 patients underwent liver resection, I divided them into two groups (n1=83, n2=18) using two devices. I compared the operative time and blood loss between the two groups using Mann-whitney test, and the P-value was more than 0.05. So I want to prove that the newer device is not inferior to the older device.

+ 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