+ Reply to Thread
Results 1 to 6 of 6

Thread: post-hoc for nonparametric paired data in groups of unequal sizes

  1. #1
    Points: 58, Level: 1
    Level completed: 16%, Points required for next Level: 42

    Posts
    6
    Thanks
    2
    Thanked 0 Times in 0 Posts

    post-hoc for nonparametric paired data in groups of unequal sizes




    I am trying to do post-hoc analysis for nonparametric data. The group sizes are unequal but are paired.

    I've found several tests online, including Tukey-Kramer, Nemenyi, Dunn's, and Tukey-Kramer with rank sum test. But none of them seem to match my three criteria (nonparametric, unequal sample size, and paired-wise comparison).

    Am I wrong? And if I am correct, what's the best test to use?

  2. #2
    Points: 3,730, Level: 38
    Level completed: 54%, Points required for next Level: 70

    Posts
    155
    Thanks
    7
    Thanked 30 Times in 29 Posts

    Re: post-hoc for nonparametric paired data in groups of unequal sizes

    What initial test are you performing? Is the data continuous or categorical?

  3. #3
    Omega Contributor
    Points: 38,334, 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: post-hoc for nonparametric paired data in groups of unequal sizes

    Follow-up,


    You have skewed data that is paired (say pre-/post-data), that you want to compare by another categorical variable that has unequal group sizes.


    At least this is how I am interpreting your post, correct or not?
    Stop cowardice, ban guns!

  4. #4
    Points: 58, Level: 1
    Level completed: 16%, Points required for next Level: 42

    Posts
    6
    Thanks
    2
    Thanked 0 Times in 0 Posts

    Re: post-hoc for nonparametric paired data in groups of unequal sizes

    I have several sets of data. Some are ordinal, some are continuous. But they are all expressed as post/pre ratio and analyzed as such. The test I used was Skillings-Mack test.

  5. #5
    Points: 58, Level: 1
    Level completed: 16%, Points required for next Level: 42

    Posts
    6
    Thanks
    2
    Thanked 0 Times in 0 Posts

    Re: post-hoc for nonparametric paired data in groups of unequal sizes

    I do have post/pre data. I am comparing post/pre data of each subject at different time points. The issue is that each subject was measured only 2-3 times during the post period and I have more than 3 groups(eg. 10-20, 20-30, 30-40, 40-50, 50-60 days after treatment). While each subject only contributes to 3 groups, the time the measurements were taken was designed to cover all groups. So this is kinda like an unbalanced repeated measure design.

  6. #6
    Points: 58, Level: 1
    Level completed: 16%, Points required for next Level: 42

    Posts
    6
    Thanks
    2
    Thanked 0 Times in 0 Posts

    Re: post-hoc for nonparametric paired data in groups of unequal sizes


    Quote Originally Posted by Disvengeance View Post
    What initial test are you performing? Is the data continuous or categorical?
    I have several sets of data. Some are ordinal, some are continuous. But they are all expressed as post/pre ratio and analyzed as such. The test I used was Skillings-Mack test.

+ 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