iSixSigma

Kendall coefficient of concordance

Six Sigma – iSixSigma Forums Old Forums General Kendall coefficient of concordance

Viewing 4 posts - 1 through 4 (of 4 total)
  • Author
    Posts
  • #48287

    Tierradentro
    Participant

    Hi,
    Could anybody share with me the deduction of Smax formula in the Kendall coefficient of concordance (W=s/Smax). What is the start figure and what kind of steps required to get the Smax=1/12K2(n3-n).
    Thanks for your help.
    Regards,
    John

    0
    #162202

    Darth
    Participant

    Would help if I included the link…big DUH!!!http://www.minitab.com/support/docs/Answers/KendallDesignDoc.pdf

    0
    #162200

    Darth
    Participant

    See if this helps.

    0
    #162288

    Tierradentro
    Participant

    Thanks, Darth
    I had a quick check regarding your info and I will think about how can I deduce the final formula of Smax. I know that it presumes that the judges’s decision is the same to every parameter. In this case this deviation will be the highest and finally if we divide the “s” (actual deviation) whit this Smax the result will be the “W” coefficient what can be between 0 and 1. If it is 1 there is agreement between the judges and if it is 0 there is disagreement.
    s2 = Sum(R-Raverage)2 so Smax2 has to be the same.
     
    Raverage = K(n+1)/2
    R = K*n1 or K*n2 … K*nn where “n” is the numbers by judges to the parameter.
    So from this 2 formula how can I get the Smax = 1/12K2(n3-n).
    Regards,
    John

    0
Viewing 4 posts - 1 through 4 (of 4 total)

The forum ‘General’ is closed to new topics and replies.