iSixSigma

Capability analysis

Six Sigma – iSixSigma › Forums › Old Forums › General › Capability analysis

Viewing 7 posts - 1 through 7 (of 7 total)
  • Author
    Posts
  • September 25, 2008 at 9:02 am #51005

    Whitehurst
    ★ 10 Years ★
    Participant

    Hello,
    Does anyone have instructions on how to perform a capability analysis for both normal and non-normal data?
    cheers

    0
    September 25, 2008 at 10:43 am #176122

    statfinder
    ★ 10 Years ★
    Member

    Hi
    Capability for Normal data can be calculated by
    CpK = Min ((USL-average)/3 stdev or (Average – LSL)/3 stdev)
    or Z = (Target – Average)/3 stdev
    If it is Non-Normal either try to transform your data using Johnson or Box-cox transformation.
     
     

    0
    September 25, 2008 at 10:59 am #176124

    Whitehurst
    ★ 10 Years ★
    Participant

    Hello,
    Thanks for this, however I would also like to know the overall approach for doing a capability trial in terms of assessing whether a new piece of equipment was suitable to use for the manufacture of product.  Does anyone have instructions on how to go about this?
     

    0
    September 25, 2008 at 11:42 am #176126

    Mikel
    ★ 10 Years ★
    Member

    Forget the transform crap – it’s bad advice.

    0
    September 29, 2008 at 5:58 am #176216

    statfinder
    ★ 10 Years ★
    Member

    The capability analysis for new equipment can be calculated using Machine capability analysis. Take continuous 50 samples without interruption and calculate CpM with stdev calculation alone changes in Cpk formula
    Sigma = Sqrt((individual value – set value)^2/ n-1)
     

    0
    September 29, 2008 at 9:55 am #176223

    Whitehurst
    ★ 10 Years ★
    Participant

    Thanks for your help.

    0
    September 29, 2008 at 1:48 pm #176231

    newbie
    ★ 10 Years ★
    Participant

    Hi Stan,
    I know that transformation for the purpose of studying capability isnt necessary, but is it harmful to an analysis? 
    And I can’t help feeling as if capability indices themselves are somewhat bogus.  When I read about all the assumptions and variability that go into the various models, would not using a standardized procedure on actual process performance to capture yield / confidence intervals be easier to apply, explain, and manage to? 
    Am I off base here?
    Thank you.

    0
  • Author
    Posts
Viewing 7 posts - 1 through 7 (of 7 total)

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