iSixSigma

Non Normal Data

Six Sigma – iSixSigma Forums Old Forums General Non Normal Data

Viewing 6 posts - 1 through 6 (of 6 total)
  • Author
    Posts
  • #36874

    Gina
    Participant

    Just looking for some direction.  I have production data for 7 months on several product lines.  When I look at it by product, it is not normal.  When I look at it by month,  some of the monthly data is normal while some is not.
    Recommendations please.
     

    0
    #107384

    Savage
    Participant

    Gina,
    Can you tell us in more detail what you’re trying to accomplish?

    0
    #107432

    Gina
    Participant

    Matt,
    To determine if my process is in control and then do process capability.
     

    0
    #107445

    TCJ
    Member

    First, identify all the logical subgroups.  Run a control chart, evaluate outliers and identify special cause.  Remove special cause were it is appropriate.  Re-run with revised data.  Other options to explore: 1) Can you approximate normal based on the Central Limit Theorem.  2) Transform data and run capability

    0
    #107666

    Gina
    Participant

    TCJ,
    I did identify one logical subgroup but it looks like I may need to look at others.  I’ll give it a try.
    Thanks,
    Gina

    0
    #107672

    Ward
    Participant

    Are any items out of spec?  If so, determine the percentage that fall out of spec and convert to a capability index.  For instance if 10% fall out of spec, that would be a Z value of about 2.33, which when divided by 3 should be Cpk of about .78.
    I do support the ideal of the logical subgrouping for the control charts, which should always be done prior to the process capability study anyway.
     

    0
Viewing 6 posts - 1 through 6 (of 6 total)

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