iSixSigma

RR Study – attribute data

Six Sigma – iSixSigma Forums Old Forums General RR Study – attribute data

Viewing 9 posts - 1 through 9 (of 9 total)
  • Author
    Posts
  • #31098

    anon
    Participant

    I need some help with suggestions of good books (title, publisher, web site) or reference materials explaining how to use R&R Study with attribute data.If possible, I would like to receive some R&R Study using attribute data.

    0
    #81743

    Gabriel
    Participant

    Get a copy of the MSA third edition, from AIAG. It is pretty inexpensive and you can buy it from the AIAG’s web site.
    There you have a couple of methods for attribute gages explained with examples.

    0
    #81744

    Monlui
    Participant

    Did you see the article listed under https://www.isixsigma.com/st/msa/ about attribute grr? There is one post in it that I found very useful.

    0
    #81746

    Gabriel
    Participant

    I don’t know. Sorry. Have you checked the section that gives references for special cases?

    0
    #81748

    Hersey
    Participant

    On the Minitab Web Site (http://www.minitab.com), there are examples and discussions of attribute gage R&R for both Service and Manufacturing. Look under the Tutorials tab. Of course, the examples are geared toward interpreting the output from Minitab.
    I have used this function and it worked great.
    Don

    0
    #81758

    Wally
    Member

    Paulo,
    Try creating a reference column using the ‘know standard/ attribute’ option in minitab.  The reference column contains the ‘standard answers’ for defect category for each part.
    If you used ‘A, B, C.. etc’ in the reference column, the appraisers’ data must be entered similarly (I think it is case sensitive).
    Hope it helps.

    0
    #81762

    Michael Schlueter
    Participant

    I would convert the attribute data into continuous data first. You can use what Bothe calls a Likert scale to do that. I used this approach on a number of occasions.The idea is to order your samples by some sort of severity. E.g. attributes A and B are just minor defects, C, D and E are stronger, F and G are almost a disaster.Next assign arbitrary numbers to each category, which expresses your situation best. E.g. you can use an equidistant scale, like 1 for A, 2 for B, 3 for C etc. Or 1 for A, 2 for B, 4 for C, 6 for D etc.Then you can use your standard R&R procedures.The key will be that you will always use the same transformation, when you have new data later in your process. Preparing some transformation guideline will be helpful, e.g. by listing examples for your Likert scale transformation.However it is best to avoid attribute data whenever possible.They appear to be simple, but tend to hide information. Most of the time you can replace them by one or a set of continuous measurements.Hope this helps you along,Michael Schlueter

    0
    #81763

    Michael Schlueter
    Participant

    Oops,
    For sure you recognized my typo. In the second example you use a 2**N series, of course, to express an exponential scale.
    1 for A, 2 for B, 4 for C, 8 for D, 16 for E etc.
    Michael Schlueter

    0
    #81771

    Chip Hewette
    Participant

    With various defects in one item, is this not a pass-fail situation?  Should not the inspector find all defects?  If all are not found, is this not a ‘fail?’
    One can put 10 to 30 items in front of 3 inspectors and see how repeatable the inspectors are very easily.  There is but one ‘truth’ and with visual defects, a wide range of possible outcomes based on the inspector’s viewpoint.
    What is important is testing the pool of inspectors with realistic and complete examples of the various defects.

    0
Viewing 9 posts - 1 through 9 (of 9 total)

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