1. This site uses cookies. By continuing to use this site, you are agreeing to our use of cookies. Learn More.
Dismiss Notice
You must be a registered member in order to post messages and view/download attached files in this forum.
Click here to register.

MSA: GRR Multiplication Factor of 5.15 Vs 6

Discussion in 'Gage R&R and MSA - Measurement Systems Analysis' started by shankar Jadhav, Sep 5, 2015.

  1. shankar Jadhav

    shankar Jadhav Member

    Sep 5, 2015
    Likes Received:
    Trophy Points:
    Historically, by convention, a 99% spread has been used to represent the “full” spread of
    measurement error, represented by a 5.15 multiplying factor (where GRR  is multiplied by 5.15
    to represent a total spread of 99%).
    A 99.73% spread is represented by a multiplier of 6.0, which is 3 and represents the full
    spread of a “normal” curve.
    If the reader chooses to increase the coverage level, or spread, of the total measurement
    variation to 99.73%, use 6.0 as a multiplier in place of 5.15 in the calculations.

    Can anyone explain me?
  2. Bev D

    Bev D Moderator Staff Member

    Jul 30, 2015
    Likes Received:
    Trophy Points:
    what part do you need to have explained?
    Why there is a choice or why the convention changed from 5.15 multiplier to 6? If it's this, there is no real reason for the change - I suppose that some people thought that with "Six Sigma" we should use 6...there is no magical reason. It's really personal choice.
    Atul Khandekar likes this.
  3. Atul Khandekar

    Atul Khandekar Administrator Staff Member

    Jul 24, 2015
    Likes Received:
    Trophy Points:
    Pune, India
    Having calculated the GRR Standard Deviation, the question is what is the total magnitude (= width = full spread) of this error. The earlier 'convention' was to multiply this StDev by 5.15 (+/- 2.575 std deviation) that covered 99% of the normal distribution. This was later changed to +/- 3 std deviation (multiply by 6, or 99.73% coverage).

    As Bev said, there doesn't seem to be any specific reason for the change. In any case, if your GRR std deviation is very small, multiplying by 5.15 or 6 won't make much difference. The multiplier of 5.15 would yield a slighly understated estimate.

    To calculate the ratio of GRR to StudyVar or Process variation, you can now divide the two standard deviations directly instead of having to calculate their 'spreads' seperately.