One-sided tolerance guidelines

Six Sigma – iSixSigma Forums Old Forums General One-sided tolerance guidelines

Viewing 6 posts - 1 through 6 (of 6 total)
  • Author
  • #27496


    Guidelines for accepatance of % R&R are provided in the AIAG MSA Handbook — i.e., under 10% error the measurement system is acceptable, etc. These are from two-sided specification.
    Where can I find the guidelines for one-sided tolerances?



    Consider looking at Juran’s Quality Control Handbook, 4th edition.  You should find the one-sided tolerance limit table in Appendix II Table V. 
    An older reference that I find very useful from time to time is a printing from the National Technical Information Service called “Experimental Statistics Handbook 1991”.  It was written in 1963, but is unfortunately out of print.  If you have an office mate who has a copy of this handbook, then you will find one-sided tolerance tables on pages T-14 and T-15 for normally distributed data. 
    Other references include Hahn, Journal of Quality Technology 1 (1969), and Hahn, Journal of American Statistical Association 64 (1969).
    Hope this helps!



    Hi Ben
    lets look at the Gage R&R issue from this perspective…. what we are trying to do is basically reduce the effect of the Measurement System variation on the actual variation of the part / component. To that extent , irrespective of whether the tolerance is one sided or double sided it really doesnt matter as long as the Measurement System variation is below 10%
    Well that’s what I have been taught.. Would really appreciate if someone else could enlighten me more
    Cheers and have a great day


    Ken K.

    You hit the nail on the head. The “sidedness” of the tolerance has nothing to do with whether the measurement system has sufficient resolution to identify changes in the process.



    Good point guys. I misread Ben’s request thinking he was interested in tolerance interval requirement for product acceptance using variables measures. Ben, these guys are correct in their observation. Compare the measurement variation to the width of the specification whether one or two sided.



    Great discussion about MSA – just a couple of points. Aligning your measurement system variation to tolerance is a useful method of MSA, but doesn’t give you the whole picture. For me, you have to look at the following:
    % Contribution – Aligns the measurement system variation with the overall observed variation. the OK for this should be 4. V Important and often overlooked.
    % Tolerance – This, as discussed, aligns variation to your CTQ’s and is also very important.This is all explained in more detail in the Minitab Help files. I hope this helps.

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

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