iSixSigma

Gage R&R with One Part, One Operator, 10 Tries

Six Sigma – iSixSigma Forums General Forums Tools & Templates Gage R&R with One Part, One Operator, 10 Tries

This topic contains 6 replies, has 3 voices, and was last updated by  Anaslmx 4 months, 2 weeks ago.

Viewing 7 posts - 1 through 7 (of 7 total)
  • Author
    Posts
  • #240180

    Anaslmx
    Participant

    Hello everyone,

    I would like to know if it is feasible to run a GR&R study through the method of Average and Range with this type of parameters :
    1 operator 1 part 10 tries on the same instrument

    The problem that I got is that both R chart and Xbar chart or can’t be used anymore because the overall average is equal to the average of the 10 tries => the average of the tries are sure to be inside the control limit in every case, which isn’t something that we want to.
    Another problem is that because I can’t calculate the range Rp of the part, I can’t determine the total variation. In this case, I can’t find the percentage of contribution from the GRR …

    One will say that the required parameters should be above 2 (to find the good factor d2 and d2*). Except, I don’t really have the choice to choose this kind of parameters, because one value is gotten after a long time.

    Does someone can tell me if it is impossible to run a good GR&R study ? Or does someone ever have run a test like this one ?

    Kind regards,
    Anas.

    0
    #240183

    Chris Seider
    Participant

    Why would you do such a thing?

    You’re forgetting you aren’t able to discern impact of operator or region of “spec range” impacting measurements with your proposal.

    0
    #240184

    Robert Butler
    Participant

    In addition to what @cseider said you also do not have independent measurements – you have repeated measures on a single item which means your estimates of variation are going to be much less than the real variation you can expect in your process.

    0
    #240185

    Anaslmx
    Participant

    Thank you for your replies !

    @cseider I’m trying to do this because when I do a test on a component, sometimes it can last 5 min, some other times 2 hours. So if I do a full Gage R&R study, with 3 operators, 10 parts and 3 tries, it will take too much time.
    Yeah I’m aware for the impact on the variation, but I wanted to be sure if this impact isn’t significant.

    @rbutler yeah the less you have repeated measures the less precision you have on the value of the standard deviation of the GRR, but is there a certain number of try from which the difference between a GRR found with 10 tries and a GRR found with less tries is insignificant ?

    0
    #240186

    Chris Seider
    Participant

    You will need to invest the time/money if truly want to understand your gage’s variation relative to the process and specification range.

    However, you can get away with just doing 2 independent measurements by each of your 3 operators if you do the 10 parts–it’s a long discussion why this CAN be done in cases for expensive and time consuming gage studies but it is at the cost of precision of gage variation knowledge so I’m not saying do it all the time.

    1
    #240187

    Robert Butler
    Participant

    No, it’s not a case of the less you have of repeated measures the less precision you have on the value of the standard deviation of the GRR rather it is a matter of the less you have of repeated measures the better the precision of your estimate of the true value of the standard deviation of the GRR. As I said – repeated measures variation will underestimate the actual standard deviation and that, in turn, will adversely impact your conclusions concerning GRR.

    1
    #240188

    Anaslmx
    Participant

    Okay I see ! @cseider @rbutler Thank you for your replies !
    I thought that could be interesting to discuss about this subject, so thank you for giving me your point of view.

    0
Viewing 7 posts - 1 through 7 (of 7 total)

You must be logged in to reply to this topic.