I'm posting a reply to 'light the bulb' - maybe attract a reply. I'm not a statistical person. If you get real needy, e-mail Howard Atkins - he's the moderator of one of the forums. He's pretty statistical.
I am writing a procedure on claculating stability. When I read in the MSA book a calculation which I don't have with me right now, but I was confused as to how to claculate the control limits. We have started stability tests on a chart, and it is a regular Xbar chart. We need to calculate the control limits to get an accurate range of the readings. Does anyone know of SPC programs which will give you the actual stability of the master part?
Thanks for the help!
You have started stability tests using a “regular” Xbar chart. However, you did not mention a chart for dispersion (R, s, sigma, etc.)?? Assuming a dispersion charts exists, then the calculation of the limits is straightforward for a “regular” control chart. If a chart for dispersion does not exist, that is another matter.
Control limits do not give an accurate range of the readings. Rather, the purpose of control limits is to determine when a process is in or out of a state of statistical control. A process can be in control and still not be stable. Perhaps you are referring to process capability? It sounds, however, that what you are trying to do is not typical. Perhaps I am still missing something. Additional details may be required.
There are many SPC programs, but I prefer Statview with the QC module installed.
We have a customer who wants us to perform stability tests on every gage we use to machine their parts, including micrometers. We do not have an SPC program which calculates stability.I have discussed this with someone and was informed to use moving range charts and we should be ok with that. Haven't tried it yet. Thanks!!!
Be sure to discriminate the difference between “stability” and “statistical process control.” I would suggest that your customer does not know the difference, either. Rather than stability tests, would not repeatability and reliability (R&R) tests be more suitable? Maybe, Maybe not.