I am learning a Quality Control course and in theory part I don't understand calculating the control limits for $\bar{x}$ and R chart.I want to know, say when I calculate the R chart control limits no points plot outside the control limit.And therefore using this $\bar{R} $ values I can then go to calculate $\bar{x} $ chart control limits.In that say 2 sample values are plotted outside the control limits and in each of these suppose an assignable cause was found.Therefore we have to remove this point and recalculate control limits for $\bar{x}$ chart.My question is do I have to recalculate the R chart control limits also.Because now in $\bar{x}$ chart 2 samples are removed.Or do I use the earlier $\bar{R} $value and use removing the two samples only recalculate $\bar{x}$?

Also say there's a pattern is present like a cycle or a shift in process level.Even if all the points lie inside the control limit with the presence of a pattern does it indicate that the process is out of control?Or is the process in control, but some factor affects to shift the process level?


1 Answer 1


Yes you have to recalculate the R chart control limits as well. Even though there is no point outside the control limits in R chart, removal of two points due to x-bar chart changes the control limits of R chart. For the second part, if there is a pattern or a cycle you can say that the system is not in statistical control. Therefore you have to look for an assignable cause

  • $\begingroup$ If the class did not cover it, there are sets of rules for determining if a chart is in statistical control. The most popular set are the Western Electric Rules. Also, I would suggest that if you are willing to accept @Bob's answer that you accept the answer in the system. $\endgroup$
    – Tavrock
    Dec 7, 2016 at 23:25

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge you have read our privacy policy.

Not the answer you're looking for? Browse other questions tagged or ask your own question.