The IMR (individual-moving average) control chart is a classical proposal in both SQC books and ISO standards for control charting single observations. Simple rules are given for setting the limits. However, it is more or less known that the MR limits are misplaced. There were some early accurate numerical Average Run Length (ARL) results by Crowder in 1987! However, they are not flawless. We provide the whole numerical package including lower and two-sided limits designs (Crowder dealt with upper ones only). Finally, we present some conclusions about whether and how IMR (or only MR) control charts should be applied. We should mention that the data form an independent series of normally distributed random variables.
|Keywords||control charting, arl, numerics|