The Wikipedia says "If the data are normally distributed with standard deviation $\sigma$ then the expected value of $\overline {MR}$ is $d_{{2}}\sigma =2\sigma /{\sqrt \pi }$."


Are the control limits based on moving range robust to violation of the normal distribution assumption?

  • $\begingroup$ I replaced ``` by \$ and removed the duplication of formulas inherent in the way Wikipedia does it. Note that in the same article it says "The value $2.66$ is obtained by dividing $3$ by the sample size-specific $d_2$ anti-biasing constant for $n=2$, as given in most textbooks on statistical process control (see, for example, Montgomery)", which adds a little information about where it comes from $\endgroup$
    – Glen_b
    Jun 6, 2022 at 23:18
  • $\begingroup$ thanks! Realize I should use $ instead of ``` for formulae now. This post helps explain the convergence of 2.66MR to 3sigma. stats.stackexchange.com/questions/288486/… $\endgroup$
    – hehe
    Jun 7, 2022 at 16:09


Your Answer

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

Browse other questions tagged or ask your own question.