<?xml version="1.0" encoding="utf-8" standalone="yes"?>
<item>
  <id>05227189</id>
  <dt>j</dt>
  <an>05227189</an>
  <augroup>
    <au>Fournier, B.</au>
    <au>Rupin, N.</au>
    <au>Bigerelle, M.</au>
    <au>Najjar, D.</au>
    <au>Iost, A.</au>
  </augroup>
  <ti>Comments on the mixture detection rule used in SPC control charts.</ti>
  <so>Commun. Stat., Simulation Comput. 36, No. 6, 1321-1331 (2007).</so>
  <py>2007</py>
  <pu>Taylor \& Francis, Philadelphia, PA</pu>
  <lagroup>
    <la>EN</la>
  </lagroup>
  <ccgroup>
  </ccgroup>
  <utgroup>
    <ut>average run length</ut>
    <ut>mixture</ut>
    <ut>statistical process control</ut>
    <ut>test for special causes</ut>
    <ut>type-I error</ut>
    <ut>Western electric rules</ut>
  </utgroup>
  <cigroup>
  </cigroup>
  <ligroup>
    <li>doi:10.1080/03610910701569630</li>
  </ligroup>
  <abgroup>
    <ab>Summary: When calculating independently the false alarm rate of the eight usual runs rules used in statistical process control (SPC) charts, it appears that the proposed rule designed to detect mixture patterns corresponds to a Type-I error strongly lower than the seven other rules. This discrepancy is underlined and the mixture rule is shown to be useless both for in-control and out-of-control processes. Thus a modification of the mixture detection rule is proposed and the impact of this new mixture rule is then illustrated and discussed using Monte Carlo calculations.</ab>
    <rv></rv>
  </abgroup>
</item>