|
|
| Line 1: |
Line 1: |
| In [[Statistical Process Control]], the '''Western Electric Rules''' are [[decision rules]] for detecting "out-of-control" or non-[[random]] conditions on [[control chart]]s.<ref>{{Citation
| | I like Knapping. Appears boring? Not at all!<br>I also try to learn German in my spare time.<br><br>Take a look at my weblog [http://Www.Henanyilong.com/plus/guestbook.php How To Get Free Fifa 15 Coins] |
| | last = Montgomery
| |
| | first = Douglas C.
| |
| | publication-date = 2005
| |
| | title = Introduction to [[Statistical Quality Control]]
| |
| | edition = 5
| |
| | publication-place = [[Hoboken, New Jersey]]
| |
| | publisher = [[John Wiley & Sons]]
| |
| | isbn = 978-0-471-65631-9
| |
| | oclc = 56729567
| |
| | year = 2005
| |
| }}</ref> Locations of the observations relative to the control chart control limits (typically at ±3 [[standard deviation]]s) and centerline indicate whether the process in question should be investigated for [[assignable cause]]s. The Western Electric Rules were codified by a specially-appointed committee of the manufacturing division of the [[Western Electric Company]] and appeared in the first edition of its [[Statistical Quality Control]] Handbook in 1956.<ref>{{Citation
| |
| | last = [[Western Electric Company]] | |
| | publication-date = 1956
| |
| | title = [[Statistical Quality Control]] handbook.
| |
| | edition = 1
| |
| | publication-place = [[Indianapolis, Indiana]]
| |
| | publisher = Western Electric Co.
| |
| | oclc = 33858387
| |
| | page = v
| |
| }}</ref> Their purpose was to ensure that line workers and engineers interpret control charts in a uniform way.<ref>{{Citation
| |
| | last = [[Western Electric Company]]
| |
| | publication-date = 1956
| |
| | title = [[Statistical Quality Control]] handbook.
| |
| | edition = 1
| |
| | publication-place = [[Indianapolis, Indiana]]
| |
| | publisher = Western Electric Co.
| |
| | oclc = 33858387
| |
| | page = 25
| |
| }}</ref>
| |
| | |
| ==Motivation==
| |
| | |
| The rules attempt to distinguish [[unnatural pattern]]s from [[natural pattern]]s based on several criteria:<ref>{{Citation
| |
| | last = [[Western Electric Company]]
| |
| | publication-date = 1956
| |
| | title = [[Statistical Quality Control]] handbook.
| |
| | edition = 1
| |
| | publication-place = [[Indianapolis, Indiana]]
| |
| | publisher = Western Electric Co.
| |
| | oclc = 33858387
| |
| | page = 24
| |
| }}</ref>
| |
| #The absence of points near the centerline (identified as a '''mixture''' pattern)
| |
| #The absence of points near the control limits (identified as a '''stratification''' pattern)
| |
| #The presence of points outside the control limits (identified as an '''instability''' pattern)
| |
| #Other unnatural patterns ('''systematic''' (autocorrelative), '''repetition''', '''trend''' patterns)
| |
| | |
| To achieve this, the rules divide the chart into zones, measured in units of [[standard deviation]] (σ) between the centerline and control limits, as follows:
| |
| {| class="wikitable" align=center
| |
| ! Zone !! Region
| |
| |-
| |
| | Zone A || Within 2σ of the centerline and the control limit (3σ)
| |
| |-
| |
| | Zone B || Within 1σ and 2σ of the centerline
| |
| |-
| |
| | Zone C || Within 1σ of the centerline
| |
| |}
| |
| | |
| Zones A, B, and C are sometimes called the '''three sigma zone''', '''two sigma zone''', and '''one sigma zone''', respectively.
| |
| | |
| ==Zone rules==
| |
| | |
| The most important of the Western Electric rules are the zone rules, designed to detect process '''instability'''—and the presence of assignable causes.<ref>{{Citation
| |
| | last = [[Western Electric Company]]
| |
| | publication-date = 1956
| |
| | title = [[Statistical Quality Control]] handbook.
| |
| | edition = 1
| |
| | publication-place = [[Indianapolis, Indiana]]
| |
| | publisher = Western Electric Co.
| |
| | oclc = 33858387
| |
| | page = 25–28
| |
| }}</ref>
| |
| There are four basic rules that deal with appraising runs of observations within the various zones:
| |
| | |
| {| class="wikitable" align=center
| |
| ! Rule !! Description !! Chart Example
| |
| |-
| |
| |width="75pt"| <center>Rule 1</center> ||width="300pt"| Any single data point falls outside the 3σ limit from the centerline (i.e., any point that falls outside Zone A, beyond either the upper or lower control limit) ||[[File:Rule 1 - Western electric control chart.svg]]
| |
| |-
| |
| | <center>Rule 2</center>|| Two out of three consecutive points fall beyond the 2σ limit (in zone A or beyond), on the same side of the centerline ||[[File:Rule 2 - Western electric control chart.svg]]
| |
| |-
| |
| | <center>Rule 3</center> || Four out of five consecutive points fall beyond the 1σ limit (in zone B or beyond), on the same side of the centerline ||[[File:Rule 3 - Western electric control chart.svg]]
| |
| |-
| |
| | <center>Rule 4</center> || Eight consecutive points fall on the same side of the centerline (in zone C or beyond) ||[[File:Rule 4 - Western electric control chart.svg]]
| |
| |}
| |
| | |
| These rules are evaluated for one side of the center line (one half of the control band) at a time (e.g., first the centerline to the upper control limit, then the centerline to the lower control limit).
| |
| | |
| Data satisfying any of these conditions as indicated by the control chart provide the justification for investigating the process to discover whether assignable causes are present and can be removed. Note that there is always a possibility of [[false positive]]s: Assuming observations are normally distributed, one expects Rule 1 to be triggered by chance one out of every 370 observations on average. The false alarm rate rises to one out of every 91.75 observations when evaluating all four rules.<ref>{{Citation
| |
| | last = Champ
| |
| | first = Charles W.
| |
| | year = 1987
| |
| | title = Exact Results for Shewhart Control Charts with Supplementary Runs Rules
| |
| | periodical = [[Technometrics]]
| |
| | volume = 29
| |
| | pages = 393–399
| |
| | doi = 10.2307/1269449
| |
| | author2 = Woodall, William H
| |
| | issue = 4
| |
| | publisher = American Society for Quality
| |
| | jstor = 1269449
| |
| }}</ref>
| |
| | |
| ===Asymmetric control limits===
| |
| The zone rules presented above apply to [[control chart]]s with symmetric control limits. The handbook provides additional guidelines for control charts where the control limits are not symmetrical, as for R charts and p-charts.
| |
| | |
| For [[Xbar and R chart|<math>\bar x</math> and R charts]] (which plot the behavior of the subgroup range), the Handbook recommends using the zone rules above for subgroups of sufficient size (five or more). For small sample subgroups, the Handbook recommends:
| |
| | |
| {| class="wikitable" align=center
| |
| ! Small-sample R chart rules
| |
| |-
| |
| | Any single data point falling above the +3σ limit
| |
| |-
| |
| | Two consecutive points falling above the +2σ limit (in the upper zone A or above)
| |
| |-
| |
| | Three consecutive points falling above the +1σ limit (in the upper zone B or above)
| |
| |-
| |
| | Seven consecutive points falling above the centerline (in the upper zone C or above)
| |
| |-
| |
| | Ten consecutive points falling below the centerline (in the lower zone C or below)
| |
| |-
| |
| | Six consecutive points falling below the -1σ limit (in the lower zone B or below)
| |
| |-
| |
| | Four consecutive points falling below the -2σ limit (in the lower zone A)
| |
| |}
| |
| | |
| For other control charts based on [[skewed]] distributions, the Handbook recommends:
| |
| #Finding the probabilities associated with each zone
| |
| #Devising tests that should result in the desired sensitivity to the presence of assignable causes
| |
| | |
| ==Other unnatural patterns==
| |
| | |
| The Handbook also identifies patterns that require consideration of both the upper and lower halves of the control chart together for identification:
| |
| | |
| {| class="wikitable" align=center
| |
| ! Pattern !! Description !! Rule
| |
| |-
| |
| | Stratification || Variation small relative to control limits || Fifteen consecutive points fall within ±1σ (zone C)
| |
| |-
| |
| | Mixture || The tendency to avoid the centerline || Eight consecutive points on both sides of the centerline with no points falling in zone C.
| |
| |-
| |
| | Systematic || Negative [[autocorrelation]]—a long series of observations that alternate high-low-high-low || (No rule given)
| |
| |-
| |
| | Repetition || The tendency of one chart to follow the same pattern as its predecessor || (No rule given)
| |
| |-
| |
| | Trend || Sustained drift or shift in the long-term mean || A series of out-of-control points in the lower zones followed by a series of out-of-control points in the upper zones or vice versa<BR>A series of points without a change in direction
| |
| |}
| |
| | |
| ==See also==
| |
| *[[Nelson rules]]
| |
| | |
| ==References==
| |
| {{reflist}}
| |
| | |
| {{DEFAULTSORT:Western Electric Rules}}
| |
| [[Category:Quality control tools]]
| |
| [[Category:Technical communication]]
| |
| [[Category:Statistical charts and diagrams]]
| |