 |
Charts |
|
|
These procedures generate various control charts useful for monitoring the average and variability of a process.
Control charts plot an ongoing process over time. Each point summarizes a
subgroup of measurements taken within a particular time interval. StatPlus plots by default:
Center line at the average of the statistic by default
Upper control limit, 3 sigmas above the center line by default
Lower control limit, 3 sigmas below the center line by default
Variables chart for subgroups
Xbar Chart
Xbar Chart is a control chart of subgroup means. You can use X charts to track
the process level and detect the presence of special causes.
R Chart
R (Range) chart displays the ranges of the subgroups. Subgroup sizes must be in the range [2,24]. Note that the S Chart, which is often used as an alternative to the R chart, has no limit on the subgroup sizes.
S Chart
An S Chart displays the standard deviation of the subgroups. This is useful for determining how much variation is present in the process when the subgroup size is large. Unlike the R chart, the s chart has no subgroup size limitation.
Time-Weighted Control Charts
CUSUM Chart
CUSUM (Cumulative Sum) chart displays a running summation of process deviation from a reference or target value. It resolves the shotgun or scattered appearance of the regular control chart into a visual tracking of process changes.
The cumulative sum chart is more sensitive than the X-bar chart in detecting small shifts in the process average. Small shifts are in the range of 0.5 to 2.0-sigma. However, the X-bar chart is more effective in detecting larger short term changes in the process level.
The points plotted are the cumulative deviations of the subgroup averages from a known target value. When the process is operating near the target value, the points should form a horizontal line, allowing for random fluctuations. When the process mean shifts, the points begin to ascend or descend. To help determine when a shift has occurred, "V-mask" criteria is used.
Moving Average See Moving Average in
Time Series Analysis and Forecasting.
Attributes Control Charts
Attributes control charts are similar in structure to variables control charts, except that they plot statistics from count data rather than measurement data.
P Chart (Control chart for defectives)
The p chart is a control chart for the fraction or percent of nonconforming items found in either constant or varying sized subgroups.
C Chart (Control chart for defects)
C charts are based on the total number of defects per area of opportunity or unit. It is very important that the area of opportunity for a defect be constant from subgroup to subgroup since the chart shows the total number of nonconformities. When the number of items tested in a subgroup changes, then a U chart should be used since it shows the number of defects per unit rather than total defects.
U Chart (Control chart for defects)
U charts are designed for situations where the number of nonconformities per unit are measured and the number of units changes from subgroup to subgroup.
Bibliography
See [8] - [10] in Bibliography.
|
