Control Charts

The control chart is a graph that represents the variability of a process variable over time. Control charts are
used to determine whether a process is in a state of statistical control, to find the causes of changes in a
process, and monitor process performance. Control charts are also known as Shewhart control charts, after
W.A. Shewhart (1931) who first introduced the concept.

A control chart consists of:

 A center line, drawn as a green line at the mean value for the in-control process (stable zone).
 Upper and lower control limits (UCL and LCL) – red lines. These control limits are chosen so that
almost all of the data points will fall within these limits as long as the process remains in-control.
Control limits are set at a distance of three sigma 3𝜎 (standard deviation) above and below the
mean centerline. Default distance (3𝜎) can be overwritten using the “CONTROL LIMITS AT THESE
MULTIPLES OF STANDARD DEVIATIONS ” option.
 Data points representing a statistic for a subgroup (mean, range, proportion) or an attribute. A point
outside the control limits indicates the presence of a special cause that deserves investigation.

There are two basic types of control charts – control charts for attributes and control charts for variables.
Following types of control charts are available:

Individuals and moving range charts

Control charts for subgroup averages
 X-bar 𝑥 chart
 R chart
 s chart
Time weighted control charts
 CUSUM chart
Control charts for attributes
 P chart
 C chart
 U chart
X-bar chart
X-bar 𝒙 chart is used to monitor the mean value of a process over time (between-sample variability). For
each subgroup, the mean value is plotted.

 Run: CHARTS->[CONTROL CHARTS] X-BAR AND R CHART OR X-BAR AND S CHART command.

 Input variables: please see the DATA LAYOUT FOR XBAR -R AND XBAR-S CHARTS section below for more
details.

R chart
R chart is used to monitor the instantaneous process variability at a given time (within-sample variability).
Standard deviation, approximated by the sample range is used as a measure of variability – for each
subgroup, the range 𝑅𝑖 = max[𝑥𝑖 ] − min[𝑥𝑖 ] is plotted. R charts are usually used when we have a
constant and relatively small sample size (N=2…15). R chart can be produced for subgroups with a sample
size up to 50.

 Run: CHARTS->[CONTROL CHARTS] X-BAR AND R CHART command.

 Input variables: please see the Data layout for Xbar-R and Xbar-S charts section below for more
details.

Methods
1 𝐾
The default (Rbar) estimate for sigma is 𝜎 = ∑ 𝑅 /𝑑2 (𝑛𝑖 ), where K is the number of subgroups,
𝑁 𝑖=1 𝑖
𝑑2 is the unbiasing factor. Minimum variance linear unbiased estimate can be selected from the
Advanced Options [v6.5+].

S chart
S chart is similar to R chart, but the standard deviation is directly estimated. S charts are preferable
when a sample size is a variable or moderately large (N>10).

 Run: CHARTS->[CONTROL CHARTS] X-BAR AND S CHART command.

 Input variables: please see the Data layout for Xbar-R and Xbar-S charts section below for more
details.

Methods
1
The default (Sbar) estimate for sigma is 𝜎 = 𝑁 ∑𝐾
𝑖=1 𝑆𝑖 /𝑐4 (𝑛𝑖 ), where K is the number of subgroups,
𝑐4 is the unbiasing factor.
 Data layout for Xbar-R and Xbar-S charts
Use the DATA LAYOUT option to select how your data is organized.

1. SUBGROUPS ARE DEFINED BY VALUES OF THE 2. SINGLE COLUMN WITH MEASUREMENTS, FIXED
GROUP VARIABLE SUBGROUP SIZE

Select the LENGTH variable as MEASUREMENTS and Select the LENGTH variable as MEASUREMENTS and
the SUBGROUP variable as (DATA L AYOUT #1) enter 4 to the (DATA LAYOUT #2) SUBGROUP SIZE
GROUP. This layout allows using subgroups with field.
unequal sizes.
3. SUBGROUPS ACROSS THE COLUMNS, EACH COLUMN 4. SUBGROUPS ACROSS THE ROWS, EACH ROW
REPRESENTS A SUBGROUP REPRESENTS A SUBGROUP

Select the SAMPLE1–SAMPLE5 variables (columns

Select the CASE1–CASE4 variables (columns K:N) as
A:E) as MEASUREMENTS. This layout allows using
MEASUREMENTS.
subgroups with unequal sizes.
Workbook with samples is available through the Dataset link at the top of this page.

CUSUM chart
CUSUM chart (cumulative sum control chart) is used for change detection monitoring. While control charts
for subgroup averages (X-bar, R and S charts) use information only from the last sample and can detect
process changes greater than 1.5𝜎, CUSUM chart, introduced by (Page, 1954), uses information given by the
entire sequence of samples and thus can detect smaller shifts and maintain tight control over a process.
CUSUM is one of the most powerful management tools available for the detection of trends and slight
changes in data.

The cumulative sum of the deviations between each data point (a sample mean) and a reference value –
target (T), is plotted. For the rth sample the cumulative sum is defined as:

𝐶𝑟 = ∑𝑟𝑖=0(𝑥𝑖 − 𝑇), where T is the target. The choice of the T value depends on the application of
the technique. Upper and lower control limits are computed as follows:
+ ] − ]
𝐶𝑟+ = max[0, 𝑥𝑖 − (𝑇 + 𝐾) + 𝐶𝑟−1 , 𝐶𝑟− = max[0, (𝑇 − 𝐾) − 𝑥𝑖 + 𝐶𝑟−1 , 𝐶0+ = 𝐶0− = 0.
 Allowance K is often chosen about halfway between the target T and the out-of-control value of the
mean that we are interested in detecting.

 Run: CHARTS->[CONTROL CHARTS] CUSUM CHART command.

 Select a variable with group codes and a variable with measurements.

 Specify the target or check the “AUTO SELECT TARGET” option to use the grand mean as the target
∑𝑠𝑢𝑏𝑔𝑟𝑜𝑢𝑝𝑠 ∑𝑖=1..𝑆𝑢𝑏𝑔𝑟𝑜𝑢𝑝 𝑆𝑖𝑧𝑒 𝑋𝑖
estimate. A grand mean is calculated as ∑𝑠𝑢𝑏𝑔𝑟𝑜𝑢𝑝𝑠 𝑆𝑢𝑏𝑔𝑟𝑜𝑢𝑝 𝑆𝑖𝑧𝑒
.

 Specify the decision interval H (control limits). Default value of H is 4.

 Specify the allowance K (also known as a slack value). Default value of K is 0.5, to detect one-sigma
shifts in the mean.

 Specifies which subgroup to center the V-mask on. The subgroups have indices starting from 1.
Leave the default value – zero, to use the last subgroup.

P chart
P chart is used to monitor the proportion of defectives in a process. The sample fraction nonconforming
(proportion of defectives) is defined as the ratio of the number of nonconforming units 𝐷 to the sample
𝐷
size 𝑁: 𝑝 = 𝑁. The random variable 𝑝 follows binomial distribution. The mean of 𝑝 is 𝜇𝑝 = 𝑝 and the
𝑝(1−𝑝)
variance of 𝑝 is 𝜎𝑝 = 𝑁
. The control limits are defined as
𝐿𝐶𝐿 = 𝑇𝑎𝑟𝑔𝑒𝑡 𝑣𝑎𝑙𝑢𝑒 − 3𝜎𝑝 , UCL = 𝑇𝑎𝑟𝑔𝑒𝑡 𝑣𝑎𝑙𝑢𝑒 + 3𝜎𝑝 .

 Run: CHARTS->[CONTROL CHARTS] P CHART command.

 Select a variable with subgroups sample size and a variable with defectives count (measurements)
for each subgroup.

 If the true fraction conforming p is known – specify the target value. When p is not known it is
estimated with the grand mean.

C chart
C chart is used to monitor the total number of nonconformities per unit 𝑐𝑖 . Unlike the P chart, the C chart
allows having more than one nonconformity per inspection unit, and requires a fixed sample size. The
random variable 𝑐 follows Poisson distribution.

Center line is defined as 𝑐̅ = 𝜇𝑐 . It is estimated as the observed average number of nonconformities

(grand mean), and control limits are defined as 𝑐̅ ± 𝑘 √𝑐̅, where 𝑘 is set to 3 by default. If the lower control
limit is negative, then there is no lower control limit.

 Run: CHARTS->[CONTROL CHARTS] C CHART command.

 Select a variable with measurements (number of nonconformities per unit).

U chart
U chart is used to monitor the average number of nonconformities per unit 𝑢𝑖 = 𝑐𝑖 /𝑁𝑖 . With U chart we can
have several inspection units in a sample. Center line is defined as 𝑢̅ = 𝜇𝑢 .

 Run: CHARTS->[CONTROL CHARTS] U CHART command.

 Select a variable with subgroups sample size and a variable with defectives count (measurements)
for each subgroup.

Individuals and moving range I-MR charts

Individuals control chart (I CHART) is used for process monitoring based on individual observations. The
center line represents an estimate of the process average (when unspecified, the average of all the
observations, grand mean, is used), and points on the chart are the individual values. Control limits are
̅̅̅̅̅ /𝑑2 , where ̅̅̅̅̅
defined as 𝑥̅ ± 𝑘𝑀𝑅 𝑀𝑅 is an average of the moving ranges, 𝑑2 is the unbiasing factor and 𝑘 is
set to 3 by default. Individual charts are less sensitive (i.e., less powerful) than Xbar and R charts, and the
assumption of normality is more critical (deviations from normality may lead to elevated rate of false
alarms).

Moving range chart (MR CHART) monitors the between variation over time. Moving ranges represent
point-to-point variation and are defined as the absolute differences between consecutive points. The
number of points used to calculate a moving range is the moving range length or span. For the default span
value of two, 𝑀𝑅𝑖 are defined as 𝑀𝑅𝑖 = |𝑥𝑖 − 𝑥𝑖−1 |. Points on the chart are moving ranges 𝑀𝑅𝑖 and the
̅̅̅̅̅. Control limits are defined as 𝑀𝑅
center line is an average of the moving ranges 𝑀𝑅 ̅̅̅̅̅ ± 𝑘𝑑3 𝑀𝑅
̅̅̅̅̅ (𝑘 is set to 3
by default). Moving range chart may show cycles or pattern of runs induced by correlation of moving ranges
(Montgomery, 2005) and thus should be treated cautiously.

 Run: CHARTS->[CONTROL CHARTS] INDIVIDUALS AND MOVING RANGE command.

 Select a variable with measurements.

 Optionally, change the method of estimating sigma.

References
Montgomery, D. (2005). Introduction to Statistical Quality Control. Hoboken, New Jersey: John Wiley &
Sons, Inc.

Oakland, J. (2007). Statistical Process Control, 6th edition. Butterworth-Heinemann.

Page, E. S. (1954). "Continuous Inspection Scheme". Biometrika. 41 (1/2): 100–115.

Shewhart, W.A. (1931). Economic Control of Quality of Manufactured Products. Van Nostrand, New York
and MacMillan, London (501 pages).

Wheeler, D. J. (2010). Individuals Charts Done Right and Wrong, Quality Digest.