Establish and maintain an understanding of the
variation of selected subprocesses using selected measures and analytic
Refer to the Measurement and Analysis
process area for more information about aligning measurement and analysis
activities and providing measurement results.
Understanding variation is achieved, in part,
by collecting and analyzing process and product measures so that special
causes of variation can be identified and addressed to achieve predictable
A special cause of process variation is
characterized by an unexpected change in process performance. Special
causes are also known as “assignable causes” because they can be
identified, analyzed, and addressed to prevent recurrence.
The identification of special causes of
variation is based on departures from the system of common causes of
variation. These departures can be identified by the presence of extreme
values or other identifiable patterns in data collected from the
subprocess or associated work products. Typically, knowledge of variation
and insight about potential sources of anomalous patterns is needed to
detect special causes of variation.
|Sources of anomalous patterns of
variation may include the following:
- Lack of process
- Undistinguished influences of multiple underlying
subprocesses on the data
- Ordering or timing of activities within the
- Uncontrolled inputs to the
- Environmental changes during subprocess
- Schedule pressure
- Inappropriate sampling or grouping of
Typical Work Products
- Collected measurements
- Natural bounds of process performance for
each measured attribute of each selected subprocess
- Process performance compared to the natural
bounds of process performance for each measured attribute of each
- Establish trial natural bounds for
subprocesses having suitable historical performance
Refer to the
Process Performance process area for more information about
establishing process-performance baselines.
Natural bounds of an attribute are the range
within which variation normally occurs. All processes show some
variation in process and product measures each time they are executed.
The issue is whether this variation is due to common causes of variation
in the normal performance of the process or to some special cause that
can and should be identified and removed.
When a subprocess is initially executed, suitable
data for establishing trial natural bounds are sometimes available from
prior instances of the subprocess or comparable subprocesses,
process-performance baselines, or process-performance models. Typically,
these data are contained in the organization’s measurement repository.
As the subprocess is executed, data specific to that instance are
collected and used to update and replace the trial natural bounds.
However, if the subprocess has been materially tailored or if conditions
are materially different from those in previous instantiations, data in
the repository may not be relevant and should not be
In some cases,
there may be no comparable historical data (e.g., when introducing a new
subprocess, when entering a new application domain, when significant
changes have been made to the subprocess). In such cases, trial natural
bounds will have to be made from early process data of this subprocess.
These trial natural bounds must then be refined and updated as
subprocess execution continues.
|Examples of criteria for determining whether
data are comparable include the following:
- Standard services and
- Application domain
- Work product and task attributes
- Service system attributes (e.g., size,
complexity, number of
- Collect data, as defined by selected
measures, on subprocesses as they execute.
- Calculate the natural bounds of process
performance for each measured attribute.
|Examples of statistical techniques for
calculating natural bounds include the following:
- Confidence intervals (for
parameters of distributions)
- Prediction intervals (for
- Identify special causes of
An example of a criterion for detecting
a special cause of process variation in a control chart is a data
point that falls outside 3-sigma control
The criteria for detecting special causes of
variation are based on statistical theory and experience and depend on
economic justification. As criteria are added, special causes are more
likely to be identified if they are present but the likelihood of false
alarms also increases.
- Analyze special causes of process variation
to determine the reasons why the anomaly occurred.
|Examples of techniques for analyzing the
reasons for special causes of variation include the
- Cause-and-effect (i.e.,
- Control charts (applied to
subprocess inputs or lower level subprocesses)
- Subgrouping (i.e.,
analyzing the same data segregated into smaller groups based on
an understanding of how the subprocess was implemented
facilitates isolation of special
Some anomalies may simply be extremes of the
underlying distribution rather than problems. Those implementing a
subprocess are usually the ones best able to analyze and understand
special causes of variation.
- Determine the corrective action to be taken
when special causes of variation are identified.
Removing a special cause of process variation
does not change the underlying subprocess. It addresses an error or
condition in the execution of the subprocess.
Refer to the Project Monitoring and
Control process area for more information about managing corrective
action to closure.
- Recalculate natural bounds for each measured
attribute of the selected subprocesses as necessary.
Recalculating the (statistically estimated)
natural bounds is based on measured values that signify that the
subprocess has changed. It is not based on expectations or arbitrary
|Examples of when natural bounds may
need to be recalculated include the following:
- There are incremental
improvements to the subprocess
- New tools are deployed for the
- A new subprocess is deployed
- The collected measures suggest that the
subprocess mean has permanently shifted or subprocess variation