The purpose of Quantitative Project Management (QPM) is to quantitatively manage the project’s defined process to achieve the project’s established quality and process-performance objectives.
The Quantitative Project Management process area involves the following activities:
• Establishing and maintaining the project’s quality and process-performance objectives
• Identifying suitable subprocesses that compose the project’s defined process based on historical stability and capability data found in process-performance baselines or models
• Selecting subprocesses within the project’s defined process to be statistically managed
• Monitoring the project to determine whether the project’s objectives for quality and process performance are being satisfied, and identifying appropriate corrective action
• Selecting measures and analytic techniques to be used in statistically managing selected subprocesses
• Establishing and maintaining an understanding of the variation of selected subprocesses using selected measures and analytic techniques
• Monitoring the performance of selected subprocesses to determine whether they are capable of satisfying their quality and process-performance objectives, and identifying corrective action
• Recording statistical and quality management data in the organization’s measurement repository
Tip
The specific practices of QPM are best implemented by those who actually execute the project’s defined process—not by management or consulting statisticians alone.
When effectively implemented, QPM empowers individuals and teams by enabling them to accurately estimate (make predictions) and make commitments to these estimates (predictions) with confidence. This implementation of QPM is a key indicator of a truly capable process and a mature organization.
The quality and process-performance objectives, measures, and baselines identified here are developed as described in the Organizational Process Performance process area. Subsequently, the results of performing the processes associated with the Quantitative Project Management process area (e.g., measurement definitions and measurement data) become part of the organizational process assets referred to in the Organizational Process Performance process area.
X-Ref
QPM and OPP are tightly coupled process areas. Each produces work products used by the other. An organization seeking to implement one of these should seek to implement both. Likewise, the capability level 4 generic practices (CL4 GPs) should not be addressed for any process area except in the context of implementing OPP and QPM.
To effectively address the specific practices in this process area, the organization must have already established a set of standard processes and related organizational process assets, such as the organization’s measurement repository and the organization’s process asset library for use by each project in establishing its defined process.
The project’s defined process is a set of subprocesses that form an integrated and coherent lifecycle for the project. It is established, in part, through selecting and tailoring processes from the organization’s set of standard processes. (See the definition of “defined process” in the glossary.)
X-Ref
QPM selects the organizational process assets established in OPD based on a quantitative understanding of their ability to meet project-specific objectives.
The project should ensure that supplier effort and progress measurements are made available. Establishing effective relationships with suppliers is also necessary for the successful implementation of this process area’s specific practices.
The acquirer uses quantitative methods to manage its work and to gain insight into supplier work and products. In addition to its own quantitative data, the acquirer uses quantitative data provided by the supplier as specified in the supplier agreement to address the specific practices in this process area.
Process performance is a measure of actual process results achieved. Process performance is characterized by both process measures (e.g., effort, cycle time, and defect removal efficiency) and product measures (e.g., reliability, defect density, and response time).
Subprocesses are defined components of a larger defined process. The subprocesses themselves may be further decomposed into other subprocesses and process elements.
An essential element of quantitative management is having confidence in estimates (i.e., being able to predict the extent to which the project can fulfill its quality and process-performance objectives). Subprocesses to be statistically managed are chosen based on identified needs for predictable performance. (See the definitions of “statistically managed process,” “quality and process-performance objective,” and “quantitatively managed process” in the glossary.)
Another essential element of quantitative management is understanding the nature and extent of the variation experienced in process performance, and recognizing when the project’s actual performance may not be adequate to achieve the project’s quality and process-performance objectives.
Statistical management involves statistical thinking and the correct use of a variety of statistical techniques such as run charts, control charts, confidence intervals, prediction intervals, and tests of hypotheses. Quantitative management uses data from statistical management to help the project predict whether it will be able to achieve its quality and process-performance objectives and identify what corrective action should be taken.
Tip
By “statistical thinking,” we mean using statistical analysis techniques as tools in appropriate ways to estimate the variation in the performance of a process, to investigate its causes, and to recognize from the data when the process is not performing as it should.
This process area applies to managing a project, but the concepts found here also apply to managing other groups and functions. Applying these concepts to managing other groups and functions may not necessarily contribute to achieving the organization’s business objectives but may help these groups and functions control their processes.
Refer to the Project Monitoring and Control process area for more information about monitoring and controlling the project and taking corrective action.
Refer to the Measurement and Analysis process area for more information about establishing measurable objectives, specifying measures and analyses to be performed, obtaining and analyzing measures, and reporting results.
Refer to the Organizational Process Performance process area for more information about the organization’s quality and process-performance objectives, process-performance analyses, process-performance baselines, and process-performance models.
Refer to the Organizational Process Definition process area for more information about organizational process assets, including the organization’s measurement repository.
Refer to the Integrated Project Management process area for more information about establishing and maintaining the project’s defined process.
Refer to the Causal Analysis and Resolution process area for more information about identifying causes of defects and other problems and taking action to prevent them from occurring in the future.
Refer to the Organizational Innovation and Deployment process area for more information about selecting and deploying improvements that support the organization’s quality and process-performance objectives.
Refer to the Solicitation and Supplier Agreement Development process area for more information about establishing reporting requirements for supplier measurement results and quantitative data in the supplier agreement.
X-Ref
See Measuring the Software Process, Statistical Process Control for Software Process Improvement by William A. Florac and Anita D. Carleton (Addison-Wesley).
See Understanding Statistical Process Control (Second Edition) by Donald J. Wheeler and David S. Chambers (SPC Press, Inc.).
See Understanding Variation: The Key to Managing Chaos (Second Edition) by Donald J. Wheeler (SPC Press, Inc.).
Specific Goal and Practice Summary
SG 1 Quantitatively Manage the Project
SP 1.1 Establish the Project’s Objectives
SP 1.2 Compose the Defined Process
SP 1.3 Select Subprocesses to Be Statistically Managed
SP 1.4 Manage Project Performance
SG 2 Statistically Manage Subprocess Performance
SP 2.1 Select Measures and Analytic Techniques
SP 2.2 Apply Statistical Methods to Understand Variation
SP 2.3 Monitor the Performance of Selected Subprocesses
SP 2.4 Record Statistical Management Data
The project is quantitatively managed using quality and process-performance objectives.
Tip
Generally, these objectives are established early during project planning as customer requirements relating to product quality, service quality, and process performance are being established and analyzed.
Once a supplier or set of suppliers are selected, revisit these objectives. Teaming with suppliers who have quantitatively managed processes may present opportunities to optimize across organizational boundaries.
Establish and maintain the project’s quality and process-performance objectives.
When establishing the project’s quality and process-performance objectives, it is often useful to think ahead about which processes from the organization’s set of standard processes will be included in the project’s defined process and what the historical data indicate regarding their process performance. These considerations will help in establishing realistic objectives for the project. Later, as the project’s actual performance becomes known and more predictable, objectives may need to be revised.
The acquirer establishes the project’s quality and process-performance objectives based on objectives of the organization, the customer, and other relevant stakeholders. The acquirer may also establish quality and process-performance objectives for supplier deliverables. These quantitative quality and process-performance objectives for the supplier are documented in the supplier agreement. The acquirer typically expects the supplier to execute its processes and apply its process-performance models toward achieving these objectives.
Hint
The project’s quality and process-performance objectives can be challenging but must be achievable. In other words, balance senior management’s desire for improvement with what projects are realistically capable of achieving.
Supplier quality and process-performance objectives that are “specified” by the acquirer prior to contract award will need to be revised once the selected supplier’s performance baselines are established.
Typical Work Products
- The project’s quality and process-performance objectives
Subpractices
- Review the organization’s objectives for quality and process performance.
The intent of this review is to ensure that the project understands the broader business context in which the project must operate. The project’s objectives for quality and process performance are developed in the context of these overarching organizational objectives.
Refer to the Organizational Process Performance process area for more information about the organization’s quality and process-performance objectives.
Tip
The project’s objectives for quality and process performance are based, in part, on those of the organization (OPP SP 1.3). This approach helps to ensure that the project’s objectives for quality and process performance are aligned with those of the organization.
- Identify the quality and process-performance needs and priorities of the customer, suppliers, end users, and other relevant stakeholders.
- Identify how process performance is to be measured.
Consider whether measures established by the organization are adequate for assessing progress in fulfilling customer, end user, and other stakeholder needs and priorities. It may be necessary to supplement these measures with additional ones.
Refer to the Measurement and Analysis process area for more information about defining measures.
- Define and document measurable quality and process-performance objectives for the project.
Defining and documenting objectives for the project involve the following:
• Incorporating the organization’s quality and process-performance objectives
• Writing objectives that reflect the quality and process-performance needs and priorities of the customer, end users, and other stakeholders, and the way these objectives should be measured
Hint
Apply the organization’s process-performance models to determine which interim objectives lead to the desired project outcomes. Review interim objectives later as part of monitoring the project’s progress toward achieving its (overarching) objectives for quality and process performance. (See SP 1.4, subpractice 2.)
- Derive interim objectives for each lifecycle phase, as appropriate, to monitor progress toward achieving the project’s objectives.
- Resolve conflicts among the project’s quality and process-performance objectives (e.g., if one objective cannot be achieved without compromising another).
Resolving conflicts involves the following activities:
• Setting relative priorities for objectives
• Considering alternative objectives in light of long-term business strategies as well as short-term needs
• Involving the customer, end users, senior management, project management, and other relevant stakeholders in tradeoff decisions
• Revising objectives as necessary to reflect results of conflict resolution
- Establish traceability to the project’s quality and process-performance objectives from their sources.
- Define and negotiate quality and process-performance objectives for suppliers.
Refer to the Solicitation and Supplier Agreement Development process area for more information about incorporating project quality and process-performance objectives into solicitation packages and into supplier agreements.
- Revise the project’s quality and process-performance objectives as necessary.
Select subprocesses that compose the project’s defined process based on historical stability and capability data.
Refer to the Integrated Project Management process area for more information about establishing and maintaining the project’s defined process.
Refer to the Organizational Process Definition process area for more information about the organization’s process asset library, which might include a process element of known and needed capability.
Tip
Some organizations may have only one standard process (e.g., because the projects are sufficiently similar to one another). In such cases, there are still some choices to explore (e.g., which attributes of the acquisition strategy should be modified to achieve project objectives).
Refer to the Organizational Process Performance process area for more information about the organization’s process-performance baselines and process-performance models.
Tip
Sources of historical stability and capability data include the organization’s process-performance baselines and models (OPP SPs 1.4 and 1.5). These organizational assets can help the project determine whether a defined process capable of achieving the project’s objectives can be established from the organization’s set of standard processes.
Subprocesses are identified from process elements in the organization’s set of standard processes and process artifacts in the organization’s process asset library.
These subprocesses may include those used for interacting with a supplier (e.g., negotiating a supplier agreement and conducting supplier reviews).
Typical Work Products
- Criteria used in identifying which subprocesses are valid candidates for inclusion in the project’s defined process
- Candidate subprocesses for inclusion in the project’s defined process
- Subprocesses to be included in the project’s defined process
- Identified risks when selected subprocesses lack a process-performance history
Subpractices
- Establish the criteria to use in identifying which subprocesses are valid candidates for use.
- Determine whether subprocesses that are to be statistically managed and were obtained from the organizational process assets are suitable for statistical management.
A subprocess may be more suitable for statistical management if it has a history of the following:
• Stable performance in previous comparable instances
• Process-performance data that satisfy the project’s quality and process-performance objectives
Historical data are primarily obtained from the organization’s process-performance baselines. However, these data may not be available for all subprocesses.
- Analyze the interaction of subprocesses to understand relationships among subprocesses and measured attributes of the subprocesses.
- Identify the risk when no subprocess is available that is known to be capable of satisfying quality and process-performance objectives (i.e., no capable subprocess is available or the capability of the subprocess is not known).
Even when a subprocess has not been selected to be statistically managed, historical data and process-performance models may indicate that the subprocess is not capable of satisfying quality and process-performance objectives.
Refer to the Risk Management process area for more information about identifying and analyzing risks.
X-Ref
To see how to use systems thinking to evaluate the underlying dynamics of common patterns of failure, see “Acquisition Archetypes: Changing Counterproductive Behaviors in Real Acquisitions” at www.sei.cmu.edu/programs/acquisition-support/pof-intro.html.
Select subprocesses of the project’s defined process to be statistically managed.
Selecting subprocesses to be statistically managed is often a concurrent and iterative process of identifying applicable project and organization quality and process-performance objectives, selecting subprocesses, and identifying process and product attributes to measure and control. Often, the selection of a process, quality and process-performance objective, or measurable attribute will constrain the selection of the other two. For example, if a particular process is selected, measurable attributes and quality and process-performance objectives may be constrained by that process.
Hint
How many subprocesses must be statistically managed to be capability or maturity level 4? There is no universal answer, of course, but an initial approach might be to select subprocesses (1) that give visibility into what is happening within each major lifecycle phase (and for each team) and (2) whose behavior can be used to update or calibrate process-performance models to predict future project outcomes. This approach allows project members to regularly determine whether they are still on track toward meeting project objectives.
Typical Work Products
- Quality and process-performance objectives to be addressed by statistical management
- Criteria used in selecting which subprocesses will be statistically managed
- Subprocesses to be statistically managed
- Identified process and product attributes of selected subprocesses that should be measured and controlled
- Identify which of the project’s quality and process-performance objectives will be statistically managed.
- Identify criteria to be used in selecting subprocesses that are the main contributors to achieving identified quality and process-performance objectives and for which predictable performance is important.
Hint
Identify which objectives will be addressed through statistically managing attributes of one or more subprocesses.
Avoid selecting objectives that are outside the acquisition team’s ability to control. Objectives that are achieved by a supplier or end user are important to track, but difficult to quantitatively manage using statistical process control techniques because the processes are outside your control.
- Select subprocesses to be statistically managed using selection criteria.
It may not be possible to statistically manage some subprocesses (e.g., where new subprocesses and technologies are being piloted). In other cases, it may not be economically justifiable to apply statistical techniques to certain subprocesses.
Tip
The project’s selection of subprocesses to statistically manage is based, in part, on those selected by the organization (OPP SP 1.1).
- Identify product and process attributes of selected subprocesses to be measured and controlled.
Monitor the project to determine whether the project’s objectives for quality and process performance will be satisfied, and identify corrective action, as appropriate.
Refer to the Measurement and Analysis process area for more information about analyzing and using measures.
A prerequisite for such a determination is that the selected subprocesses of the project’s defined process are statistically managed and their process capability is understood. Specific practices of specific goal 2 provide detail on statistically managing selected subprocesses.
Tip
Expand your process improvement toolkit to include techniques such as Six Sigma or Theory of Constraints when deciding the corrective actions to take.
The acquirer monitors the performance of selected subprocesses to assess whether the project is on track in achieving its quality and process-performance objectives. These subprocesses include those that involve interaction with a supplier. This selective monitoring provides the acquirer with insight into project and supplier performance to predict the likelihood of achieving project objectives for quality and process performance. The acquirer uses this information to manage the project and to initiate corrective actions in time to meet project objectives.
X-Ref
To see how to use Six Sigma with CMMI see “CMMI and Six Sigma: Partners in Process Improvement,” at www.sei.cmu.edu/publications/books/process/cmmi-six-sigma.html.
For more information on using Theory of Constraints and the Critical Thinking Tools, see Thinking for a Change: Putting the TOC Thinking Processes to Use by Lisa Scheinkopf (CRC).
Typical Work Products
- Estimates (i.e., predictions) of the achievement of the project’s quality and process-performance objectives
- Documentation of risks in achieving the project’s quality and process-performance objectives
- Documentation of actions needed to address deficiencies in achieving project objectives
Typical Supplier Deliverables
- Supplier process-performance data for quality and process-performance objectives and expected service levels
Subpractices
- Periodically review the performance and capability of each subprocess selected to be statistically managed to appraise progress toward achieving the project’s quality and process-performance objectives.
The process capability of each selected subprocess is determined with respect to that subprocess’s established quality and process-performance objectives. These objectives are derived from the project’s quality and process-performance objectives, which are defined for the project as a whole.
- Periodically review actual results achieved against established interim objectives for each phase of the project lifecycle to appraise progress toward achieving the project’s quality and process-performance objectives.
- Track supplier results for achieving their quality and process-performance objectives.
- Use process-performance models calibrated with obtained measures of critical attributes to estimate progress toward achieving the project’s quality and process-performance objectives.
Tip
The organization’s process-performance models (OPP SP 1.5) can help the project determine whether it will be able to achieve the project’s objectives.
Process-performance models are used to estimate progress toward achieving objectives that cannot be measured until a future phase in the project lifecycle. An example is the use of process-performance models to predict latent defects in the delivered product using interim measures of defects identified during peer reviews.
Refer to the Organizational Process Performance process area for more information about process-performance models.
Calibration of the process-performance models is based on results obtained from performing the previous subpractices.
- Identify and manage risks associated with achieving the project’s quality and process-performance objectives.
Refer to the Risk Management process area for more information about identifying and managing risks.
- Determine and document actions needed to address deficiencies in achieving the project’s quality and process-performance objectives.
The performance of selected subprocesses within the project’s defined process is statistically managed.
Tip
A “statistically managed process” does not require or expect control charts per se, but rather techniques that help determine the natural bounds in process variation and detect anomalous events. To date, control charts are the most widely used statistical analysis technique. When the circumstances warrant (e.g., when dealing with time-ordered event data from statistically independent events), control charts are a practical technique for accomplishing these things.
Avoid the temptation of using cumulative data (e.g., Schedule Performance Index or Cost Performance Index) on control charts. Variation is masked because of the cumulative nature of the indicator and large variances associated with independent events can be missed. This specific goal describes an activity critical to achieving the Quantitatively Manage the Project specific goal of this process area. The specific practices under this specific goal describe how to statistically manage subprocesses whose selection was described in specific practices under specific goal 1. When selected subprocesses are statistically managed, their capability to achieve their objectives can be determined. By these means, it is possible to predict whether the project will be able to achieve its objectives, which is key to quantitatively managing the project.
Select measures and analytic techniques to be used in statistically managing selected subprocesses.
Refer to the Measurement and Analysis process area for more information about establishing measurable objectives; specifying the measures and analyses to be performed; obtaining, analyzing, and updating measures; and reporting results.
Typical Work Products
- Definitions of measures and analytic techniques to be used in (or proposed for) statistically managing subprocesses
- Operational definitions of measures, their collection points in subprocesses, and how the integrity of measures will be determined
- Traceability of measures back to the project’s quality and process-performance objectives
- Instrumented organizational support environment that supports automatic data collection
Tip
The project’s identification of common measures to support statistical management is based, in part, on measures established by the organization to be included in its process performance analyses (OPP SP 1.2).
Subpractices
- Identify common measures from the organizational process assets that support statistical management.
- Identify additional measures that may be needed for this instance to cover critical product and process attributes of the selected subprocesses.
In some cases, measures may be research-oriented. Such measures should be explicitly identified.
- Identify the measures that are appropriate for statistical management.
Critical criteria for selecting statistical management measures include the following:
• Controllable (e.g., can a measure’s values be changed by changing how the subprocess is implemented?)
• Adequate performance indicator (e.g., is the measure a good indicator of how well the subprocess is performing relative to the objectives of interest?)
- Specify the operational definitions of measures, their collection points in subprocesses, and how the integrity of measures will be determined.
Operational definitions are stated in precise and unambiguous terms. They address two important criteria:
• Communication: What has been measured, how it was measured, what are the units of measure, and what has been included or excluded?
• Repeatability: Is the measurement repeatable, given the same definition, to get the same results?
- Analyze the relationship of identified measures to the objectives of the organization and its projects, and derive objectives that state target measures or ranges to be met for each measured attribute of each selected subprocess.
- Instrument the organizational or project support environment to support collection, derivation, and analysis of statistical measures.
This instrumentation is based on the following:
• Description of the organization’s set of standard processes
• Description of the project’s defined process
• Capabilities of the organizational or project support environment
- Identify appropriate statistical analysis techniques that are expected to be useful in statistically managing the selected subprocesses.
The concept of “one size does not fit all” applies to statistical analysis techniques. What makes a particular technique appropriate is not just the type of measures but, more important, how the measures will be used and whether the situation warrants applying that technique. The appropriateness of the selection may need to be reviewed from time to time.
Examples of statistical analysis techniques are given in the next specific practice.
- Revise measures and statistical analysis techniques as necessary.
Establish and maintain an understanding of the variation of selected subprocesses using selected measures and analytic techniques.
Tip
Achieving a stable subprocess (in which special causes of variation are detected and removed) is not enough. A subprocess that otherwise appears to be stable may demonstrate unacceptably wide variation, which should arouse suspicion. In any case, such a subprocess is not very predictable.
Refer to the Measurement and Analysis process area for more information about collecting, analyzing, and using 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 performance.
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.
Hint
To address unacceptably wide variation, investigate the sources of that variation. How does the subprocess behave on certain data? How is its performance affected by upstream and lower-level subprocesses? The answers are opportunities to reduce variation in subprocess performance and more accurately predict future performance.
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 are needed to detect special causes of variation.
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 selected subprocess
Typical Supplier Deliverables
- Collected supplier measurements
- Natural bounds of supplier process performance for each measured attribute of each selected subprocess
- Supplier process performance compared to the natural bounds of process performance for each measured attribute of each selected subprocess
Subpractices
- Establish trial natural bounds for subprocesses having suitable historical performance data.
Refer to the Organizational Process Performance process area for more information about organizational 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 used.
In some cases, there may be no comparable historical data (e.g., when introducing a new subprocess, when entering a new application domain, or 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.
Tip
If the circumstances of subprocess execution are similar to those on which a process-performance baseline is based, such a baseline may be used to help establish trial natural bounds.
Hint
If all other means of establishing trial natural bounds fail, use the first measurements obtained from performing the subprocess. Estimate natural bounds (a.k.a. trial control limits) when there are only three or four data points, but take care not to overinterpret “assignable cause signals” until natural bounds become substantiated with further data.
- Collect data, as defined by selected measures, on subprocesses as they execute.
- Calculate the natural bounds of process performance for each measured attribute.
- Identify special causes of variation.
Tip
Special causes of variation need to be identified and addressed to maintain predictable performance of the subprocess.
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 cause of process variation to determine the reasons the anomaly occurred.
X-Ref
For more information, see the references in “Related PAs” and the entry for “Control Charts” in Wikipedia, www.wikipedia.org.
Hint
To better understand subprocess variation, investigate at a lower level of granularity. Restratify the data (grouped to match input types or teams that will execute the subprocess), and test data subsequences for stability to obtain tighter control. See Example 7.1 in Measuring the Software Process—Statistical Process Control for Software Process Improvement by William A. Florac and Anita D. Carleton (Addison-Wesley).
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 in the way the subprocess is executed.
Refer to the Project Monitoring and Control process area for more information about taking corrective action.
- 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, not on expectations or arbitrary decisions.
Monitor the performance of selected subprocesses to determine their capability to satisfy their quality and process-performance objectives, and identify corrective action as necessary.
The intent of this specific practice is to do the following:
• Statistically determine process behavior expected from the subprocess
• Appraise the probability that the subprocess will meet its quality and process-performance objectives
• Identify the corrective action to be taken based on a statistical analysis of process-performance data
Hint
For each stable subprocess (i.e., stable relative to a particular attribute to be controlled), compare its natural bounds against its associated objectives for quality and process performance and take corrective action as necessary.
Tip
This comparison of the natural bounds against derived objectives is called “determining the process capability” and “comparing the ‘voice of the process’ tohe ‘voice of the customer’.”
These actions are intended to help the project use a more capable process. (See the definition of “capable process” in the glossary.)
A prerequisite for comparing the capability of a selected subprocess against its quality and process-performance objectives is that the measured attributes of the subprocess indicate that its performance is stable and predictable.
Tip
To determine whether a subprocess is capable relative to a particular attribute you must first know whether it is stable relative to that attribute.
Process capability is analyzed for those subprocesses and measured attributes for which (derived) objectives are established. Not all subprocesses or measured attributes that are statistically managed are analyzed regarding process capability.
Historical data may be inadequate for initially determining whether the subprocess is capable. It also is possible that the estimated natural bounds for subprocess performance may shift away from quality and process-performance objectives. In either case, statistical control implies monitoring capability as well as stability.
Typical Work Products
- Natural bounds of process performance for each selected subprocess compared to its established (derived) objectives
- The process capability of each subprocess
- The actions needed to address deficiencies in the process capability of each subprocess
Typical Supplier Deliverables
- Actions needed to address deficiencies in supplier process performance or the quality of deliverables
- Compare quality and process-performance objectives to the natural bounds of the measured attribute.
This comparison provides an appraisal of the process capability for each measured attribute of a subprocess. These comparisons can be displayed graphically in ways that relate the estimated natural bounds to the objectives or as process capability indices, which summarize the relationship of objectives to natural bounds.
- Monitor changes in quality and process-performance objectives and the process capability of the selected subprocess.
- Identify and document deficiencies in subprocess capability.
- Determine and document actions needed to address deficiencies in subprocess capability.
Hint
Sometimes you can change the objectives derived for a particular attribute so that the subprocess’s capability meets them by investigating whether some other subprocesses can give up some needed slack.
Refer to the Project Monitoring and Control process area for more information about taking corrective action.
Record statistical and quality management data in the organization’s measurement repository.
Refer to the Measurement and Analysis process area for more information about managing and storing data, measurement definitions, and results.
Refer to the Organizational Process Definition process area for more information about the organization’s measurement repository.
X-Ref
Statistical and quality management data may contribute to a future revision of the organization’s process-performance baselines and models (OPP SPs 1.4 and 1.5).
Typical Work Products
- Statistical and quality management data recorded in the organization’s measurement repository