What this is
What is a statistical process capability study?
What is a statistical process capability study?
A deliberately designed measurement of whether a process can consistently hold its tolerance, distinguishing short-term machine capability from long-term process capability that accounts for operators, batches and time. It records the design, the data, the resulting indices and the disposition decision that follows a poor result.
Why does the template ask for a study type before any data?
Short-term studies use Cp and Cpk, answering what the machine can do under near-ideal conditions. Long-term studies use Pp and Ppk, answering what the customer will actually see. Choosing the type after the data is collected is how the two get confused.
What happens when capability falls below target?
The template forces an immediate disposition decision: whether full inspection is needed while the process or specification is fixed, and whether the customer needs telling. This is a live risk to shipped product, not only a finding for a future review.
Scope
When is a statistical process capability study required?
This assessment is one step in a larger programme. Using it for work that belongs to a neighbouring template produces records that are hard to report on later.
Use this template when
- A new process is being qualified, or an existing one has changed enough to need capability re-established
- A customer requirement specifies a study directly, often at a stated Cpk or Ppk minimum
- A capability concern has been raised from complaint, scrap or an SPC chart showing a shift
- You are running the Statistical Process Control programme and this is one of its steps
- A linked record needs this one to exist: SPC monitoring or a change control record depends on the result
Do not use it for
- Manufacturing First Article Inspection, which inspects the first part off a setup against every specified characteristic, with no capability calculation needed
- Statistical Process Control Chart Review, which reviews ongoing control charts for stability, not one bounded study
- Gage Repeatability and Reproducibility Study, which quantifies how much observed variation comes from the measurement system, and should precede this study
- Production Part Approval Record, the broader submission package a capability study feeds into rather than replaces
- Anything outside KnowQuality, which belongs in the workspace that owns that process
Compliance mapping
Which ISO 9001 cl.8.5 requirements does this satisfy?
ISO 9001 clause 8.5 requires controlled production and controlled change; ISO 22514 supplies the statistical method the figures are calculated by. The template sits at the join between the two.
| Clause | Requirement | Where it lands |
|---|---|---|
| ISO 9001 cl.8.5.1 | Production carried out under controlled conditions, including monitoring and measurement where applicable | Results |
| ISO 9001 cl.8.5.6 | Changes affecting conformity to requirements are reviewed and controlled | Conclusion |
| ISO 22514-2 | Capability indices for a normally distributed characteristic, distinguishing short-term (Cp, Cpk) from long-term (Pp, Ppk) | Results |
| ISO 22514-1 | The process is shown stable before a capability figure is calculated from it | Data |
| IATF 16949 cl.9.1.1.1 | Ongoing monitoring and statistical understanding of variation in manufacturing process characteristics | Data |
| IATF 16949 cl.8.5.1.1 | Control plan maintained and updated in response to a process change or capability shift | Conclusion |
What it does not cover
- Manufacturing First Article Inspection, which checks the first piece off a setup against specification, rather than establishing ongoing capability.
- Statistical Process Control Chart Review, which examines a control chart over time for stability, not a single study's Cpk or Ppk.
- Gage Repeatability and Reproducibility Study, which measures the measurement system's own contribution to variation and should precede this study.
- Production Part Approval Record, the customer submission this study's result feeds into, not a substitute for it.
- Rework Instruction Record, which documents how nonconforming product already made is corrected, not why the process produced it.
Global
Statistical Process Capability Study requirements by country
ISO 9001 and ISO 22514 are voluntary standards, so the binding force behind a study is usually a customer requirement, not a statute, and it varies most in how specific that requirement is about design.
ISO 9001:2015 clause 8.5; ISO 22514 parts 1 and 2
Requires controlled production and controlled change, with the calculation method set separately by ISO 22514.
An auditor examines whether the study's design and data support the conclusion, not only whether a Cpk exists.
AIAG SPC reference manual; customer-specific requirements under IATF 16949
Automotive and manufacturing customers specify minimum Cpk or Ppk values and the study design expected to demonstrate them.
The short/long-term distinction is usually the customer's requirement, and a mismatch is a supplier nonconformance.
VDA quality management standards; IATF 16949 across European automotive supply chains
German and wider European automotive customers commonly require capability evidence as part of production part approval.
A study without a clearly stated study type is routinely rejected at incoming quality review.
How to complete it
How to complete a statistical process capability study, step by step
The template prompts for design choices before it prompts for numbers. What decides whether the eventual Cpk or Ppk means anything comes first.
Decide short-term machine capability or long-term process capability, and design sampling to match: a short-term study can reasonably use one operator and one setup, a long-term study cannot. Choosing the type after the data exists is how a short-term dataset ends up labelled long-term.
Multiple operators, multiple batches and a defined representative period are scored fields precisely because they are easy to skip under time pressure. A study that scores well everywhere else is still a study of one convenient window, not of the process.
An outlier is either a data error, whose cause should be recorded, or a real event the process can produce, and deleting it hides the behaviour the study exists to find. The template treats none present and investigated as equally acceptable, and deleted as a failure regardless of how the numbers would look.
A band below target should trigger a decision on full inspection and customer notification in the same session, not after a corrective action plan is drafted. Product already shipped does not wait for the fix to be designed.
What auditors find
Most common statistical process capability study findings
The template almost always contains a Cpk. The findings concern whether the study was designed to support it and whether a poor result moved anything downstream.
| Finding | Clause | What fixes it |
|---|---|---|
| Study type not distinguished, so Cp/Cpk from a short-term run is reported as though it were Pp/Ppk. | ISO 22514-2 | Require the study type selected before data entry, and match the indices calculated to the type declared. |
| Long-term study run on a single operator and a single batch of material. | IATF 16949 cl.9.1.1.1 | Score representativeness honestly; a single-operator, single-batch dataset is short-term regardless of its label. |
| Outliers removed from the dataset rather than investigated. | ISO 22514-1 | Require a recorded cause for any excluded point, and refuse silent deletion. |
| Capability band below target with customer notification marked no and no rationale given. | ISO 9001 cl.8.5.6 | Gate the notification field against the capability band, and require a stated reason to override it. |
| Restudy due date set to a routine interval rather than tied to the change that prompted the study. | ISO 9001 cl.8.5.1 | Link the restudy date to the study trigger, so a process change brings it forward automatically. |
| Control plan marked not needed despite a material shift in the capability band. | IATF 16949 cl.8.5.1.1 | Require a reference or reason whenever the band has changed since the previous study. |
Case in point
Case in point: the long-term study that was really one good shift
A tier-one supplier ran a study on a critical dimension after a tooling change, labelled long-term as the customer's spec required. Data came from the day shift's best operator over a single week, one batch of material, no outliers present. Ppk came back at 1.71, above the 1.33 minimum, and the study went into the part approval package.
Six weeks into full production, across all three shifts and several lots, incoming inspection began flagging parts outside tolerance at a rate the submitted Ppk said should not occur. The re-investigation found the study had never included a second operator or batch, both fields the template asks for directly, and the true long-term variation was far wider than the favourable week had shown.
The template
The template, field by field
The form exactly as it installs. Every field, option, score and conditional rule is editable, and the links to other templates come with it.
5 sections
- Reference
- QUA-108
- Archetype
- Assessment
- Record ID
- CPK-2026-000
- Scoring
- Capability index
- Direction
- High is good
- Singleton
- Yes
- Basis
- ISO 9001 cl.8.5
- Links
- Links SPC, Change control
- Tags
- Manufacturing, Capability
- Sections
- 5
- Fields
- 52
- Follow up fields
- 3
- Repeating sections
- 0
- Links out
- 3
Header
16 fieldsStudy ID*
Auto sequence. Format CPK-2026-000.
The record's own ID. Other templates point at this value.
Status*
Drives who this goes to next.
- Planned2 pts
- In progress2 pts
- Complete3 pts
- Deferred0 pts
- Open0 pts
- Closed3 pts
- Overdue0 pts
Date and Time*
Raised By*
Site*
Site ID*
Format SITE-000.
Links to FDN-001 Site ID
Line*
Shift*
Line Lead
Batch Number*
Numeric key joining to your ERP batch record.
Links to External system reference
Product*
Production Date*
Fix The Process Or The Specification
A process that cannot hold the tolerance will not be fixed by inspecting more often. Either the process changes, the tolerance changes, or you sort forever.
Characteristic*
Study Trigger*
Study Type*
Short term machine capability, or long term process capability including all sources of variation.
Data
9 fieldsSample Size*
Data Collected Over Representative Period*
- Yes3 pts
- Marginal1 pt
- No0 pts
Multiple Operators Included*
- Yes3 pts
- No0 pts
Multiple Batches Of Material Included*
- Yes3 pts
- No0 pts
Process In Control Before Study*
Capability calculated on an out of control process is a meaningless number.
- Yes3 pts
- Marginal1 pt
- No0 pts
Measurement System Verified*
- Yes3 pts
- Assumed0 pts
Gauge Study ID
Links to QUA-066 Study ID
Data Normality Checked
- Yes3 pts
- No0 pts
Outliers Investigated Not Deleted*
- Investigated3 pts
- Deleted0 pts
- None present3 pts
Results
9 fieldsMean*
Standard Deviation*
Specification Range*
Cp Or Pp
Cpk Or Ppk*
Capability Band*
- Above 1.674 pts
- 1.33 to 1.673 pts
- 1.00 to 1.331 pt
- Below 1.000 pts
Process Centred*
A wide gap between Cp and Cpk means the process is capable but off centre, which is usually the easier fix.
- Yes3 pts
- Slightly off1 pt
- Clearly off0 pts
Predicted Defect Rate
Meets Customer Requirement*
- Yes3 pts
- Marginal1 pt
- No0 pts
Conclusion
5 fieldsAction Needed*
Centre the process, reduce variation, widen the tolerance, or introduce full inspection.
- No3 pts
- Yes1 pt
Full Inspection Required Meanwhile*
- Not required3 pts
- Yes1 pt
Customer Notification Required*
- No3 pts
- Yes0 pts
Control Plan Updated*
- Yes3 pts
- Not needed3 pts
- No0 pts
Restudy Due*
Result
13 fieldsItems Assessed*
Excludes anything marked N/A.
Items Failed*
Score Percent*
Calculated on submission. High is good. N/A items leave the denominator.
Result Band*
- Pass3 pts
- Caution1 pt
- Fail0 pts
Completeness Percent*
How much of the template was actually answered. A high score on a half completed form is not a high score.
Action Required*
Raise the action record, then enter its reference here.
- No2 pts
- Yes0 pts
Priority
- High0 pts
- Medium1 pt
- Low3 pts
CAPA ID
Format CAPA-2026-00000.
Links to FDN-014 CAPA ID
Action Owner
Quality Engineer*
Signature*
Technical Manager*
Second Signature*
QUA-108 · record IDs look like CPK-2026-000 · Links SPC, Change control
Open in KnowellaRun it with agents
From a document you fill in to a programme that runs itself
The Cpk figure is a snapshot of one designed study. What protects anything downstream is whether disposition, the control plan and the next study actually follow from it.
Holds the capability study library against the SPC and change control registers, flags a study whose linked process has since changed, and routes a poor result to disposition.
Tracks the gauge study behind the measurement system verification and flags a study relying on gauge evidence that has since expired.
Connects a capability shift to the change record that caused it, so a tooling or material change and its consequence stay linked.
Coordinates the crew, rolls capability results and open disposition decisions into one view, and holds every write for approval before it touches a record.
This template lives in KnowQuality — quality and food safety. HACCP, nonconformance, traceability, laboratory and customer complaints.
Meet KnowQuality→Glossary
Statistical Process Capability Study definitions and key terms
- Cpk
- Short-term capability index, from within-subgroup variation, describing what a process can do under near-ideal, tightly controlled conditions.
- Ppk
- Long-term performance index, from overall variation across operators, batches and time, describing what a process actually delivers in production.
- Representativeness
- How far a study's data spans the operators, batches and time the process will encounter, scored as a precondition to trusting the result.
- Outlier
- A data point far from the rest of the distribution, which must be investigated for cause and either explained or accepted as genuine, never simply removed.
- Restudy
- The next scheduled capability study, whose due date should follow from the trigger that prompted the current study, not a fixed calendar interval.
FAQ
Frequently asked questions about statistical process capability study
What is a statistical process capability study based on?+
It is built against ISO 9001 clause 8.5, requiring controlled production and controlled change, using capability indices defined by ISO 22514. Automotive and manufacturing customers typically layer IATF 16949 expectations on top, particularly around study design.
What is the difference between a short-term and a long-term capability study?+
A short-term study uses Cp and Cpk, from within-subgroup variation under near-ideal conditions, usually one operator and one setup. A long-term study uses Pp and Ppk, from overall variation across multiple operators, batches and time, and answers what the customer will actually receive.
Why does the template score multiple operators and multiple batches separately?+
Because a long-term claim built on one operator and one batch is not a long-term study, whatever indices it reports. Scoring representativeness directly makes that gap visible when the study is reviewed, rather than after a customer finds the process performs differently in full production.
What should happen to an outlier in the data?+
It should be investigated, not deleted. A genuine data error can be explained and excluded with that on record; a real but unusual event is exactly what the study exists to find, and removing it understates the risk.
What does a capability below target require immediately?+
Two decisions independent of the corrective action plan: whether full inspection is needed on product made meanwhile, and whether the customer needs notifying. Both are scored fields in the conclusion, and neither should wait on the fix being designed.
Which programme does this template belong to?+
The Statistical Process Control programme, alongside first article inspection, the SPC chart review and the gauge study it depends on, with results feeding change control and the control plan when a shift warrants it.
Keep going
Related templates and programmes
Industries this is written for
Programmes this belongs to
Used together in Statistical Process Control
Maintenance Calibration Record
Records calibration of maintenance instruments such as torque wrenches, pressure gauges and multimeters
Statistical Process Control Log
Records measurements over time so process variation can be seen and acted on before product fails
Process Capability Study
Measures whether a process can reliably hold its specification, using data from a stable run
Manufacturing First Article Inspection
Inspects the first part or pack off a setup against every specified characteristic before the run continues
Statistical Process Control Chart Review
Reviews control charts for a characteristic to see whether the process is stable and capable, not merely in specification
Production Part Approval Record
Records the evidence pack that approves a part or product for series production, covering drawings, capability, measurement and samples
More in Manufacturing Quality
Manufacturing First Article Inspection
Inspects the first part or pack off a setup against every specified characteristic before the run continues
Statistical Process Control Chart Review
Reviews control charts for a characteristic to see whether the process is stable and capable, not merely in specification
Production Part Approval Record
Records the evidence pack that approves a part or product for series production, covering drawings, capability, measurement and samples
Rework Instruction Record
Sets out how a specific batch is to be reworked, what checks apply and who authorised it
Customer Specific Requirement Review
Reviews requirements a customer imposes beyond the standard specification, and whether the site can meet them
Written and reviewed by
Siddarth Singh
Founder & Chief Executive Officer, Knowella
Certified Safety Professional and industrial and systems engineer with more than a decade inside food supply chain, freight and manufacturing operations. This page was written against the current text of the standards it cites, not against secondary summaries of them.
- Certified Safety Professional (CSP), Board of Certified Safety Professionals
- MBA, University of Chicago Booth School of Business
- MS and BS, The Ohio State University, Industrial and Systems Engineering
- Six Sigma Black Belt
Sources and last review. Reviewed 16 August 2026 against:
- ISO 9001:2015 clause 8.5, production and service provision
- ISO 22514-1 and 22514-2, statistical methods in process management, capability and performance
- IATF 16949, clauses 9.1.1.1 and 8.5.1.1
- AIAG Statistical Process Control reference manual
This page is general guidance, not legal advice. Confirm requirements with your jurisdiction’s regulator.