C-chart¶

Monitor the count of nonconformities in constant-size inspection units against Poisson-based center and control limits.

Version: v1 · 2026-08-30 · History
Domain-specific #: 1424
Origin domain: statistics
Subdomain: attribute control charts
Aliases: C control chart, Count-of-nonconformities chart

Core Idea¶

A C-chart is an attribute control chart for a sequence of counts of nonconformities observed in inspection units of constant opportunity or size. A single unit can contain more than one nonconformity, so the observed variable is a defect count rather than the number or fraction of defective units. Under the conventional Poisson model, the in-control center is the mean count \(\bar c\), and three-sigma limits are commonly \(\bar c \pm 3\sqrt{\bar c}\), with a negative lower limit truncated to zero.^[1]

Each comparable inspection interval yields a count \(c_i\). Baseline data judged representative of stable common-cause operation estimate \(\bar c\). The chart places counts in temporal order and marks a center line and calculated limits; a point beyond a limit or a declared run-rule pattern triggers investigation of a possible assignable cause. The limits describe expected process variation under the model, not engineering tolerance or customer acceptability. If exposure varies, normalizing counts by opportunity and using a U-chart is the constitutive change.^[2]

The chart's Poisson assumptions include counts on comparable units and a variance approximately equal to the mean. Overdispersion, clustering, serial dependence, changing definitions, rare enormous opportunities, or estimation from contaminated data can distort false-alarm rates. An NP-chart counts nonconforming units in a fixed sample; a C-chart counts nonconformities and can record several per unit. The method monitors stability rather than proving causation or guaranteeing conformance to specification limits.^[3]

Structural Signature¶

Inspection unit. A constant-size area, item, interval, or opportunity frame makes counts comparable.
Nonconformity definition. A stable operational rule determines what events enter the count.
Count sequence. Ordered observations preserve time and expose shifts or unusual points.
Baseline mean. A stable reference period estimates the in-control expected count \(\bar c\).
Poisson variance model. The expected variance supplies the square-root scale for limits.
Control limits. Calculated thresholds distinguish statistically unusual counts from common variation.
Signal rule. Points or patterns are interpreted under a declared alarm convention.
Investigation response. A signal initiates contextual diagnosis rather than automatically naming a cause.

What It Is Not¶

Not a U-chart. A U-chart handles nonconformities per variable-size unit or opportunity base.
Not an NP-chart. An NP-chart counts defective units, each classified once, rather than multiple defects.
Not a P-chart. A P-chart monitors proportions and allows sample-size changes.
Not specification limits. Control limits estimate process variation and do not encode product requirements.
Not a causal diagnosis. An alarm says the model is strained; it does not identify the generator.
Not a histogram. Temporal order and sequential limits are essential to process monitoring.

Scope of Application¶

The abstraction is literal wherever practitioners can identify the same constitutive roles, apply the same boundary tests, and obtain the same kind of output. The following habitats are uses of C-chart itself, not metaphors based only on resemblance.

Manufacturing inspection. Tracking surface flaws or assembly nonconformities per constant item batch.
Document quality. Monitoring error counts per constant-length or constant-opportunity record.
Service processes. Counting defined incidents per comparable operating interval.
Baseline establishment. Estimating an in-control center from screened historical observations.
Ongoing surveillance. Detecting shifts after a process has entered routine operation.
Chart selection. Choosing C only when both event type and exposure frame satisfy its count assumptions.

Clarity¶

A clear account of C-chart must preserve the recognition invariant stated in the Core Idea rather than rely on the title alone. Define one nonconformity and state whether several may occur in one unit. Demonstrate that inspection opportunities are effectively constant. Report the baseline interval, mean estimate, dispersion check, and signal rule. Keep control limits, specification limits, and response procedures conceptually separate. These declarations are not editorial extras: each changes what observations count, which transformations are licensed, and what conclusion can be drawn. A reader should be able to reconstruct the input, the operative rule, the output, and at least one defeater from the account without consulting an implementation or guessing an unstated convention.

Manages Complexity¶

C-chart manages complexity by replacing a diffuse field of observations or possible operations with a bounded role structure: inspection unit supplies a constant-size area, item, interval, or opportunity frame makes counts comparable.; nonconformity definition supplies a stable operational rule determines what events enter the count.; count sequence supplies ordered observations preserve time and expose shifts or unusual points.; baseline mean supplies a stable reference period estimates the in-control expected count \(\bar c\).; poisson variance model supplies the expected variance supplies the square-root scale for limits.. The compression is useful because it localizes disagreement. One can ask whether the input was properly formed, whether a constitutive relation held, whether an alternative explanation defeats the inference, or whether the output was overinterpreted. The same compression can mislead when its discarded detail is exactly what the decision requires. A reference-grade use therefore reports both the invariant retained and the information intentionally lost.

Abstract Reasoning¶

Specify the unit and count rule before reviewing outcome values.
Check that exposure and detection opportunity remain comparable across observations.
Screen the baseline for obvious special causes without erasing inconvenient variation silently.
Estimate \(\bar c\) and evaluate whether Poisson dispersion is plausible.
Compute and label center and control limits, truncating only the impossible negative bound.
Apply the declared point and run rules to the ordered sequence.
Investigate signals contextually and revise the chart only after a documented process change.
Test the candidate interpretation against the nearest named confusable rather than accepting a shared surface feature.
State the conclusion at the same scope as the source conditions, and retain uncertainty or nonuniqueness where the construct does not remove it.

Knowledge Transfer¶

The strict upward abstraction is Quality Control. C-chart instantiates Quality Control because it repeatedly compares observed process counts with a stable reference model to detect departures requiring investigation. Within attribute control charts, the full mechanism transfers literally when the same roles and boundary tests recur. Beyond that domain, only the parent-level skeleton should travel. Reusing the label C-chart after removing its constitutive vocabulary would hide a change of mechanism behind an analogy. The honest transfer rule is therefore two-stage: recognize the domain-specific pattern first, then lift only the parent relation that remains invariant under a substrate change.

Examples¶

Canonical¶

Twenty equal-area panels are inspected using one defect definition, producing a stable baseline mean of \(\bar c=4\). Conventional three-sigma limits are \(4\pm 6\), so the lower limit becomes zero and the upper limit ten. A later panel with eleven nonconformities signals unusual variation. The chart calls for investigation; it does not prove which machine condition produced the count.

Mapped back: input and conventions → constitutive role test → bounded output → explicit interpretation and defeater check.

Applied / In Practice¶

A support center counts documentation errors each day, but daily case volume doubles on some days. Plotting raw counts on a C-chart would confuse workload with process change. The analyst instead defines an opportunity base and considers a U-chart. Rejecting the C-chart here is a correct application of its abstraction boundary, not a failure of control-chart reasoning.

Mapped back: field observation or problem → candidate recognition → confusable and limit checks → appropriately scoped conclusion.

Structural Tensions¶

T1: Simple limits versus model fit. Poisson square-root limits are transparent but can be miscalibrated under overdispersion. Diagnostic: Does baseline variance materially exceed or fall below its mean?
T2: Constant unit versus changing opportunity. Equal labels can hide different exposure amounts. Diagnostic: Would two units with the same process rate have the same expected count?
T3: Signal versus explanation. A rare point draws attention without naming its cause. Diagnostic: What process evidence discriminates an assignable cause from model misspecification?
T4: Retrospective cleaning versus honest baseline. Removing points can manufacture apparent stability. Diagnostic: Is every exclusion tied to a documented external cause?
T5: Control versus conformance. A stable process may consistently miss specifications. Diagnostic: Are control limits being confused with customer tolerances?
T6: Autonomous chart versus Quality Control. Quality Control is general; this chart fixes a count model and constant unit. Diagnostic: Would the method remain a C-chart without countable repeated nonconformities and Poisson limits?

Structural–Framed Character¶

The C-chart is quantitative and institutional: its probability model is mathematical, while the defect definition, baseline, and investigation response are governed by quality practice. The five framing criteria point in a consistent direction. Evaluative weight is limited to whether the defining conditions are met, not whether the outcome is desirable. Human practice matters to the extent that experts choose conventions, instruments, or reporting thresholds, but those choices do not make every verdict arbitrary. Institutional history explains the name and standard use; it does not replace the recognition rule. The operative vocabulary travels within the home field and closely adjacent subfields, while transfer farther away requires translation to the parent prime. Thus recognition remains disciplined even where interpretation is defeasible.

Structural Core vs. Domain Accent¶

What is skeletal. C-chart instantiates Quality Control because it repeatedly compares observed process counts with a stable reference model to detect departures requiring investigation. This is the part that can be expressed without the candidate's specialist nouns.

What is domain-bound. The domain accent is a count of multiple nonconformities, constant inspection opportunity, Poisson mean–variance structure, and sequential control limits. Remove those elements and the result is no longer C-chart; it is only the parent relation or a loose analogy.

Why this does not clear the prime bar. The name does not recur with unchanged diagnostics across three independent domains. What transfers is already represented by prime:quality_control. The candidate remains autonomous because its in-domain recognition rule, failure modes, and consequences are stable, but its vocabulary and interventions do not float free of the home substrate.

C-chart instantiates Quality Control because it repeatedly compares observed process counts with a stable reference model to detect departures requiring investigation.

The prospective workspace queue contains one strict upward edge to prime:quality_control. No live DAG mutation is authorized.

Relationships to Other Abstractions¶

Current abstraction C-chart Domain-specific

Parents (1) — more general patterns this builds on

C-chart is a kind of Quality Control Prime

C-chart instantiates Quality Control because it repeatedly compares observed process counts with a stable reference model to detect departures requiring investigation.

Hierarchy paths (2) — routes to 2 parentless roots

C-chart → Quality Control → Verification → Evaluation → Comparison → Self Checking

Show alternative path (1)

Neighborhood in Abstraction Space¶

C-chart sits in a sparse region of the domain-specific corpus (93^rd percentile for distinctiveness): few abstractions share its structure, so a faithful description tends to retrieve it precisely.

Family — Statistical Process Control (14 abstractions)

Nearest neighbors

Np-chart — 0.80
Natural Process Variation — 0.80
P-chart — 0.78
Effective Data Transfer Rate — 0.77
U-chart — 0.76

Computed from structural-signature embeddings · 2026-09-08

Not to Be Confused With¶

U-chart. Normalizes defects by varying opportunity rather than requiring a constant unit.
NP-chart. Counts nonconforming items in a fixed sample, not multiple defects.
P-chart. Tracks a nonconforming fraction and can vary sample size.
X-bar chart. Monitors averages of continuous measurements.
Specification limit. Expresses an external requirement rather than expected process variation.
Poisson regression. Models count covariates but is not inherently a sequential control display.

References¶

[1] NIST/SEMATECH. e-Handbook of Statistical Methods, §6.3.3, ‘What Are Attributes Control Charts?’ https://www.itl.nist.gov/div898/handbook/pmc/section3/pmc33.htm registry ↩

[2] NIST/SEMATECH. e-Handbook of Statistical Methods, §6.3.3.1, ‘Counts Control Charts.’ https://www.itl.nist.gov/div898/handbook/pmc/section3/pmc331.htm registry ↩

[3] International Organization for Standardization. (2023). ISO 7870-2:2023, Control charts—Part 2: Shewhart control charts. https://www.iso.org/standard/76802.html registry ↩