ICBB key terms

The structured collection of customer needs, expectations, and complaints gathered through interviews, surveys, and complaint data, then translated into measurable requirements that a Six Sigma project can target.

A measurable characteristic of a product or service that directly reflects an important customer requirement, derived from VOC data and used to set project metrics and specification limits.

A high-level process map showing Suppliers, Inputs, Process steps, Outputs, and Customers, used at project definition to agree on scope and boundaries before detailed mapping begins.

A formal document authorizing a Six Sigma project that states the problem, goal, scope, business case, team, milestones, and expected financial benefit, and is signed by the project sponsor.

A concise description of the gap between current and desired performance, including what, where, when, and how much, without stating a cause or a solution.

A specific, measurable, time-bound target for improving the metric named in the problem statement, expressed as a direction, amount, and deadline.

A goal written to be Specific, Measurable, Achievable, Relevant, and Time-bound, which helps teams avoid vague aims such as improve quality or reduce waste.

A senior manager who provides resources, removes organizational barriers, approves the charter, and is accountable for realizing the project's financial and operational benefits.

The process of identifying everyone affected by or able to influence a project, then assessing their interest and power to plan appropriate communication and involvement.

The total cost incurred because work is done incorrectly, including internal and external failures, appraisal, and prevention costs, often used to size the business case for improvement.

A precise, unambiguous description of how a characteristic is measured, including the instrument, procedure, and decision criteria, so different people obtain consistent results.

The classification of data as continuous (measured on a scale, such as time or weight) or discrete (counted or categorized, such as defects or pass/fail), which determines the statistical tools that apply.

A set of studies that quantifies variation contributed by the measurement system itself, separating repeatability, reproducibility, bias, linearity, and stability from true process variation.

A study that estimates how much observed variation comes from repeatability (same operator, same part) and reproducibility (different operators), usually expressed as a percentage of total variation.

The variation observed when one operator measures the same item multiple times with the same instrument under identical conditions, reflecting the equipment and method consistency.

The variation in measurements introduced by differences between operators or setups when measuring the same items, reflecting how consistently people apply the measurement procedure.

A study for discrete or subjective judgments that assesses agreement of each appraiser with themselves, with other appraisers, and with a known standard, reported as percentages or kappa values.

Indices comparing specification width and centering to process variation; Cp ignores centering while Cpk accounts for how far the mean sits from the nearest specification limit.

The upper and lower bounds on a characteristic set by the customer or design, defining acceptable output; they are not derived from the process's own observed variation.

Capability-like indices calculated using the overall standard deviation of all data rather than within-subgroup variation, so they reflect long-term performance including shifts and drift.

A time-ordered plot of a process metric with a center line and statistically derived limits, used to distinguish common-cause variation from special-cause signals.

The routine, random variation inherent in a stable process, produced by many small interacting sources; reducing it requires changing the process itself, not reacting to individual points.

Variation arising from an identifiable, non-routine event such as a bad batch, new operator, or equipment fault, detected by control chart rules and investigated for a root cause.

A structured investigation to find the underlying reasons a defect occurs, using tools such as the 5 Whys, fishbone diagrams, and hypothesis testing, rather than treating symptoms.

A cause-and-effect diagram that organizes potential causes of a problem into branches, commonly people, method, machine, material, measurement, and environment, to guide data collection.

An iterative questioning technique that asks why repeatedly, typically five times, to move from a surface symptom down to an actionable underlying cause.

A statistical procedure that uses sample data to decide whether an observed difference or relationship is larger than expected from chance, reported with a test statistic and p-value.

The probability of observing a result at least as extreme as the sample result if the null hypothesis were true; small values suggest the null hypothesis is unlikely.

Rejecting a true null hypothesis, that is, concluding a real difference or effect exists when it does not; its probability is the significance level alpha chosen for the test.

Failing to reject a false null hypothesis, that is, missing a real difference or effect; its probability is beta, and one minus beta is the test's power.

A modeling technique that fits an equation relating one or more input variables to a continuous output, used to quantify relationships and predict the effect of changing inputs.

A planned approach to varying multiple factors together so their individual and interaction effects on a response can be estimated efficiently and with minimal runs.

A fractional factorial design used early in improvement to test many factors with few runs, identifying the vital few that warrant fuller investigation.

The change in a response caused by changing one factor across its levels, averaged over all levels of the other factors in the experiment.

A situation where the effect of one factor on the response depends on the level of another factor, so the factors cannot be interpreted in isolation.

A mistake-proofing device or design that prevents an error from being made or makes it immediately obvious, rather than relying on operator attention or training.

A continuous improvement practice in which teams make many small, rapid, low-cost changes to a process, often in a focused event lasting several days.

A repeating improvement loop of Plan, Do, Check, and Act that structures experimentation: plan a change, trial it, compare results to the aim, then standardize or adjust.

Documented, agreed-upon methods and sequences for performing a task, including cycle time and work-in-process, forming the baseline that makes further improvement and control possible.

A document listing the process steps, the characteristics to monitor, the measurement method, sample size and frequency, control limits, and the response plan when out-of-control conditions occur.

The probability that a unit passes every process step without a defect, calculated as the product of each step's first-pass yield, revealing hidden rework between steps.

The planned approach to helping people adopt new processes, covering communication, training, sponsorship, resistance handling, and reinforcement so gains are sustained.