PECB Six Sigma Green Belt key terms

A measurable characteristic of a product or service that directly reflects what the customer values, translated from vague customer wants into a specification the process can be measured against.

The structured collection of customer needs, expectations, and complaints gathered through interviews, surveys, and field data, used to define requirements and prioritize improvement projects.

A short authorizing document that states the business case, problem statement, goal, scope, team, milestones, and expected benefits of a Six Sigma project, agreed by the sponsor before work begins.

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

A senior manager who owns the business result of a Six Sigma project, removes organizational barriers, approves resources, and ensures the improved process is sustained after the team disbands.

A high-level process map showing Suppliers, Inputs, Process steps, Outputs, and Customers, used at project definition to agree scope and boundaries without detailing every task.

A structured review of the people and groups affected by or able to influence a project, recording their interest, influence, and likely support so communication and resistance can be planned.

A ranking of problem categories by frequency or cost, based on the observation that a small number of causes usually accounts for most of the effect, used to focus improvement effort.

The money lost through internal failures, external failures, appraisal, and prevention activities; quantifying it helps justify a project in financial terms a sponsor will accept.

A step that changes the form, fit, or function of the product or service in a way the customer would pay for, and that is done right the first time.

Any activity that consumes resources without adding value for the customer; commonly grouped as overproduction, waiting, transport, overprocessing, inventory, motion, and defects.

A diagram of the material and information flow required to deliver a product or service, annotated with cycle times, wait times, and inventory, used to expose delay and non-value-adding steps.

The available production time divided by customer demand for that period; it sets the pace a process must meet to satisfy demand without building excess inventory.

A relationship stating that average work in process equals throughput multiplied by average flow time; useful for predicting how reducing WIP shortens lead time.

A workplace organization method with five steps: sort, set in order, shine, standardize, and sustain; it reduces search time, defects, and safety incidents by making abnormal conditions visible.

A device or design feature that prevents an error from being made or makes it immediately obvious, so defects cannot pass to the next step regardless of operator attention.

A documented, currently best-known sequence of tasks with defined times, WIP, and quality checks, forming the baseline against which changes are evaluated and sustained.

A continuous, incremental improvement approach in which the people doing the work identify and implement small changes, often in a short focused event with rapid implementation.

A repeating improvement loop of plan, do, check, and act, in which a change is tested on a small scale, results are compared with prediction, and the change is standardized or abandoned.

The five-phase improvement roadmap of define, measure, analyze, improve, and control, used for existing processes whose causes of variation are not yet known.

A design-for-Six-Sigma roadmap of define, measure, analyze, design, and verify, used when a new process or product is needed rather than repairing an existing one.

A shorthand stating that an output Y is a function of input and process variables x; Six Sigma work identifies which x variables most influence Y and controls them.

A precise description of how a characteristic is measured, including the instrument, procedure, and decision criteria, so different people classify the same item the same way.

A study quantifying how much observed variation comes from the gauge, the appraiser, and the method, typically reporting repeatability, reproducibility, and their share of total variation.

A specific MSA study that separates repeatability (same appraiser, same part) from reproducibility (different appraisers) and compares combined gauge variation with process or tolerance variation.

Measurements taken on a scale that can be subdivided, such as length, time, or temperature; it carries more information per observation than counting data and enables more powerful tests.

Observations that classify items into categories or count occurrences, such as pass/fail, defect type, or number of complaints; analyzed with proportions and count-based methods.

A documented rule specifying how many units to measure, how and when to select them, and the acceptance criteria, chosen so the data represent the process rather than one convenient shift.

Splitting data into logical subgroups such as machine, shift, operator, or supplier, so patterns hidden in aggregate figures become visible and variation sources can be located.

Indices comparing process spread, and spread plus centering, with the specification width; Cpk accounts for how far the mean sits from the nearer specification limit.

The number of process standard deviations between the process mean and the nearest specification limit, commonly converted to a defects-per-million-opportunities rate for benchmarking.

The probability that a unit passes every step of a process without any defect, calculated by multiplying the first-pass yields of the individual steps.

The upper and lower bounds on a characteristic set by the customer or design, which define acceptability and are independent of the process's own natural spread.

A symmetric bell-shaped probability model described by a mean and standard deviation, in which about 68, 95, and 99.7 percent of values fall within one, two, and three standard deviations.

The result that the distribution of sample averages approaches a normal distribution as sample size grows, regardless of the shape of the underlying population, enabling many statistical tests.

A team tool that branches possible causes of a problem into categories such as people, machine, method, material, measurement, and environment, to structure brainstorming before data collection.

A questioning technique that repeatedly asks why a problem occurred, typically about five times, to move from a symptom to a process-level cause that can be addressed.

The underlying process condition that, if removed, prevents recurrence of a problem; it is verified with data rather than assumed from opinion or a single observed event.

A formal procedure comparing observed sample data with what a stated null hypothesis predicts, producing a p-value used to decide whether an effect is larger than chance variation.

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

Rejecting a null hypothesis that is actually true, also called the producer's risk or alpha; its probability is set in advance, commonly at 0.05.

Failing to reject a null hypothesis that is actually false, also called the consumer's risk or beta; its complement, one minus beta, is the test's power.

The number of observations needed to detect an effect of a given size with chosen alpha and power; larger samples detect smaller differences but cost more to collect.

A planned set of runs in which input factors are varied together according to a statistical structure, so main effects and interactions can be estimated efficiently.

A main effect is the average change in response when one factor changes; an interaction means the effect of one factor depends on the level of another, so they must be read together.

A fractional design that studies many factors in few runs to identify the few that matter, accepting confounding of higher-order effects in exchange for economy.

A document naming the process characteristics to monitor, the measurement method, sample size and frequency, control limits, and the reaction plan when a signal occurs.

Monitoring a process with control charts so that common-cause variation is distinguished from special-cause signals, triggering investigation rather than routine adjustment.

A time-ordered plot of a process measure with a center line and statistically derived limits, used to detect shifts, trends, and outliers that indicate special-cause variation.

Placing performance, status, and standard information where the work happens so that normal and abnormal conditions are recognized at a glance by anyone, without asking.

A technique listing the forces driving a change and the forces restraining it, then weighting them to plan how to strengthen drivers and remove or weaken restraints before implementation.

The time a process step takes to complete one unit from start to finish of that step, excluding waiting; it is compared with takt time to reveal capacity gaps.