CSSYB key terms

A disciplined, data-driven approach to improving processes by reducing variation and eliminating defects, with the goal of no more than 3.4 defects per million opportunities.

The five-phase improvement cycle - Define, Measure, Analyze, Improve, Control - used to solve problems in existing processes that fall short of customer requirements.

Design for Six Sigma applies when a product or process does not yet exist; DMADV stands for Define, Measure, Analyze, Design, and Verify, and aims to build quality in from the start.

A normalized defect metric that scales the number of defects found to one million opportunities, allowing processes of different sizes and complexity to be compared on a single scale.

A shorthand statement of the Six Sigma premise that outcomes (Y) result from process inputs and causes (x); improvement comes from finding and changing the influential x's.

The customer needs, expectations, and feedback gathered through interviews, surveys, complaints, and observation; it is the starting point for defining what quality means for the project.

A measurable characteristic of a product or process that is essential to satisfying the customer, translating vague customer wants into specifications the project team can measure and improve.

Work the customer would willingly pay for because it changes the product or service in a way the customer values, and it is performed correctly the first time.

The eight categories of non-value-adding activity: defects, overproduction, waiting, non-utilized talent, transportation, inventory, motion, and extra processing, often remembered by the acronym TIMWOODS.

A senior manager who authorizes a Six Sigma project, secures resources, removes organizational barriers, and holds the team accountable for delivering the intended business results.

A formal document that authorizes a project and states its business case, problem, goal, scope, team, schedule, and expected benefits; it serves as the team's contract with management.

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

A specific, measurable target for the project that states the improvement to be achieved, by when, and how it will be verified; it is derived directly from the problem statement.

The justification for doing the project, describing the financial and strategic benefit to the organization and the consequences of failing to act on the problem.

A high-level map showing the Suppliers, Inputs, Process, Outputs, and Customers of a process, used to agree on scope and boundaries before detailed analysis begins.

Identifying everyone affected by or able to influence the project and assessing their interest and influence so the team can plan communication and build support.

A visual diagram of the sequence of steps, decisions, and handoffs in a process, used to expose complexity, rework loops, and steps that add no value.

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

Measurement data that can take any value within a range, limited mainly by the precision of the measuring device, such as time, weight, length, or temperature.

Data that can take only specific countable values, such as pass or fail, number of defects, or number of complaints; also called attribute or categorical data.

A structured form for recording how often events occur, designed so data are collected consistently and can be tallied easily by anyone at the point where the process runs.

A bar chart of continuous data grouped into intervals that shows the shape, center, and spread of a distribution and reveals unusual features such as multiple peaks or skew.

A study that quantifies how much observed variation comes from the measurement system itself - repeatability and reproducibility - rather than from the process being measured.

A comparison of a process's spread and centering against its specification limits, expressed through indices such as Cp and Cpk that show how well requirements can be met.

A structured investigation to find the underlying process conditions that produce a problem, so corrective action removes the source of the problem rather than its symptom.

A team tool that branches the possible causes of a problem into categories such as people, machine, method, material, measurement, and environment; also called a fishbone or Ishikawa diagram.

A simple technique of repeatedly asking why a problem occurs, with each answer prompting the next question, until the fundamental cause is reached; typically about five rounds are needed.

A plot of paired values for two variables that shows whether they move together and roughly how strong the relationship is; it demonstrates association, not proof of causation.

A bar chart of problems ordered by frequency with a cumulative percentage line, used to separate the vital few causes from the trivial many according to the 80/20 principle.

A structured table that lists how a process or product could fail, rates severity, occurrence, and detection, and prioritizes actions using a risk priority number.

A group technique for generating a large number of ideas without judging them, encouraging free thinking first and organizing and evaluating the list afterwards.

Designing a process, device, or check so that an error cannot be made or cannot pass to the next step, removing reliance on operator attention and memory.

A philosophy and practice of continuous, incremental improvement carried out by the people who do the work, often through short focused events that test changes quickly.

A workplace organization method - sort, set in order, shine, standardize, and sustain - that removes clutter, reduces wasted motion, and makes abnormal conditions easy to see.

A limited trial of a proposed change on a small scale to confirm that it works, refine the details, and build evidence before full implementation across the process.

A document that specifies, for each process characteristic, what is monitored, the specification, the measurement method, the sample size and frequency, and the reaction when limits are exceeded.

A time-ordered plot of data with statistically calculated control limits, used to distinguish normal common-cause variation from special-cause signals that require investigation.

A documented, agreed description of the safest and most effective way to perform each task, including sequence, cycle time, and required materials, forming the baseline for further improvement.

Predetermined actions stating who does what when a control chart or monitoring point signals an out-of-control condition, so the process is corrected promptly and consistently.

The person accountable for the ongoing performance of a process after the project ends; this role monitors controls, maintains standard work, and authorizes further changes.