CSSC Green Belt flashcards

32 cards. Read the term and the definition here. The deck at the top of this page is optional.

SIPOC diagram

A high-level process map listing Suppliers, Inputs, Process steps, Outputs, and Customers; used in Define to set project scope before any detailed mapping.

CTQ tree

A tool that translates broad Voice of Customer statements into specific, measurable Critical to Quality requirements that a project can target.

Project charter

A document that authorizes a Six Sigma project and defines the problem statement, business case, goal, scope, team, and timeline.

COPQ

Cost of Poor Quality; the money lost to internal failures, external failures, and appraisal, as contrasted with prevention spending.

DMAIC versus DMADV

DMAIC improves an existing process, while DMADV (Design for Six Sigma) creates a new process or product when none exists or a redesign is required.

Kano model

Classifies customer requirements as must-be, performance, or delighter attributes, showing where added features do or do not raise satisfaction.

Gage R&R

A measurement system study quantifying repeatability (equipment) and reproducibility (appraiser) variation; percent GRR under 10 is acceptable, over 30 is not.

DPMO

Defects Per Million Opportunities, computed as defects divided by the product of units and opportunities per unit, then multiplied by one million.

Cp

Process capability ratio equal to the specification width (USL minus LSL) divided by six sigma; it measures potential capability and ignores centering.

Cpk

Capability index equal to the smaller of (USL minus mean) or (mean minus LSL) divided by three sigma; it accounts for an off-center process.

Rolled throughput yield

The product of the first-pass yields of every step in a process; it shows the real probability a unit passes without rework.

Central Limit Theorem

The sampling distribution of the mean approaches normality as sample size grows, so means can be tested even when the population is not normal.

Attribute versus variable data

Variable data is continuous and measured, while attribute data is discrete counts or classifications and needs different charts and hypothesis tests.

Type I error

Rejecting a true null hypothesis; its probability is alpha, the significance level chosen for the test, and it is called the producer's risk.

Type II error

Failing to reject a false null hypothesis; its probability is beta, and the power of a test equals one minus beta.

ANOVA

An analysis of variance test comparing means of three or more groups by splitting total variation into between-group and within-group components.

RPN

Risk Priority Number in FMEA, calculated as Severity times Occurrence times Detection, each scored one to ten; higher values get priority for action.

Chi-square test

A hypothesis test for categorical data that compares observed counts with expected counts to assess independence or goodness of fit.

R-squared

The proportion of variation in the response explained by a regression model; adjusted R-squared penalizes the value when predictors are added.

5 Whys

A root cause technique that repeatedly asks why a problem occurred until the underlying systemic cause rather than a symptom is identified.

Poka-yoke

Error proofing; a device or design change that prevents a mistake from being made or makes the error immediately obvious to the operator.

Full factorial design

A designed experiment testing every combination of factor levels, requiring 2^k runs for k two-level factors and estimating all interactions.

TIMWOOD

The seven lean wastes: Transport, Inventory, Motion, Waiting, Overproduction, Overprocessing, and Defects; adding unused talent gives TIMWOODS.

Takt time

Available production time divided by customer demand; it sets the pace a process must achieve to satisfy the customer.

OEE

Overall Equipment Effectiveness, the product of availability, performance, and quality rates; it expresses how much scheduled time is truly productive.

5S

A workplace organization method with five steps, Sort, Set in order, Shine, Standardize, and Sustain, that removes clutter and exposes abnormal conditions.

Control chart

A time-ordered plot with a center line and upper and lower three-sigma limits, used to separate common-cause from special-cause variation.

X-bar and R chart

A pair of variables control charts tracking subgroup means and subgroup ranges, used for continuous data collected in small subgroups.

p chart

An attribute control chart for the proportion of defective units per subgroup, used when the subgroup sample size varies.

Control plan

A document specifying the metric, monitoring method, frequency, owner, and reaction plan for keeping an improved process in a state of control.

Common cause variation

Inherent random variation from many small sources inside a stable process; it can only be reduced by changing the process itself.

Ppk versus Cpk

Cpk uses within-subgroup sigma for short-term capability, while Ppk uses overall long-term sigma and is typically the smaller of the two values.