1-Sample t-Test: Compares the difference between the mean and a target value
2-Sample t-Test: A statistical test used to detect differences between means of two populations.
5S’s: ordered actions used to achieve a clean, well-organized workplace; Sort, Simplify, Sanitize, Standardize, Sustain
6M’s: categories representing the sources of variation (Man, Method, Material, Measurement, Mother Nature, Machine)
7 Wastes: Defects, Over Production, Transportation, Waiting, Inventory/Storage, Motion, Processing
ANOVA: tests to see if the difference between the means of each level is significantly more than the variation within each level. 1-way ANOVA is used when two or more means (a single factor with three or more levels) must be compared with each other.
Buffer Stock: Maintaining some small portion of finished products/goods to temporarily satisfy variations in demand.
C-Chart: Control chart for counting defects (Sample size is same) for discrete data
Capability Maturity Matrix (CMM): A framework for assessing organizational capability in terms of various characteristics (e.g. lean practices). Level 1 normally represents rudimentary capability and level 5 represents world-class industry leader capability.
Common Cause: used to refer to variation that happens in the same way from worker to worker, hour to hour, lot to lot, etc.; on a control chart, common causes by definition always fall within control limits. See also Special Cause.
Confidence Intervals: Confidence intervals help us state the likely range of the population parameter
Confidence Level: The probability that a random variable x lies within a defined interval.
Confidence Limits: The two values that define the confidence interval.
Continuous / Variable data: Any variable measured on a continuum or scale that can be infinitely divided into recognizable parts includes time, dollars, size, weight, temperature, and speed. Any metric that can be continuously divided by 2 and the metric still makes sense is a continuous metric.
Control Chart: a graphical tool for monitoring a process and/or for determining where variation lies; control charts show results over time, with +/- 3σ boundaries representing the upper and lower control limits (UCL/LCLs)
Control Methods: standard methods implemented during the “control” phase of the DMAIC process include: fix, minimize, standardize, measure and monitor, communicate and audit
Controllable Inputs: input variables (x’s) that can be changed to see the effect on Process Output Variables (y’s); sometimes called “Knob” Variables
Cp: Ratio of total variation allowed by the specification tolerance to the total variation actually measured from the process
Cpk: The minimum value of CPU or CPL where K is the selected statistic (is the process centered within the tolerance)
Critical Chain Project Management (CCPM): A process to plan and execute projects, combining the critical chain approach with traditional project management methodology. Addresses the root causes of why projects are routinely late and over budget.
Critical Characteristics (in FMEA): those items which affect customer safety and/or could result in non-compliance to regulations and thus require controls to ensure 100% compliance; these are usually process “settings” such as temperature, time, speed, etc..
Critical Inputs: x’s that the tools (FMEA, DOE, SPC, etc..) and significant process knowledge have proved to have a major impact on the variability of the y’s
Critical Path: Not considering the resource constraint, it's the longest set of dependent activities within a project.
Critical-to-Quality Tree (CTQ): A critical-to-quality tree enables you to take a "soft" customer need and break it down into more tangible customer requirements.
Current Controls (in FMEA): are the mechanisms (for both design and process) which prevent the cause of the failure mode from occurring, or detect the failure mode, should it occur, before the product reaches your “customer” for example, current controls include SPC, inspections, written procedures, training, preventive maintenance and all other activities that ensure a smooth-running process
Current State: Part of the Value Stream Analysis, this depicts the current or "as is" process and how it functions in terms of operations, materiel, and information flow.
Cycle Time (C/T): time that elapses between one product exiting the process to the next product coming out or the time it takes to complete a process step; typically the value-added time.
Data Collection Plan: is used to identify the methods for data gathering. It ensures clarity and consistency in data gathering and sampling
Defect: any error or nonconformance which adds cost without adding value
Defective: a part that is not acceptable due to one or more defects. A defective unit can have more than one defect.
Defect rate (% bad): calculated as the #defective / # of opportunities
Detection (in FMEA): an assessment of the likelihood that the current controls (design and process) will detect the cause (process weakness) of the failure mode, should it occur, thus preventing it from reaching your customer; the customer, in this case, could be the next operation, subsequent operations, or the end-user
Discrete / Attribute data: A count, proportion, or percentage of a characteristic or category. Service process data is often discrete. Often binomial as in pass/fail, on-time/late, etc
Discrimination (in MSE): the technological ability of the measurement system to adequately differentiate between measured values for a selected parameter
DMAIC: the standard framework for Lean Six Sigma projects/implementations, which stands for “Define, Measure, Analyze, Improve, Control”
DOE: Design of Experiment - A DOE is a planned set of tests on the response variable(s) (KPOVs) with one or more inputs (factors) (PIVs) each at two or more settings (levels) which to determine if any factor is significant and develop predictive models.
DPMO: Defects Per Million Opportunities
DPO: Defect Per Opportunity
DPU: Defects Per Unit
Error-proofing: A technique of preventing production errors by designing the process, equipment, and tools so that an operation literally cannot be performed incorrectly (see poke-yoke).
Experimentation: the manipulation of controllable factors (independent variables) at different levels to see their effect on some response (dependent variable); common methods include: trial-and-error, one-factor-at-a-time, full factorial, and fractional factorial
External Work: set-up activities which can be performed while the machine (or process) is running; See also Internal Work
Failure Modes and Effects Analysis (FMEA): a tool used to assess the potential failure modes of a process, and the likely effects of potential failures; developed by NASA to eliminate failures during the planning phase of a project
Flow Production: continuous movement of the product or service from start to finish without interruption or storage with the intent to eliminate batch sizing and produce at the smallest possible increment
FPY: First Pass Yield; the measure typically referred to as “yield”; the total number of parts that are accepted divided by the total number of parts that were started
Future State: A vision of the optimum operating environment with new/improved processes in place.
Gage R&R: Gage Repeatability and Reproducibility, a measure of variation arising from the use of a specific measurement device and/or the operator of the measurement device
Gap Analysis: An analysis that compares current performance to desired performance so solutions can be found to reduce the difference (close the gap).
Hidden Factory: unintended steps, tasks, or rework in a process
Hypothesis testing: using relatively small samples are used to answer questions about population parameters (inferential statistics). Means hypothesis testing roadmap; Variance hypothesis testing roadmap
I-MR chart: Individuals Moving Range chart for continuous data
ICC: IntraClass Correlation, an attribute measurement system evaluation
Internal Work: set-up activities that requires the machine (or process) be stopped (see external work)
Kaizen: a Japanese term for continuous improvement
Kanban: a Japanese word for “signal”; kanban systems are pull systems, which replenish materials only as they are used
Kappa: an attribute measurement system which compares how well a judge repeats him/herself and/or how well judges agree
Lead Time: average time to manufacture and deliver a product or service, from order receipt to delivery to the customer
Mean: parameter used to characterize the “process location” or “center”; an average of all data points in sample or population
Measurement Error: variation in measurement which can be attributed to variation in the item being measured or to the measurement system itself
Median: A measure of central tendency. It is the value that splits the data into two equal groups, one with values greater than or equal to the median and one with values less than or equal to the median.
Mixed Effects Model: Contains elements of both the fixed and random-effects models.
Mode: A measure of location, defined as the most frequently occurring data value.
Moving Range Chart: a chart used when control charting individual data; the moving range is used to estimate the short-term variation which is then compared to the individual value variation
MSE: Measurement System Evaluation; identifies and quantifies the different sources of variation that affect a measurement system
NEM: Numerical Evaluation of Metrics, evaluation of control chart data to: 1) determine common or special cause or 2) determine where the majority of variation lies; even though NEM uses control charts, it is different from SPC which is focused on ‘monitoring’ a process
Noise Inputs: input variables that impact the y’s but are uncontrollable, difficult, or too costly to control; example: environmental variables such as humidity, ambient temperature, etc..
Non-Value Added: anything that does not transform the form, fit and or function of a product or service as defined by the customer the first time
Normal Probability Distribution: A continuous probability distribution shaped like a bell-shaped curve. The mean, median and mode are not different. It is fully defined by the mean m and the standard deviations.
Occurrence (in FMEA): an assessment of the likelihood that a particular cause will happen and result in the failure mode
OTED: One Touch Exchange of Dies; a set-up performed by one touch
Overall Equipment Effectiveness (OEE): Framework for measuring the efficiency and effectiveness of a process, by breaking it down into three constituent components (the OEE Factors).
Overall Equipment Effectiveness Factors: The three constituent elements of OEE (Availability, Performance, and Quality).
Overall Equipment Effectiveness Losses: The three types of productivity loss associated with the three OEE Factors (Down Time Loss, Speed Loss, and Quality Loss).
Pareto Chart: the Pareto principle says that 80% of the problems will arise from 20% of the causes; a Pareto chart tests and/or illustrates this relationship by sorting and displaying metrics in a descending order chart
PMAP: Process Map (not a process flow which does not contain inputs and outputs)
PPM: Parts Per Million (defective)
Process Capability Index: comparison of the Voice of the Process to the Voice of the Customer requirements
Process Dispersion: the standard deviation of f(x), symbolized by “σ”, the Greek letter known as “sigma”
Process Input Variables: process inputs can be categorized as controllable, critical, noise, or standard operating procedures
Process Location: the mean or average of f(x), symbolized by “μ”, the Greek letter known as “mu”
Process yield (% good): calculated as # of good units / # of opportunities
Profound Knowledge: The philosophy espoused by Dr. Deming that centers on the theories of systems, variation, knowledge, and psychology—and their interrelationships.
Pull Material System: a method of controlling the flow of resources by replacing what has been consumed
Pure Waste: weak process that adds no value and is not required by the customer
Push System: a system where work is performed to a schedule or plan and sent to the next process without regard to customer demand from that process.
Queue Time: time a product waits between the value-added process steps; if inventory exists between process steps, can be approximated by dividing the inventory by customer demand for a time frame
R Chart: Range Chart, also called the “within” chart as the points on the chart represent within group variation; this control chart is , used to display change within subgroups; the R chart for a set of data must be “in control”, more technically defined as “stable’, to be able to use an X-bar chart based on the same data
Rapid Improvement Event (RIE): A short-term, high-intensity effort to address a specific problem also called simply an Event. The focus is typically a week, though the preparation normally begins several weeks in front and follow-up continues after. Also know as Rapid Improvement Workshop, Kaizen Event, Kaizen Blitz and etcetera.
Repeatability (in MSE): variation between successive measurements of the same part or characteristic, by the same person, using the same instrument; also known as test-retest error or operator uncertainty.
Reproducibility (in MSE): the difference in the average of measurements made by different persons measuring the same part or characteristic
Required Waste: process that adds no value to the product, but is required by the current process
Rework: any work that must be done to correct product or process defects
Risk Priority Number (RPN): used in an FMEA to assess the relative priority of potential solutions; calculated as “Severity x Occurrence x Detectability”
Root Cause: the source of a problem which, if eliminated, would prevent recurrence of the issue
RPN: see Risk Priority Number
RTY: Rolled Throughput Yield; the probability that a part will make it through multiple process steps without a defect
Run Chart (Trend chart): is a graph that shows the changes in a process measure over time. It can help you to recognize patterns of performance in a process.
Sample: set of elements drawn from and analyzed to estimate the characteristics of a population
Scatter Diagram: A scatter diagram is a graph that can reveal a possible relationship between two variables. Use it to identify possible causes of problems and to recognize how one important variable might be related to another.
SCOR: Supply Chain Operations Reference; a methodology that extends the scope of the value stream, starting with your supplier’s supplier and continuing to your customer’s customer
Segmentation or Stratification: is a process used to divide a large group into smaller, logical categories (factors)for analysis; these factors can help you stratify the data to find special causes
Setup Time: the elapsed time from the production of the last good product to the production of the first good product; associated with changing the process from one product to another
Severity (in FMEA): an assessment of how serious the effect of the potential failure mode is on the customer; the customer in this case could be the next operation, subsequent operations, or the end-user
Sigma (Excel function): account for shift and drift if necessary by adding 1.5; or see Reference Chart in the appendix
Sigma: 18th letter of the greek alphabet; mathematically understood to represent standard deviation
Significant Characteristics (in FMEA): those items which require SPC and quality planning to ensure acceptable levels of capability
SIPOC: boundary-scoping tool used in the design phase to identify Suppliers, Inputs, Process, Outputs, and Customers
Six Big Losses: Six categories of productivity losses that are almost universally experienced in manufacturing: Breakdowns, Setup and Adjustments, Small Stops, Reduced Speed, Startup Rejects, and Production Rejects.
Six Sigma: philosophy focuses on defect prevention through the use of statistical tools as opposed to defect detection through inspection
SMED: Single Minute Exchange of Dies; SMED performance levels for the changing of tooling (9 minutes and 59 seconds or less)
SOP: Standard Operating Procedure
SPC Statistical Process Control: the application of statistical techniques to understand and analyze variation in a process. Analyze and characterize the outputs of a process. Maintain a state of statistical control of that process.
Special Cause: variation that is a result of a special circumstance; on a control chart, by definition, special causes always fall outside control limits
Standard Deviation: parameter used to characterize the “process dispersion”
Standard Operating Procedures: procedures that describe how the process is run and identify certain factors to monitor and maintain; standard procedure for running the process
Standard work: Standardized work is the detailed and timed description of the best possible succession of basic tasks to complete a job
Stretch Goals: goals and objectives that require employees to achieve more than normally thought possible
Subgrouping: a method of organizing (classify, stratify, group, etc..) data from a process to ensure the greatest similarity among the data in each subgroup and the greatest difference among the data in different subgroups. Groups need to be selected rationally, i.e. you have a belief that the groups are different and important.
Subject Matter Expert (SME): A recognized expert in a given functional area or subject.
Supply Chain Management (SCM): Proactively directing the movement of materials and supplies from the source to delivery to supported organizations and personnel (customers). SCM aims to reduce operating costs, lead times, and inventory footprint and increase the speed of delivery, product availability, and customer satisfaction.
Systems Thinking: Systems thinking focuses on how the component parts of a complex system interact to produce core outcomes.
Takt Time: “takt” is German for the word metronome; synchronizes the pace of the process to match the pace of customer demand; calculated as available time divided by customer demand
Tampering: Also known as “firefighting”. Using emergency fixes for process problems without eliminating the root cause or analyzing the process to bring it into control and improve it in an informed manner; managing by crisis instead of structured problem-solving.
TDU: total defects per unit, the sum of all the DPUs for all parts in an assembly or all process steps in a process flow diagram
Theory of Constraints (TOC): TOC provides a set of analytical tools and concepts for analyzing and improving complex interrelated processes and systems to improve overall system functioning and capability.
Thought Process Map (TMAP): project strategy-planning tool
Throughput Time: Cycle Time + Queue Time; actual time for a product to move through a production process
Upper Control Limit (UCL) / Lower Control Limit (LCL): control limits that are calculated from time-series process data; they are also referred to as the voice of the process
Upper Spec Limit (USL)/Lower Spec Limit (LSL): customer supplied specification limits or tolerance for a process output; they are also referred to as the voice of the customer.
Value Stream Map (VSM): a map of the product, information, and material flows of a process; with value-added and non-value-added data gathered and displayed for each step
Value: a capability provided to a customer at the right time at an appropriate price, as defined in each case by the voice of the customer
Value-added: transforms the form, fit and or function of a product or service as defined by the customer the first time
Visual Control: indicators that allow employees to detect visually whether a process is in or out of control; examples include temperature gauges, control charts, tool boards, etc..
Visual Management: Tools which allow management to quickly visually determine whether a process is proceeding as expected, or is in trouble (e.g., scorecard software).
Voice of Customer (VOC): customer requirements/specifications of the process (see Upper Spec Limit)
Voice of Process (VOP): natural variability of a process typically characterized by a normal distribution (see Upper Control Limits)
VSM: see Value Stream Map
Waste: anything that adds cost without producing a corresponding benefit
What's In It For Me (WIIFM): A key concept in change management, helps employees see why the change is important and can actually help them.
X: the inputs to a process (inputs for individual process steps/tasks are identified using the lower-case “x”)
X-Bar Chart: an averages chart, also called the “between” chart because the points represent variation between groups; this control chart examines the average of samples in a subgroup
Y = f(x): Function used to describe a process whereby x’s represent all the inputs to a process (factors) and Y represents the output of the process (response)
Y: the output of a process (outputs of individual process steps/tasks are identified using the lower-case “y”)
Z Distribution: Called a “Standard Normal”. It is completely described once the mean and standard deviation are known. Any normal distribution can be converted to a standard normal distribution by a Z-transformation: Z = (Xi-mean)/standard deviation. It is used to calculate Sigma, displaying residuals, and understanding variation.