Glossary

Affinity diagrams: A diagram that organizes a large number of ideas by finding relationships between them. The information is then gradually structured from the bottom up into meaningful groups. From there you can clearly "see" what you have and then begin your analysis or come to a decision.

Average: The sum of all the values in a set of data divided by the number of values in the set. For example, if the values are 3, 5, 7, and 9, then the average would be 6 (total of all numbers ÷ 4).

Basic flowchart: A flowchart that shows the sequence of steps in a job or process. It can have different levels of detail.

Cause-and-effect diagram: A tool that is used for identifying and organizing possible causes of a problem in a structured format. It is sometimes called a "fishbone" diagram because it looks like the skeleton of a fish.

Centerline: The middle line on a control chart or time plot. It represents either the average or median value of the data.

Check sheets: Forms used to collect data by making tally marks to indicate the number of times something occurs. Check sheets help standardize the data that are collected and the data collection process.

Common cause: A cause of variation that is inherent to the process.

Control chart: A time plot that has a centerline and statistical control limits added. There is an upper control limit and a lower control limit. These limits allow you to quickly detect specific types of changes in a process.

Control limit: A line on a control chart that indicates either the upper or lower range of the common cause variation within a process. It is also called the "statistical control limit".

Cost-added only step: A step in a process that is not essential for producing the product or service. It is carried out because defects, errors, or omissions do occur or because we worry that defects, errors, or omissions might occur.

Cumulative line: A line that can be added to a Pareto chart. It shows how much, or what percentage, of the problem comes from the largest categories.

Data: Clearly defined measurements of characteristics. They are most useful when collected for the purpose of monitoring or improving a process.

Data point: A single measurement, count, or observation.

Deployment flowchart: A flowchart that shows the detailed steps in a process and which people are involved in each step. (Also see relationship flowchart.)

Detailed flowchart: A flowchart that breaks the sequence of steps in a job or a process into detailed substeps.

DMAIC: The methodology used in Six Sigma - define, measure, analyze, improve, and control.

Dot plot: A type of frequency plot that uses dots to show how often values occur in each interval. It shows the shape or distribution of the variation in the data.

80/20 rule: A principle that offers the belief that, in many situations, roughly 80% of the problems are caused by only 20% of the contributors. (Also see Pareto Principle.)

Error proofing: Implementation of fail-safe mechanisms to prevent a process from producing defects. (also known as poka-yoke). The philosophy behind error proofing is that it is not acceptable to make even a very small number of defects, and the only way to achieve a goal is to prevent defects from happening in the first place.

Failure Modes and Effects Analysis (FMEA): A step-by-step approach for identifying all possible failures in a design, process, product, or service. "Failure modes" means the ways, or modes, in which something might fail. Failures are any errors or defects, especially ones that affect the customer, and they can be potential or actual. "Effects analysis" refers to studying the consequences of those failures.

5S System: A tool used in Lean Thinking. The idea is that a messy workplace, desk, or manufacturing cell makes it hard to find things, easier to get distracted, and more prone to accidents or mistakes. The 5S's stand for: sort - sort needed and unneeded items; set in order - arrange things in their proper place; shine - clean up the workplace; standardize - standardize the first three S's; and sustain - make the 5S a part of the job.

5 Step Process for Data Collection: A process that ensures the collection of meaningful data and includes 1) clarification of data collection goals, 2) development of operational definitions, 3) planning for data consistency and stability, 4) beginning data collection, and 5) continuous improvement of measurement systems.

Flowchart: A picture of the sequence of steps in a process. Different steps or actions are represented by boxes or other symbols. Common types of flowcharts include basic, opportunity, and deployment.

Frequency plot: A graphical tool that shows the shape, or distribution, of the data by showing how often different values occur. This picture makes it easier to see what is happening with the data and to identify some types of process problems. (See histogram)

Gantt chart: A Gantt chart is a graphical representation of the duration of tasks against the progression of time. It is a useful tool for planning, scheduling, and monitoring a project's progress.

Graph: A picture of data.

Histogram: A type of frequency plot that uses bars to show how often values occur in each interval. It shows the shape or distribution of the variation in the data.

Horizontal axis: the labeled straight line at the bottom of a graph that runs from left to right, or horizontally. It is also called the X-axis.

Improvement tools: Data collection and analysis tools used to better understand and more quickly solve problems.

Kaizen (Japanese for "improvement"): A Japanese philosophy that focuses on continuous improvement throughout all aspects of life. When applied to the workplace, Kaizen activities continually improve all functions of a business, from manufacturing to management and from the CEO to the assembly line workers. By improving standardized activities and processes, Kaizen aims to eliminate waste. Key elements of Kaizen are quality, effort, involvement of all employees, willingness to change, and communication.

Lean: A process improvement methodology that originated from the Toyota Production System (TPS). It focuses on improving efficiency by removing waste. Lean has come to mean any effort to do more with less and has become interchangeable with the term waste reduction. The five basic steps are identify value, define value stream, determine flow, define pull, and improve process.

Lean Six Sigma: A blended methodology that incorporates both Lean (focus on process flow and waste reduction) and Six Sigma (focus on variation reduction).

Six Sigma uses statistics to understand variation. Lean uses visuals such as flowcharting and value stream mapping to understand the process flow.

Lower control limit (LCL): A value, represented by a line on a control chart, that specifies the lower limit of the results of common cause variation. Data points that fall below this value provide signals of special cause.

Matrix diagram: A graphical tool that shows the connection or correlation between ideas or issues in the form of a table (matrix). A relationship is indicated at each intersection of rows and columns as present or absent.

Mean: The arithmetic average of a list of numbers. (See average) Example: Door to ECG times of 2, 3, 4, 8, 8. The mean time is 5 minutes.

Median: The numerical midpoint of a list of numbers. It is found by rank ordering the values and locating the number that in rank is halfway between the beginning and end. If there are an odd number of values, the median is the middle value; if there is an even number of values, the median is the average of the middle two values. Example: Door-to-ECG times of 2, 3, 4, 8, 8. The mean time is 4 minutes.

Metric: A measured variable that is tracked and can be used to detect errors or variation and make improvements.

Mode: The value that occurs most often in a list of numbers. Example: Door-to-ECG times of 2, 3, 4, 8, 8. The mode time is 8 minutes. A set of data can have more than one mode.

Non-value-added steps: Activities that do not contribute to the product or the process and should therefore be eliminated. Non-value-added steps are waste.

Operational definition: A precise description that tells how to get a value for the characteristic you are trying to measure.

Opportunity flowchart: A detailed flowchart organized to separate steps taken when things go right from steps taken when things go wrong.

Pareto chart: A graphical tool that helps break a big problem down into its parts and then identifies which parts are the most important.

Pareto Principle: A principle that states that, in many situations, a small number of causes account for most of the problems, while most of the causes account for only a few of the problems. (Also see 80/20 rule.)

PDSA (Plan Do Study Act), PDCA (Plan Do Check Act), Shewhart Cycle, Deming Cycle: Titles/acronyms for the four-step model used to bring about process change. It is arguably the most recognized method of identifying an opportunity for change, implementing this change, and then continually monitoring the change for success, thus ensuring continuous improvement. Typically depicted as a circle, it is a recognized method of testing what has been identified as an improvement opportunity.

Process: A series of linked steps necessary to accomplish work. A process turns inputs, such as information or raw materials, into outputs such as products, services, and reports.

Pull: A production system characterized by smaller batches, quick responses to customer demand, and smooth product flow. Originating from the infamous Toyota Corporation, pull production is a process that aims to arrange an organization so that customer preference or orders are what cause materials to be "pulled" through a system.

Range: The difference between the lowest and highest values in a list of numbers. Example: Door-to-ECG times of 2, 3, 4, 8, 8. The range is 6 minutes. The range tells you something about how spread out the data is. Data with large ranges tend to be more spread out.

Relationship flowchart: A flowchart that shows the detailed steps in a process and who is involved in each step. Each of the people or groups involved in a process is listed across the top of the chart, and the steps are arranged in the columns of the people who carry them out. (Also see deployment flowchart.)

Root cause: The deep, underlying cause of a problem in a process or system.

Run charts: Graphs of data over time.

Scatter diagram: A graphical tool that shows the relationship between two variables also referred to as scatter plot.

Six Sigma: Six standard deviations from mean Sigma is the Greek letter used to represent standard deviation in statistics. Six Sigma methodology improves an existing process by constantly reviewing and re-tuning the process. To achieve this, Six Sigma uses a methodology known as DMAIC (define, measure, analyze, improve, and control). This methodology focuses on improving process capability by reducing variation.

Special cause: A specific or assignable cause of variation that is outside of the normal variation in a process. It is signaled by a data point falling outside of the upper control limit (UCL) or lower control limit (LCL), or by one of several defined patterns on a control chart or time plot.

Stratification: Dividing a whole group of data into subgroups (strata) to see whether the data are different for different subgroups. This helps focus efforts on those factors that have the most impact on the problem.

Time plot: A graph of data in time order. It helps identify any changes that occur over time.

Time-ordered data: Characteristics that are measured, counted, or observed and recorded in the chronological order in which they occur.

Top-down flowchart: A flowchart that shows both the major steps in a process and the next level of substeps.

Upper control limit (UCL): A value, represented by a line on a control chart, that specifies the upper limit of the results of common cause variation. Data points that fall above this value provide signals of special causes.

Value-added step: A step in a process that is essential for producing the product or service at the current level of technology.

Value stream mapping: A Lean technique used to analyze the flow of materials and information currently required to bring a product or service to a consumer.

Variable: The characteristic(s) that you are measuring.

Variation: Differences among measured values in a process.

Vertical axis: The labeled straight line at the side of a graph that runs up and down, or vertically. It is also called the Y-axis.

Work-flow diagram: A tool for collecting data on how work flows through an operation. The path of the work is recorded on a schematic of the workplace.

Value chain: A chain of activities. Products pass through all activities of the chain in order and at each activity the product gains some value. The chain of activities gives the products more added value than the sum of added values of all activities.