Six Sigma Terminology

Six Sigma Terminology Welcome

2008-07-05T00:39:00.000-07:00

This dictionary provides useful terms and definitions for Six Sigma understanding.

How to Use Six Sigma Terminology
In the alphabet listed aside, just click the first letter of the word, terminology you are searching for. When that specific page appears, simply scroll down the page until you find the term. If you can't find what you want, contact us. If the term is relevant to Six Sigma we will add it as soon as we can, and let you know.

z-value

2008-07-05T00:13:00.001-07:00

a standardized value formed by subtracting the mean and then dividing this difference by the standard deviation. A Z value is a data point's position between the mean and another location as measured by the number of standard deviations. Z is a universal measurement because it can be applied to any unit of measure. Z is a measure of process capability and corresponds to the process sigma value that is reported by the businesses. For example, a 3 sigma process means that three standard deviations lie between the mean and the nearest specification limit. Three is the Z value.

Zst

2008-07-05T00:11:00.000-07:00

Often called 'benchmarking sigma' or 'sigma value'. The distribution, or variation, or spread around the mean(average) value of any process or procedure. For a business process, the sigma value indicates how well that process is performing, i.e. Zst is a short-term capability index of a process or a part(Zst=1.0 is bad, Zst=4.0 is mediocre performance, Zst=6.0 is considered 'worldcalss').

Z Shift

2008-07-05T00:08:00.003-07:00

Z shift is the difference between ZST and ZLT. The larger the Z shift, the more you are able to improve the control of the special factors identified in the subgroups.

Z Score

2008-07-05T00:08:00.002-07:00

A measure of the distance in standard deviations of a sample from the mean.

Z lt

2008-07-05T00:08:00.001-07:00

Z long term (ZLT) is the Z bench calculated from the overall standard deviation and the average output of the current process. Used with continuous data, ZLT represents the overall process capability and can be used to determine the probability of making out-of-spec parts within the current process.

Z bench

2008-07-05T00:07:00.003-07:00

Z bench is the Z value that corresponds to the total probability of a defect.

YRT(Rolled Throughput Yield)

2008-07-05T00:07:00.002-07:00

- Passing Ratio of one item through the whole process without even one defect.(the Yield without rework of fix).
- Application: Certain accumulating certain step of process in order, which is used for evaluation quality level.

YNA

2008-07-05T00:07:00.001-07:00

YNA(Normalized Yield): Average Yield of successive process
- Application: This is used for evaluation the level of quality in complete product.

Yield.

2008-07-05T00:06:00.002-07:00

An index controlling a process quality in consideration of the inferiority like reproduction or waste of parts in each step of process.

Yield in Six Sigma is to produce perfect quality of product at last in consideration of all inferiority being generating in each process.
Hidden Factory, namely it is a goal that reduce the fundamental inferiority through disclosing all problem made in production process and using a fundamental data to implement its improvement activity.

Yield

2008-07-05T00:06:00.001-07:00

One of the key improvement dimension, alongside variation, cycle time, process design and product design. The degree to which the input factors are utilised effectively in the output of the process.
Yield is the percentage of a process that is free of defects.

OR

Yield is defined as a percentage of met commitments (total of defect free events) over the total number of opportunities.

First Time Yield - FTY
Rolled Throughput Yield - RTY

YFT(First Time Yield)

2008-07-05T00:05:00.000-07:00

- First Time of Yield: The Yield whithout rework, of fix.
- Application: Deciding each Quality level individual process in use.

Y=f(X)

2008-07-05T00:04:00.004-07:00

In this equation X represents the input of the process and Y the output of the procees and f the function of the variable X.

Y is the dependent output variable of a process. It is used to monitor a process to see if it is out of control, or if symptoms are developing within a process. It is a function of the Xs that contribute to the process. Once quantified through Design of Experiment, a transfer function Y=f(X) can be developed to define the relationship of elements and help control a process.

Y is the output measure, such as process cycle time or customer satisfaction. f is the letter representing "function" (what the value(s) of X(s) does/do for Y (the output). X(s) is/are any process input(s) (variables) having assigned or inherent values(s) that is/are involved in producing the output.

For example, if you call your major department store to ask a question, the ability to have your question answered (Y) is a function (f) of the wait time, the number of people answering the phones, the time it takes to talk with the representative, the representative's knowledge, etc. All of these X's can be defined, measured and improved.

Y

2008-07-05T00:04:00.003-07:00

Y is the dependent output variable of a process. It is used to monitor a process to see if it is out of control, or if symptoms are developing within a process. It is a function of the Xs that contribute to the process. Once quantified through Design of Experiment, a transfer function Y=f(X) can be developed to define the relationship of elements and help control a process.

x bar s charts

2008-07-05T00:04:00.002-07:00

for variables data: control charts for the average and standard deviation(sigma) of subgroups of data.

x bar and R charts

2008-07-05T00:04:00.001-07:00

for variables data: control chart for the average and range of subgroups of data.

Work Activities

2008-07-05T00:03:00.001-07:00

Activities applied directly to implementing the solution.

White Noise

2008-07-05T00:03:00.000-07:00

White Noises are deviation that effected by common factor existed in process.
Can't control them the present technology level.
Effect to process deviation in many cases.
Effected by very many trifling factors.
Denoted by Z.st

Weibull distribution

2008-07-05T00:02:00.001-07:00

This distribution has a density function that has many possible shapes.

variance

2008-07-05T00:02:00.000-07:00

The squared value of the standard deviation

Variance inflation factor(VIF)

2008-07-05T00:01:00.004-07:00

A calculated quantity for each term in a regression model that measures the combined effect of the dependencies among the regressors on the variance of that term.

Variance

2008-07-05T00:01:00.003-07:00

A measure of dispersion of observations based upon the mean of the squared deviations from the arithmetic mean.

variables data

2008-07-05T00:01:00.002-07:00

concerning the values of a variable, as opposed to attribution data. A dimensional value can be recorded and is only limited in value by the resolution of the measurement system.

Variables

2008-07-05T00:01:00.001-07:00

Factors within a fractional factorial designed experiment or response surface experiment.

Variable Charts

2008-07-05T00:00:00.001-07:00

Variable charts are always plotted in pairs, with one graphic to represent the mean and one graphic to represent the process spread.

variability

2008-07-05T00:00:00.000-07:00

the property of exhibiting variation, i.e., changes or differences, in key measurements of a process.

Varance

2008-07-04T23:59:00.002-07:00

the mean of the squared deviations

USL(upper specification limit)

2008-07-04T23:59:00.001-07:00

the highest value of a product dimension or measurements of a process.

Upper Control Limit

2008-07-04T23:59:00.000-07:00

A horizontal line on a control chart(usually dootted) which represents the upper limits of process capability.

upper confidence

2008-07-04T23:58:00.004-07:00

the larger of the two numbers that form a confidence interval.

Unit

2008-07-04T23:58:00.003-07:00

In manufacturing, a unit can be a final assembly, a subassembly, or a component. In non-manufacturing a drawing, a purchase order, or a typed document can be a unit.

uniform distribution

2008-07-04T23:58:00.002-07:00

a distribution in which all outcomes are equally likely.

Uncensored data

2008-07-04T23:58:00.001-07:00

All sample dta have failed or have a reading

UCL(upper control limit)

2008-07-04T23:57:00.000-07:00

for control charts: the upper limit below which a process statistic(x bar, R, etc.) must remain to be in control. Typically this value is 3 standard deviations above the center line.

u-chart

2008-07-04T23:56:00.002-07:00

for attribute data: a control chart of the average number of defects per part in a subgroup.

Type II error

2008-07-04T23:56:00.001-07:00

concluding H0 when H1 really true.

Type I error

2008-07-04T23:55:00.001-07:00

concluding H1 (or rejecting H0) when H0 is really true.

Type Error

2008-07-04T23:55:00.000-07:00

The error in rejecting Ho when it is in fact true, or in saying there is no difference.

two-level deign

2008-07-04T23:54:00.002-07:00

also known as a two-sided test, it is a hypothesis test with a two-sided alternative hypothesis. That is, one could possibly err on either side of the center.

t-tests

2008-07-04T23:54:00.001-07:00

t-tsets neddd to be based on normal or close to normal data. Their variancesmust be close and their quantity must be similar.

t-test

2008-07-04T23:54:00.000-07:00

a hypothesis test of population means when small samples are involved.

t-Test

2008-07-04T23:53:00.004-07:00

A statistical test applied to one or two mean values.

Trial

2008-07-04T23:53:00.003-07:00

One of the facttor combinations in an experiment

trend

2008-07-04T23:53:00.002-07:00

a gradual, systematic change with time or some other variable.

Transportation

2008-07-04T23:53:00.001-07:00

Cost of bringing material and components to the production facility and cost of bringing product to market.

total quality management(TQM)

2008-07-04T23:52:00.002-07:00

a management philosophy of integrated controls, including engineering, purchasing, financial administration, marketing and manufacturing, to ensure customer satisfaction and economical cost of quality.

Tolerance

2008-07-04T23:52:00.001-07:00

Revenues which really express customer satisfaction with the company.

Thermal Cycling

2008-07-04T23:51:00.002-07:00

The inverse power law is used to model fatigue failure of metals that are subjected to thermal cycling.

The Hidden factory

2008-07-04T23:51:00.001-07:00

The notion that much of the endeavour of the company that is not quality minded is directed inadvertently to creating waste and performing wasteful tasks - examples of wasteful activities are the production of non-conforming products and the holding of excessive stock. The hidden factory is the extra useful, positive output that would theoretically be possible if the energy directed at creating waste were released and directed instead at making good quality items. In 1977, the quality guru Armand Feigenbaum estimated the endeavour within the hidden factory might be 15% to 40% of total company effort. The notion of the hidden factory is bound up with the metric COPQ (cost of poor quality). The COPQ may be estimated by multiplying the number of defects per period of time by the average unit cost to fix a defect (labour and materials). Such a calculation however omits such costs as loss of goodwill and loss of competitiveness, and such other matters as warranty costs and even legal damages.

test statistic

2008-07-04T23:51:00.000-07:00

a single value which combines the evidence obtained from sample data. The P-value in a hypothesis test is directly related to this value.

Technical Requirement

2008-07-04T23:50:00.001-07:00

A quantitative requirement set on a dimension or system of parts or dimensions which, when satisfied, will meet a consumer's expectations.

t-distriution

2008-07-04T23:50:00.000-07:00

a sysmmetric, bell-shaped distiribution that resembles the standardized normal(or Z) distribution, but it typically has more area in its tails than does the Z distribution. That is, it has greater variability than the Z distribution.

SWOT Analysis

2008-07-04T23:49:00.000-07:00

A scan of the internal and external environment is an important part of the strategic planning process. Environmental factors internal to the firm usually can be classified as strength (S) or weaknesses (W), and that external to the firm can be classified as opportunity (O) or threats (T). Such an analysis of the strategic environment is referred to as a SWOT analysis.

The SWOT analysis provides information that is helpful in matching the firm's resources and a capability to the competitive environment in which it operates. As such, it is instrumental in strategy formulation and selection.

Supply Chain Management

2008-07-01T18:22:00.003-07:00

Managing the movement of goods from raw materials to the finished product delivered to customers. Supply Chain Management aims to reduce operating costs, lead times, and inventory and increase the speed of delivery, product availability, and customer satisfaction.

Sub-Group

2008-07-01T18:22:00.002-07:00

A distinct group within a group; a subdivision or subset of a group.

Stratification

2008-07-01T18:22:00.001-07:00

A technique used to analyze/divide a universe of data into homogeneous groups (strata) often data collected about a problem or event represents multiple sources that need to treated separately.

It involves looking at process data, splitting it into distinct layers (almost like rock is stratified) and doing analysis to possibly see a different process.

For instance, you may process loans at your company. Once you stratify by loan size (e.g. less than 10 million, greater than 10 million), you may see that the central tendency metrics are completely different which would indicate that you have two entirely different processes...maybe only one of the processes is broken.

Stratification is related to, but different from, Segmentation.

A stratifying factor, also referred to as stratification or a stratifier, is a factor that can be used to separate data into subgroups. This is done to investigate whether that factor is a significant special cause factor.

Strategic Planning

2008-07-01T18:21:00.003-07:00

Strategic planning is a disciplined effort to produce fundamental decisions and actions that shape and guide what an organization is, what it does, and why it does it, with a focus on the future.

Statistics

2008-07-01T18:21:00.002-07:00

A branch of mathematics, dealing with the collection, analysis, interpretation and presentation of masses of numerical data.

Statistically Significant

2008-07-01T18:21:00.001-07:00

A result that leads us to reject the null bypothesis. What is observed has small probability assuming that the null hypothesis is true. The size of such a predetermined probability is called the significance level and denoted alpha. This is normally represented by large test statistics or small P-values.

Statistical Quality Control (SQC)

2008-07-01T18:20:00.000-07:00

The application of statistical methods for measureing and improveing the quality of processes. SPC is one method included in SQC.

Statistical Process Control(SPC)

2008-07-01T18:17:00.000-07:00

The application of statistical techniques in the control of processes. SPC is often considered a subset of SQC, where the emphasis in SPCis on the tools associated with the process but not product acceptance techniques.

Statistical inference

2008-07-01T18:16:00.003-07:00

Determining when dirrerences in results might be due to random variation, and when differences in results cannot be attributed to random variation.

Statistical Control

2008-07-01T18:16:00.002-07:00

A process in which variation in the outcome arises only from common causes. Also called a predictable process.

Statistic

2008-07-01T18:16:00.001-07:00

A numerical value, such as standard deviation or mean, that characterizes the sample or population from which it was derived. Any number calculated from sample data, describes a sample characteristic.

Stationary process

2008-07-01T18:15:00.001-07:00

Aprocess with an ultimate constant variance.

standardized normal distribution

2008-07-01T18:15:00.000-07:00

a normal distibution or random variable having a mean and standard deviation of 0 and 1, respectively. It is denoted by the symbol Z and is also called the Z distribution.

standard(measurement)

2008-07-01T18:14:00.001-07:00

a reference item providing a known value of a quantity to be measured. Standards may be primary--i.e., the standard essentially defines the unit of measure--or secondary(transfer) standard, which have been compared to the primary standard(directly or by way of an intermediate transfer standard). Standards are used to calibrate instruments which are then employed to make routine measurements.

Standard Order

2008-07-01T18:14:00.000-07:00

Design of experiment (DOE) treatments often are presented in a standard order. In a standard order, the first factor alternates between the low and high setting for each treatment. The second factor alternates between low and high settings every two treat

Standard error

2008-07-01T18:13:00.001-07:00

The square root of the variance of the sampling distribution of a statistic.

Standard Deviation

2008-07-01T18:13:00.000-07:00

The Standard Deviation is the square root of (the sum of the squared deviations from the mean, divided by the sample size minus one).
In formulae it is often represented by the letters SD or the symbol (Greek letter) sigma.
Although it is closely related to, and used in calculations for, the Sigma level of a process you need to be careful to distinguish the two meanings.

Stakeholder

2008-07-01T18:12:00.001-07:00

People who will be affected by the project or can influence it but who are not directly involved with doing the project work. Examples are Managers affected by the project, Process Owners, People who work with the process under study, Internal departments that support the process, customers, suppliers, and financial department.

Stable Process

2008-07-01T18:11:00.001-07:00

A process that does not contain any special cause variation -- it only contains common cause variation. Common cause variation is that which is normal to the process and doesn't change over time.

Stability

2008-07-01T18:11:00.000-07:00

Stability represents variation due to elapsed time. It is the difference between an individual's measurements taken of the same parts after an extended period of time using the same techniques.

Also, PROCESS STABILITY INDEX is often used in SPC where many charts are ranked by the %OOC (instability) due to application of control limits and alarm rules. Stability is not the same as Capability. Stability is based on statistical control limits, while Capability is based on customer specification limits. Often shown as %OOC and Cpk. But of course a Stable process has LOW %OOC near zero, but never zero long term if limits are set correctly due to false alarm rate with good limits and rules.

Stationary (lack of drift) is opposite of Dynamic. Not the same as Stability. Engineers and statisticians argue about these terms.

SST

2008-07-01T18:10:00.005-07:00

Total sum of squares, or the sum of squared deviations of the observed values from the mean.

SSR

2008-07-01T18:10:00.004-07:00

Sum of squares due to regression, or the sum of squared deviations of the predicted values from the mean.

SSE

2008-07-01T18:10:00.003-07:00

sum of squares due to error, or sum of squared residuals.

SS

2008-07-01T18:10:00.002-07:00

Sum of squares, normally calculated as

Spread

2008-07-01T18:10:00.001-07:00

The spread of a process represents how far data points are distributed away from the mean, or center. Standard deviation is a measure of spread.

Sporadic problem

2008-07-01T18:09:00.002-07:00

A problem that occurs in a process because of an unusual condition.

Specification

2008-07-01T18:09:00.001-07:00

Customer's expectation for product or service deliverable/output.

Parameters by which an output can be verified.

Special Cause Variation

2008-07-01T18:09:00.000-07:00

Unlike common cause variability, special cause variation is caused by known factors that result in a non-random distribution of output. Also referred to as "exceptional" or "assignable" variation. Example: Few X's with big impact.

Special cause variation is a shift in output caused by a specific factor such as environmental conditions or process input parameters. It can be accounted for directly and potentially removed and is a measure of process control.

Special Cause

2008-07-01T18:07:00.004-07:00

A source of *Quality* failure that lies outside the *Process*, and so is intermittent, unpredictable, unstable; sometimes called an *Assignable Cause*.

Statistical Process Control - SPC

2008-07-01T18:07:00.003-07:00

Statistical Process Control, the methodolgy for monitoring and improving processes using control charts.

Some taguchi concepts

2008-07-01T18:07:00.002-07:00

The purpose of an experiment should be to reduce variation. It is usually easy to get the correct level for a process, but variation is more troublesome and often results in bad product.

Soft Savings

2008-07-01T18:07:00.001-07:00

Six Sigma project benefits such as reduced time to market, improved employee morale and an enhanced image for the organization may result in additional savings to your organization, but are harder to quantify. These are referred to as soft savings.

Six Sigma

2008-07-01T18:06:00.006-07:00

Six Sigma is a rigorous and a systematic methodology that utilizes information (management by facts) and statistical analysis to measure and improve a company's operational performance, practices and systems by identifying and preventing 'defects' in manufacturing and service-related processes in order to anticipate and exceed expectations of all stakeholders to accomplish effectiveness.

SIPOC

2008-07-01T18:06:00.005-07:00

SIPOC stands for suppliers, inputs, process, output, and customers. You obtain inputs from suppliers, add value through your process, and provide an output that meets or exceeds your customer's requirements.

Supplier-Input-Process-Output-Customer: Method that helps you not to forget something when mapping processes.

Single sided test

2008-07-01T18:06:00.004-07:00

A triangular spatial design space used for variables that are mixture ingredients.

simulation(modeling)

2008-07-01T18:06:00.003-07:00

using a mathematical model of a system or process to predict the performance of the real system. The model consists of a set of equations or logic rules which operate on numerical values representing the operating parameters of the system. The result of the equation is a prediction of the system's output.

Simple Linear Regression

2008-07-01T18:06:00.002-07:00

Simple linear regression is a method that enables you to determine the relationship between a continuous process output (Y) and one factor (X). The relationship is typically expressed in terms of a mathematical equation such as Y = b + mX

Sigma Level

2008-07-01T18:06:00.001-07:00

Determining sigma levels of processes (one sigma, six sigma, etc.) allows process performance to be compared throughout an entire organization, because it is independent of the process. It is merely a determination of opportunities and defects, however the terms are appropriately defined for that specific process.

Sigma is a statistical term that measures how much a process varies from perfection, based on the number of defects per million units.

One Sigma = 690,000 per million units
Two Sigma = 308,000 per million units
Three Sigma = 66,800 per million units
Four Sigma = 6,210 per million units
Five Sigma = 230 per million units
Six Sigma = 3.4 per million units

In formulae for control limits and process capabilities, sigma is the symbol for Standard Deviation, calculated from the squares of the deviations of measured samples from the mean value (or sometimes by other methods using 'magic' numbers). For a normally distributed output, 99.7% would be expected to fall between +/-(3 x sigma) levels.

Sigma

2008-07-01T18:05:00.001-07:00

The Greek letter s (sigma) refers to the standard deviation of a population. Sigma, or standard deviation, is used as a scaling factor to convert upper and lower specification limits to Z. Therefore, a process with three standard deviations between its mean and a spec limit would have a Z value of 3 and commonly would be referred to as a 3 sigma process.

Short-term Process Performance

2008-07-01T18:05:00.000-07:00

The performance of a process when 'it is at its best', when it is 'centred', when it has no significant variation(no special causes, only common causes), used for benchmarking.

short-run SPC

2008-07-01T18:01:00.003-07:00

a set of techniques used for SPC in low-volume, short duration manufacturing.

Short term Capability

2008-07-01T18:01:00.002-07:00

Short term capability is to exist only random error and have to be the same quality level. In sampling data, generally, it means of quality characteristic change by technical factor.
Therefore, the greater variation of quality characteristic, the greather random error, then the short term capability is poor.
Zst( st), Cp
Zst=3*Cp

Shift

2008-07-01T18:01:00.001-07:00

Inevitable changes of mean values over long term. Two Americans, Bender and Gilson, are said to have independently studied shift and drift, and found it to be 1.49 standard deviations based on 30 years experience.

Shewhart control chart

2008-07-01T18:00:00.003-07:00

Shewhart is credited with developing the standard control chart test based on 3¥ò limits to separate the steady component of variation from assignable causes.

Shape Parameter

2008-07-01T18:00:00.002-07:00

A parameter used in the Weibull distribution that describes the shape of the distribution and is equal to the slope of a Weibull probability plot.

Sequential testing

2008-07-01T18:00:00.001-07:00

A procedure where items are tested in sequence. Deci sions are "continually" made to determine whether the test should be continued or stopped.

Sensitivity

2008-07-01T18:00:00.000-07:00

The ratio of change in the output to the change in the value of the measure.