Professional Documents
Culture Documents
Six Sigma Tools in A Excel Sheet
Six Sigma Tools in A Excel Sheet
rev. 2.0b
Author: R. Chapin
Definition:
Tool to use: What does it do? Why use it? When to use?
No picture available!
Continuous Y & all X's
At least one group of data is different
than at least one other group.
Alpha risk is defined as the risk of accepting the alternate hypothesis when, in fact, the null hypothesis is true; in other words, stating a
difference exists where actually there is none. Alpha risk is stated in terms of probability (such as 0.05 or 5%). The acceptable level of
alpha risk is determined by an organization or individual and is based on the nature of the decision being made. For decisions with high
consequences (such as those involving risk to human life), an alpha risk of less than 1% would be expected. If the decision involves
minimal time or money, an alpha risk of 10% may be appropriate. In general, an alpha risk of 5% is considered the norm in decision
making. Sometimes alpha risk is expressed as its inverse, which is confidence level. In other words, an alpha risk of 5% also could be
expressed as a 95% confidence level.
ANOVA General Linear Model (GLM) is a
statistical tool used to test for differences in
means. ANOVA tests to see if the difference
between the means of each level is
significantly more than the variation within
each level. ANOVA GLM is used to test the
effect of two or more factors with multiple
levels, alone and in combination, on a
dependent variable.
The General Linear Model allows you to
learn one form of ANOVA that can be
used for all tests of mean differences
involving two or more factors or levels.
Because ANOVA GLM is useful for
identifying the effect of two or more
factors (independent variables) on a
dependent variable, it is also extremely
useful for identifying important Xs for a
project Y. ANOVA GLM also yields a
percent contribution that quantifies the
variation in the response (dependent
variable) due to the individual factors and
combinations of factors.
You can use ANOVA GLM any time you
need to identify a statistically significant
difference in the mean of the dependent
variable due to two or more factors with
multiple levels, alone and in
combination. ANOVA GLM also can be
used to quantify the amount of variation
in the response that can be attributed to
a specific factor in a designed
experiment.
Data Type:
P <.05 Indicates:
Six Sigma 12 Step Process
Step Description Focus Deliverable Sample Tools
0 Project Selection Identify project CTQ's, develop team charter, define high-level process map
1 Select CTQ characteristics
Y
Identify and measure customer CTQ's Customer, QFD, FMEA
2 Define Performance Standards
Y
Define and confirm specifications for the Y Customer, blueprints
3 Measurement System Analysis
Y
Measurement system is adequate to measure Y
Continuous Gage R&R, Test/Retest,
Attribute R&R
4 Establish Process Capability
Y
Baseline current process; normality test Capability indices
5 Define Performance Objectives
Y
Statisicly define goal of project Team, benchmarking
6 Identify Variation Sources
X
List of statistically significant X's based on analysis of historical data
Process Analysis, Graphical analysis,
hypothesis testing
7 Screen Potential Causes
X
Determine vital few X's that cause changes to your Y DOE-screening
8 Discover Variable Relationships
X
Determine transfer function between Y and vital few X's; Determine optimal
settings for vital few X's; Perform confirmation runs
Factorial designs
9 Establish Operating Tolerances
Y, X
Specify tolerances on the vital few X's Simulation
10
Define and Validate Measurement System on X's
in actual application Y, X
Measurement system is adequate to measure X's
Continuous Gage R&R, Test/Retest,
Attribute R&R
11 Determine Process Capability
Y, X
Determine post improvement capability and performance Capability indices
12 Implement Process Control
X
Develop and implement process control plan Control charts, mistake proof, FMEA
233110882.xls.ms_office GE PROPRIETARY INFORMATION RMC 6/9/2014
Definitions
184
Term Definition Training Link
1-Sample sign test Tests the probability of sample median being equal to hypothesized value.
Accuracy
Accuracy refers to the variation between a measurement and what actually exists. It is the difference between an individual's average measurements and that of a
known standard, or accepted "truth."
Alpha risk
Alpha risk is defined as the risk of accepting the alternate hypothesis when, in fact, the null hypothesis is true; in other words, stating a difference exists where
actually there is none. Alpha risk is stated in terms of probability (such as 0.05 or 5%). The acceptable level of alpha risk is determined by an organization or
individual and is based on the nature of the decision being made. For decisions with high consequences (such as those involving risk to human life), an alpha risk of
less than 1% would be expected. If the decision involves minimal time or money, an alpha risk of 10% may be appropriate. In general, an alpha risk of 5% is
considered the norm in decision making. Sometimes alpha risk is expressed as its inverse, which is confidence level. In other words, an alpha risk of 5% also could be
expressed as a 95% confidence level.
Alternative hypothesis (Ha)
The alternate hypothesis (Ha) is a statement that the observed difference or relationship between two populations is real and not due to chance or sampling error.
The alternate hypothesis is the opposite of the null hypothesis (P < 0.05). A dependency exists between two or more factors
Analysis of variance (ANOVA) Analysis of variance is a statistical technique for analyzing data that tests for a difference between two or more means. See the tool 1-Way ANOVA.
Anderson-Darling Normality Test P-value < 0.05 = not normal.
Attribute Data see discrete data
Bar chart A bar chart is a graphical comparison of several quantities in which the lengths of the horizontal or vertical bars represent the relative magnitude of the values.
Benchmarking
Benchmarking is an improvement tool whereby a company measures its performance or process against other companies' best practices, determines how those
companies achieved their performance levels, and uses the information to improve its own performance. See the tool Benchmarking.
Beta risk
Beta risk is defined as the risk of accepting the null hypothesis when, in fact, the alternate hypothesis is true. In other words, stating no difference exists when there
is an actual difference. A statistical test should be capable of detecting differences that are important to you, and beta risk is the probability (such as 0.10 or 10%)
that it will not. Beta risk is determined by an organization or individual and is based on the nature of the decision being made. Beta risk depends on the magnitude
of the difference between sample means and is managed by increasing test sample size. In general, a beta risk of 10% is considered acceptable in decision making.
Bias
Bias in a sample is the presence or influence of any factor that causes the population or process being sampled to appear different from what it actually is. Bias is
introduced into a sample when data is collected without regard to key factors that may influence the population or process.
Blocking Blocking neutralizes background variables that can not be eliminated by randomizing. It does so by spreading them across the experiment
Boxplot A box plot, also known as a box and whisker diagram, is a basic graphing tool that displays centering, spread, and distribution of a continuous data set
CAP Includes/Excludes CAP Includes/Excludes is a tool that can help your team define the boundaries of your project, facilitate discussion about issues related to your project scope, and
challenge you to agree on what is included and excluded within the scope of your work. See the tool CAP Includes/Excludes.
CAP Stakeholder Analysis
CAP Stakeholder Analysis is a tool to identify and enlist support from stakeholders. It provides a visual means of identifying stakeholder support so that you can
develop an action plan for your project. See the tool CAP Stakeholder Analysis.
Capability Analysis
Capability analysis is a Minitab
TM
tool that visually compares actual process performance to the performance standards. See the tool Capability Analysis.
Cause A factor (X) that has an impact on a response variable (Y); a source of variation in a process or product.
Cause and Effect Diagram
A cause and effect diagram is a visual tool used to logically organize possible causes for a specific problem or effect by graphically displaying them in increasing
detail. It helps to identify root causes and ensures common understanding of the causes that lead to the problem. Because of its fishbone shape, it is sometimes
called a "fishbone diagram." See the tool Cause and Effect Diagram.
Center The center of a process is the average value of its data. It is equivalent to the mean and is one measure of the central tendency.
Center points
A center point is a run performed with all factors set halfway between their low and high levels. Each factor must be continuous to have a logical halfway point. For
example, there are no logical center points for the factors vendor, machine, or location (such as city); however, there are logical center points for the factors
temperature, speed, and length.
Central Limit Theorem
The central limit theorem states that given a distribution with a mean m and variance s
2
, the sampling distribution of the mean appraches a normal distribution with
a mean and variance/N as N, the sample size, increases
Characteristic A characteristic is a definable or measurable feature of a process, product, or variable.
Chi Square test
A chi square test, also called "test of association," is a statistical test of association between discrete variables. It is based on a mathematical comparison of the
number of observed counts with the number of expected counts to determine if there is a difference in output counts based on the input category. See the tool Chi
Square-Test of Independence. Used with Defects data (counts) & defectives data (how many good or bad). Critical Chi-Square is Chi-squared value where p=.05.
3.096
Term Definition Training Link
Common cause variability
Common cause variability is a source of variation caused by unknown factors that result in a steady but random distribution of output around the average of the
data. Common cause variation is a measure of the process's potential, or how well the process can perform when special cause variation is removed. Therefore, it is
a measure of the process technology. Common cause variation is also called random variation, noise, noncontrollable variation, within-group variation, or inherent
variation. Example: many X's with a small impact. Step 12 p.103
Confidence band (or interval)
Measurement of the certainty of the shape of the fitted regression line. A 95% confidence band implies a 95% chance that the true regression line fits within the
confidence bands. Measurement of certainty.
Confounding
Factors or interactions are said to be confounded when the effect of one factor is combined with that of another. In other words, their effects can not be analyzed
independently.
Consumers Risk Concluding something is bad when it is actually good (TYPE II Error)
Continuous Data
Continuous data is information that can be measured on a continuum or scale. Continuous data can have almost any numeric value and can be meaningfully
subdivided into finer and finer increments, depending upon the precision of the measurement system. Examples of continuous data include measurements of time,
temperature, weight, and size. For example, time can be measured in days, hours, minutes, seconds, and in even smaller units. Continuous data is also called
quantitative data.
Control limits
Control limits define the area three standard deviations on either side of the centerline, or mean, of data plotted on a control chart. Do not confuse control limits
with specification limits. Control limits reflect the expected variation in the data and are based on the distribution of the data points. Minitab calculates control
limits using collected data. Specification limits are established based on customer or regulatory requirements. Specification limits change only if the customer or
regulatory body so requests.
Correlation
Correlation is the degree or extent of the relationship between two variables. If the value of one variable increases when the value of the other increases, they are
said to be positively correlated. If the value of one variable decreases when the value of the other decreases, they are said to be negatively correlated. The degree of
linear association between two variables is quantified by the correlation coefficient
Correlation coefficient (r)
The correlation coefficient quantifies the degree of linear association between two variables. It is typically denoted by r and will have a value ranging between
negative 1 and positive 1.
Critical element
A critical element is an X that does not necessarily have different levels of a specific scale but can be configured according to a variety of independent alternatives.
For example, a critical element may be the routing path for an incoming call or an item request form in an order-taking process. In these cases the critical element
must be specified correctly before you can create a viable solution; however, numerous alternatives may be considered as possible solutions.
CTQ
CTQs (stands for Critical to Quality) are the key measurable characteristics of a product or process whose performance standards, or specification limits, must be
met in order to satisfy the customer. They align improvement or design efforts with critical issues that affect customer satisfaction. CTQs are defined early in any Six
Sigma project, based on Voice of the Customer (VOC) data.
Cycle time
Cycle time is the total time from the beginning to the end of your process, as defined by you and your customer. Cycle time includes process time, during which a
unit is acted upon to bring it closer to an output, and delay time, during which a unit of work waits to be processed.
Dashboard
A dashboard is a tool used for collecting and reporting information about vital customer requirements and your business's performance for key customers.
Dashboards provide a quick summary of process performance.
Data Data is factual information used as a basis for reasoning, discussion, or calculation; often this term refers to quantitative information
Defect A defect is any nonconformity in a product or process; it is any event that does not meet the performance standards of a Y.
Defective
The word defective describes an entire unit that fails to meet acceptance criteria, regardless of the number of defects within the unit. A unit may be defective
because of one or more defects.
Descriptive statistics
Descriptive statistics is a method of statistical analysis of numeric data, discrete or continuous, that provides information about centering, spread, and normality.
Results of the analysis can be in tabular or graphic format.
Design Risk Assessment
A design risk assessment is the act of determining potential risk in a design process, either in a concept design or a detailed design. It provides a broader evaluation
of your design beyond just CTQs, and will enable you to eliminate possible failures and reduce the impact of potential failures. This ensures a rigorous, systematic
examination in the reliability of the design and allows you to capture system-level risk
Detectable Effect Size
When you are deciding what factors and interactions you want to get information about, you also need to determine the smallest effect you will consider significant
enough to improve your process. This minimum size is known as the detectable effect size, or DES. Large effects are easier to detect than small effects. A design of
experiment compares the total variability in the experiment to the variation caused by a factor. The smaller the effect you are interested in, the more runs you will
need to overcome the variability in your experimentation.
DF (degrees of freedom) Equal to: (#rows - 1)(#cols - 1)
Discrete Data
Discrete data is information that can be categorized into a classification. Discrete data is based on counts. Only a finite number of values is possible, and the values
cannot be subdivided meaningfully. For example, the number of parts damaged in shipment produces discrete data because parts are either damaged or not
damaged.
Distribution
Distribution refers to the behavior of a process described by plotting the number of times a variable displays a specific value or range of values rather than by
plotting the value itself.
DMADV
DMADV is GE Company's data-driven quality strategy for designing products and processes, and it is an integral part of GE's Six Sigma Quality Initiative. DMADV
consists of five interconnected phases: Define, Measure, Analyze, Design, and Verify.
Term Definition Training Link
DMAIC
DMAIC refers to General Electric's data-driven quality strategy for improving processes, and is an integral part of the company's Six Sigma Quality Initiative. DMAIC is
an acronym for five interconnected phases: Define, Measure, Analyze, Improve, and Control.
DOE
A design of experiment is a structured, organized method for determining the relationship between factors (Xs) affecting a process and the output of that process.
DPMO
Defects per million opportunities (DPMO) is the number of defects observed during a standard production run divided by the number of opportunities to make a
defect during that run, multiplied by one million.
DPO
Defects per opportunity (DPO) represents total defects divided by total opportunities. DPO is a preliminary calculation to help you calculate DPMO (defects per
million opportunities). Multiply DPO by one million to calculate DPMO.
DPU Defects per unit (DPU) represents the number of defects divided by the number of products.
Dunnett's(1-way ANOVA):
Check to obtain a two-sided confidence interval for the difference between each treatment mean and a control mean. Specify a family error rate between 0.5 and
0.001. Values greater than or equal to 1.0 are interpreted as percentages. The default error rate is 0.05.
Effect An effect is that which is produced by a cause; the impact a factor (X) has on a response variable (Y).
Entitlement As good as a process can get without capital investment
Error
Error, also called residual error, refers to variation in observations made under identical test conditions, or the amount of variation that can not be attributed to the
variables included in the experiment.
Error (type I) Error that concludes that someone is guilty, when in fact, they really are not. (Ho true, but I rejected it--concluded Ha) ALPHA
Error (type II) Error that concludes that someone is not guilty, when in fact, they really are. (Ha true, but I concluded Ho). BETA
Factor A factor is an independent variable; an X.
Failure Mode and Effect Analysis
Failure mode and effects analysis (FMEA) is a disciplined approach used to identify possible failures of a product or service and then determine the frequency and
impact of the failure. See the tool Failure Mode and Effects Analysis.
Fisher's (1-way ANOVA):
Check to obtain confidence intervals for all pairwise differences between level means using Fisher's LSD procedure. Specify an individual rate between 0.5 and 0.001.
Values greater than or equal to 1.0 are interpreted as percentages. The default error rate is 0.05.
Fits Predicted values of "Y" calculated using the regression equation for each value of "X"
Fitted value A fitted value is the Y output value that is predicted by a regression equation.
Fractional factorial DOE
A fractional factorial design of experiment (DOE) includes selected combinations of factors and levels. It is a carefully prescribed and representative subset of a full
factorial design. A fractional factorial DOE is useful when the number of potential factors is relatively large because they reduce the total number of runs required.
By reducing the number of runs, a fractional factorial DOE will not be able to evaluate the impact of some of the factors independently. In general, higher-order
interactions are confounded with main effects or lower-order interactions. Because higher order interactions are rare, usually you can assume that their effect is
minimal and that the observed effect is caused by the main effect or lower-level interaction.
C:\Six Sigma\CD Training\04B_analysis_010199.pps - 7
Frequency plot A frequency plot is a graphical display of how often data values occur.
Full factorial DOE
A full factorial design of experiment (DOE) measures the response of every possible combination of factors and factor levels. These responses are analyzed to
provide information about every main effect and every interaction effect. A full factorial DOE is practical when fewer than five factors are being investigated. Testing
all combinations of factor levels becomes too expensive and time-consuming with five or more factors.
F-value (ANOVA)
Measurement of distance between individual distributions. As F goes up, P goes down (i.e., more confidence in there being a difference between two means). To
calculate: (Mean Square of X / Mean Square of Error)
Gage R&R
Gage R&R, which stands for gage repeatability and reproducibility, is a statistical tool that measures the amount of variation in the measurement system arising
from the measurement device and the people taking the measurement. See Gage R&R tools.
Gannt Chart
A Gantt chart is a visual project planning device used for production scheduling. A Gantt chart graphically displays time needed to complete tasks.
Goodman-Kruskal Gamma Term used to describe % variation explained by X
GRPI
GRPI stands for four critical and interrelated aspects of teamwork: goals, roles, processes, and interpersonal relationships, and it is a tool used to assess them. See
the tool GRPI.
Histogram
A histogram is a basic graphing tool that displays the relative frequency or occurrence of continuous data values showing which values occur most and least
frequently. A histogram illustrates the shape, centering, and spread of data distribution and indicates whether there are any outliers. See the tool Histogram.
Homegeneity of variance
Homogeneity of variance is a test used to determine if the variances of two or more samples are different. See the tool Homogeneity of Variance.
Hypothesis testing
Hypothesis testing refers to the process of using statistical analysis to determine if the observed differences between two or more samples are due to random
chance (as stated in the null hypothesis) or to true differences in the samples (as stated in the alternate hypothesis). A null hypothesis (H0) is a stated assumption
that there is no difference in parameters (mean, variance, DPMO) for two or more populations. The alternate hypothesis (Ha) is a statement that the observed
difference or relationship between two populations is real and not the result of chance or an error in sampling. Hypothesis testing is the process of using a variety of
statistical tools to analyze data and, ultimately, to accept or reject the null hypothesis. From a practical point of view, finding statistical evidence that the null
hypothesis is false allows you to reject the null hypothesis and accept the alternate hypothesis.
I-MR Chart
An I-MR chart, or individual and moving range chart, is a graphical tool that displays process variation over time. It signals when a process may be going out of
control and shows where to look for sources of special cause variation. See the tool I-MR Control.
Term Definition Training Link
In control
In control refers to a process unaffected by special causes. A process that is in control is affected only by common causes. A process that is out of control is affected
by special causes in addition to the common causes affecting the mean and/or variance of a process.
Independent variable An independent variable is an input or process variable (X) that can be set directly to achieve a desired output
Intangible benefits
Intangible benefits, also called soft benefits, are the gains attributable to your improvement project that are not reportable for formal accounting purposes. These
benefits are not included in the financial calculations because they are nonmonetary or are difficult to attribute directly to quality. Examples of intangible benefits
include cost avoidance, customer satisfaction and retention, and increased employee morale.
Interaction
An interaction occurs when the response achieved by one factor depends on the level of the other factor. On interaction plot, when lines are not parallel, there's an
interaction.
Interrelationship digraph An interrelationship digraph is a visual display that maps out the cause and effect links among complex, multivariable problems or desired outcomes.
IQR Intraquartile range (from box plot) representing range between 25th and 75th quartile.
Kano Analysis Kano analysis is a quality measurement used to prioritize customer requirements.
Kruskal-Wallis
Kruskal-Wallis performs a hypothesis test of the equality of population medians for a one-way design (two or more populations). This test is a generalization of the
procedure used by the Mann-Whitney test and, like Moods median test, offers a nonparametric alternative to the one-way analysis of variance. The Kruskal-Wallis
test looks for differences among the populations medians. The Kruskal-Wallis test is more powerful (the confidence interval is narrower, on average) than Moods
median test for analyzing data from many distributions, including data from the normal distribution, but is less robust against outliers.
Kurtosis Kurtosis is a measure of how peaked or flat a curve's distribution is.
L1 Spreadsheet An L1 spreadsheet calculates defects per million opportunities (DPMO) and a process Z value for discrete data.
L2 Spreadsheet An L2 spreadsheet calculates the short-term and long-term Z values for continuous data sets.
Leptokurtic Distribution
A leptokurtic distribution is symmetrical in shape, similar to a normal distribution, but the center peak is much higher; that is, there is a higher frequency of values
near the mean. In addition, a leptokurtic distribution has a higher frequency of data in the tail area.
Levels Levels are the different settings a factor can have. For example, if you are trying to determine how the response (speed of data transmittal) is affected by the factor
(connection type), you would need to set the factor at different levels (modem and LAN) then measure the change in response.
Linearity
Linearity is the variation between a known standard, or "truth," across the low and high end of the gage. It is the difference between an individual's measurements
and that of a known standard or truth over the full range of expected values.
LSL
A lower specification limit is a value above which performance of a product or process is acceptable. This is also known as a lower spec limit or LSL.
Lurking variable A lurking variable is an unknown, uncontrolled variable that influences the output of an experiment.
Main Effect
A main effect is a measurement of the average change in the output when a factor is changed from its low level to its high level. It is calculated as the average
output when a factor is at its high level minus the average output when the factor is at its low level. C:\Six Sigma\CD Training\04A_efficient_022499.pps - 13
Mallows Statistic (C-p) Statistic within Regression-->Best Fits which is used as a measure of bias (i.e., when predicted is different than truth). Should equal (#vars + 1)
Mann-Whitney
Mann-Whitney performs a hypothesis test of the equality of two population medians and calculates the corresponding point estimate and confidence interval. Use
this test as a nonparametric alternative to the two-sample t-test.
Mean
The mean is the average data point value within a data set. To calculate the mean, add all of the individual data points then divide that figure by the total number of
data points.
Measurement system analysis
Measurement system analysis is a mathematical method of determining how much the variation within the measurement process contributes to overall process
variability.
Median The median is the middle point of a data set; 50% of the values are below this point, and 50% are above this point.
Mode The most often occurring value in the data set
Moods Median
Moods median test can be used to test the equality of medians from two or more populations and, like the Kruskal-Wallis Test, provides an nonparametric
alternative to the one-way analysis of variance. Moods median test is sometimes called a median test or sign scores test. Moods Median Test tests:
H0: the population medians are all equal versus H1: the medians are not all equal
An assumption of Moods median test is that the data from each population are independent random samples and the population distributions have the same
shape. Moods median test is robust against outliers and errors in data and is particularly appropriate in the preliminary stages of analysis. Moods Median test is
more robust than is the Kruskal-Wallis test against outliers, but is less powerful for data from many distributions, including the normal.
Multicolinearity
Multicolinearity is the degree of correlation between Xs. It is an important consideration when using multiple regression on data that has been collected without
the aid of a design of experiment (DOE). A high degree of multicolinearity may lead to regression coefficients that are too large or are headed in the wrong direction
from that you had expected based on your knowledge of the process. High correlations between Xs also may result in a large p-value for an X that changes when the
intercorrelated X is dropped from the equation. The variance inflation factor provides a measure of the degree of multicolinearity.
Multiple regression Multiple regression is a method of determining the relationship between a continuous process output (Y) and several factors (Xs).
Multi-vari chart
A multi-vari chart is a tool that graphically displays patterns of variation. It is used to identify possible Xs or families of variation, such as variation within a subgroup,
between subgroups, or over time. See the tool Multi-Vari Chart.
Term Definition Training Link
Noise Process input that consistently causes variation in the output measurement that is random and expected and, therefore, not controlled is called noise. Noise also is
referred to as white noise, random variation, common cause variation, noncontrollable variation, and within-group variation.
Nominal
It refers to the value that you estimate in a design process that approximate your real CTQ (Y) target value based on the design element capacity. Nominals are
usually referred to as point estimate and related to y-hat model.
Non-parametric Set of tools that avoids assuming a particular distribution.
Normal Distribution
Normal distribution is the spread of information (such as product performance or demographics) where the most frequently occurring value is in the middle of the
range and other probabilities tail off symmetrically in both directions. Normal distribution is graphically categorized by a bell-shaped curve, also known as a
Gaussian distribution. For normally distributed data, the mean and median are very close and may be identical.
Normal probability Used to check whether observations follow a normal distribution. P > 0.05 = data is normal
Normality test
A normality test is a statistical process used to determine if a sample or any group of data fits a standard normal distribution. A normality test can be performed
mathematically or graphically. See the tool Normality Test.
Null Hypothesis (Ho)
A null hypothesis (H0) is a stated assumption that there is no difference in parameters (mean, variance, DPMO) for two or more populations. According to the null
hypothesis, any observed difference in samples is due to chance or sampling error. It is written mathematically as follows: H0: m1 = m2 H0: s1 = s2. Defines
what you expect to observe. (e.g., all means are same or independent). (P > 0.05)
Opportunity An opportunity is anything that you inspect, measure, or test on a unit that provides a chance of allowing a defect.
Outlier
An outlier is a data point that is located far from the rest of the data. Given a mean and standard deviation, a statistical distribution expects data points to fall within
a specific range. Those that do not are called outliers and should be investigated to ensure that the data is correct. If the data is correct, you have witnessed a rare
event or your process has changed. In either case, you need to understand what caused the outliers to occur.
Percent of tolerance
Percent of tolerance is calculated by taking the measurement error of interest, such as repeatability and/or reproducibility, dividing by the total tolerance range,
then multiplying the result by 100 to express the result as a percentage.
Platykurtic Distribution
A platykurtic distribution is one in which most of the values share about the same frequency of occurrence. As a result, the curve is very flat, or plateau-like. Uniform
distributions are platykurtic.
Pooled Standard Deviation
Pooled standard deviation is the standard deviation remaining after removing the effect of special cause variation-such as geographic location or time of year. It is
the average variation of your subgroups.
Prediction Band (or interval)
Measurement of the certainty of the scatter about a certain regression line. A 95% prediction band indicates that, in general, 95% of the points will be contained
within the bands.
Probability
Probability refers to the chance of something happening, or the fraction of occurrences over a large number of trials. Probability can range from 0 (no chance) to 1
(full certainty).
Probability of Defect
Probability of defect is the statistical chance that a product or process will not meet performance specifications or lie within the defined upper and lower
specification limits. It is the ratio of expected defects to the total output and is expressed as p(d). Process capability can be determined from the probability of
defect.
Process Capability
Process capability refers to the ability of a process to produce a defect-free product or service. Various indicators are used-some address overall performance, some
address potential performance.
Producers Risk Concluding something is good when it is actually bad (TYPE I Error)
p-value
The p-value represents the probability of concluding (incorrectly) that there is a difference in your samples when no true difference exists. It is a statistic calculated
by comparing the distribution of given sample data and an expected distribution (normal, F, t, etc.) and is dependent upon the statistical test being performed. For
example, if two samples are being compared in a t-test, a p-value of 0.05 means that there is only 5% chance of arriving at the calculated t value if the samples were
not different (from the same population). In other words, a p-value of 0.05 means there is only a 5% chance that you would be wrong in concluding the
populations are different. P-value < 0.05 = safe to conclude there's a difference. P-value = risk of wasting time investigating further.
Q1 25th percentile (from box plot)
Q3 75th percentile (from box plot)
Qualitative data Discrete data
Quality Function Deployment Quality function deployment (QFD) is a structured methodology used to identify customers' requirements and translate them into key process deliverables. In Six
Sigma, QFD helps you focus on ways to improve your process or product to meet customers' expectations. See the tool Quality Function Deployment.
Quantitative data Continuous data
Radar Chart
A radar chart is a graphical display of the differences between actual and ideal performance. It is useful for defining performance and identifying strengths and
weaknesses.
Randomization
Running experiments in a random order, not the standard order in the test layout. Helps to eliminate effect of "lurking variables", uncontrolled factors whihc might
vary over the length of the experiment.
Rational Subgroup
A rational subgroup is a subset of data defined by a specific factor such as a stratifying factor or a time period. Rational subgrouping identifies and separates special
cause variation (variation between subgroups caused by specific, identifiable factors) from common cause variation (unexplained, random variation caused by
factors that cannot be pinpointed or controlled). A rational subgroup should exhibit only common cause variation.
Term Definition Training Link
Regression analysis
Regression analysis is a method of analysis that enables you to quantify the relationship between two or more variables (X) and (Y) by fitting a line or plane through
all the points such that they are evenly distributed about the line or plane. Visually, the best-fit line is represented on a scatter plot by a line or plane.
Mathematically, the line or plane is represented by a formula that is referred to as the regression equation. The regression equation is used to model process
performance (Y) based on a given value or values of the process variable (X).
Repeatability Repeatability is the variation in measurements obtained when one person takes multiple measurements using the same techniques on the same parts or items.
Replicates Number of times you ran each corner. Ex. 2 replicates means you ran one corner twice.
Replication
Replication occurs when an experimental treatment is set up and conducted more than once. If you collect two data points at each treatment, you have two
replications. In general, plan on making between two and five replications for each treatment. Replicating an experiment allows you to estimate the residual or
experimental error. This is the variation from sources other than the changes in factor levels. A replication is not two measurements of the same data point but a
measurement of two data points under the same treatment conditions. For example, to make a replication, you would not have two persons time the response of a
call from the northeast region during the night shift. Instead, you would time two calls into the northeast region's help desk during the night shift.
Reproducibility Reproducibility is the variation in average measurements obtained when two or more people measure the same parts or items using the same measuring technique.
Residual
A residual is the difference between the actual Y output value and the Y output value predicted by the regression equation. The residuals in a regression model can
be analyzed to reveal inadequacies in the model. Also called "errors"
Resolution
Resolution is a measure of the degree of confounding among effects. Roman numerals are used to denote resolution. The resolution of your design defines the
amount of information that can be provided by the design of experiment. As with a computer screen, the higher the resolution of your design, the more detailed
the information you will see. The lowest resolution you can have is resolution III.
Robust Process
A robust process is one that is operating at 6 sigma and is therefore resistant to defects. Robust processes exhibit very good short-term process capability (high
short-term Z values) and a small Z shift value. In a robust process, the critical elements usually have been designed to prevent or eliminate opportunities for defects;
this effort ensures sustainability of the process. Continual monitoring of robust processes is not usually needed, although you may wish to set up periodic audits as
a safeguard.
Rolled Throughput Yield Rolled throughput yield is the probability that a single unit can pass through a series of process steps free of defects.
R-squared A mathematical term describing how much variation is being explained by the X. FORMULA: R-sq = SS(regression) / SS(total)
R-Squared Answers question of how much of total variation is explained by X. Caution: R-sq increases as number of data points increases. Pg. 13 analyze
R-squared (adj)
Unlike R-squared, R-squared adjusted takes into account the number of X's and the number of data points. FORMULA: R-sq (adj) = 1 -
[(SS(regression)/DF(regression)) / (SS(total)/DF(total))]
R-Squared adjusted Takes into account the number of X's and the number of data points...also answers: how much of total variation is explained by X.
Sample A portion or subset of units taken from the population whose characteristics are actually measured
Sample Size Calc.
The sample size calculator is a spreadsheet tool used to determine the number of data points, or sample size, needed to estimate the properties of a population.
See the tool Sample Size Calculator.
Sampling Sampling is the practice of gathering a subset of the total data available from a process or a population.
scatter plot
A scatter plot, also called a scatter diagram or a scattergram, is a basic graphic tool that illustrates the relationship between two variables. The dots on the scatter
plot represent data points. See the tool Scatter Plot.
Scorecard
A scorecard is an evaluation device, usually in the form of a questionnaire, that specifies the criteria your customers will use to rate your business's performance in
satisfying their requirements.
Screening DOE
A screening design of experiment (DOE) is a specific type of a fractional factorial DOE. A screening design is a resolution III design, which minimizes the number of
runs required in an experiment. A screening DOE is practical when you can assume that all interactions are negligible compared to main effects. Use a screening DOE
when your experiment contains five or more factors. Once you have screened out the unimportant factors, you may want to perform a fractional or full-fractional
DOE.
Segmentation
Segmentation is a process used to divide a large group into smaller, logical categories for analysis. Some commonly segmented entities are customers, data sets, or
markets.
S-hat Model It describes the relationship between output variance and input nominals
Sigma
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.
Simple Linear Regression
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
SIPOC
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.
Skewness
Most often, the median is used as a measure of central tendency when data sets are skewed. The metric that indicates the degree of asymmetry is called, simply,
skewness. Skewness often results in situations when a natural boundary is present. Normal distributions will have a skewness value of approximately zero. Right-
skewed distributions will have a positive skewness value; left-skewed distributions will have a negative skewness value. Typically, the skewness value will range
from negative 3 to positive 3. Two examples of skewed data sets are salaries within an organization and monthly prices of homes for sale in a particular area.
Span A measure of variation for "S-shaped" fulfillment Y's
Term Definition Training Link
Special cause variability
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. Step 12 p.103
Spread
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.
SS Process Report
The Six Sigma process report is a Minitab tool that calculates process capability and provides visuals of process performance. See the tool Six Sigma Process
Report.
SS Product Report
The Six Sigma product report is a Minitab tool that calculates the DPMO and short-term capability of your process. See the tool Six Sigma Product Report.
Stability
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.
Standard Deviation (s)
Standard deviation is a measure of the spread of data in relation to the mean. It is the most common measure of the variability of a set of data. If the standard
deviation is based on a sampling, it is referred to as "s." If the entire data population is used, standard deviation is represented by the Greek letter sigma (s). The
standard deviation (together with the mean) is used to measure the degree to which the product or process falls within specifications. The lower the standard
deviation, the more likely the product or service falls within spec. When the standard deviation is calculated in relation to the mean of all the data points, the result
is an overall standard deviation. When the standard deviation is calculated in relation to the means of subgroups, the result is a pooled standard deviation. Together
with the mean, both overall and pooled standard deviations can help you determine your degree of control over the product or process.
Standard Order
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 treatments. The third factor alternates between low and high settings every
four treatments. Note that each time a factor is added, the design doubles in size to provide all combinations for each level of the new factor.
Statistic Any number calculated from sample data, describes a sample characteristic
Statistical Process Control (SPC) Statistical process control is the application of statistical methods to analyze and control the variation of a process.
Stratification
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.
Subgrouping Measurement of where you can get.
Tolerance Range Tolerance range is the difference between the upper specification limit and the lower specification limit.
Total Observed Variation Total observed variation is the combined variation from all sources, including the process and the measurement system.
Total Prob of Defect
The total probability of defect is equal to the sum of the probability of defect above the upper spec limit-p(d), upper-and the probability of defect below the lower
spec limit-p(d), lower.
Transfer function A transfer function describes the relationship between lower level requirements and higher level requirements. If it describes the relationship between the nominal
values, then it is called a y-hat model. If it describes the relationship between the variations, then it is called an s-hat model.
Transformations Used to make non-normal data look more normal. GEAE CD (Control)
Trivial many The trivial many refers to the variables that are least likely responsible for variation in a process, product, or service.
T-test
A t-test is a statistical tool used to determine whether a significant difference exists between the means of two distributions or the mean of one distribution and a
target value. See the t-test tools.
Tukey's (1-wayANOVA):
Check to obtain confidence intervals for all pairwise differences between level means using Tukey's method (also called Tukey's HSD or Tukey-Kramer method).
Specify a family error rate between 0.5 and 0.001. Values greater than or equal to 1.0 are interpreted as percentages. The default error rate is 0.05.
Unexplained Variation (S) Regression statistical output that shows the unexplained variation in the data. Se = sqrt((sum(yi-y_bar)^2)/(n-1))
Unit A unit is any item that is produced or processed.
USL An upper specification limit, also known as an upper spec limit, or USL, is a value below which performance of a product or process is acceptable.
Variation
Variation is the fluctuation in process output. It is quantified by standard deviation, a measure of the average spread of the data around the mean. Variation is
sometimes called noise. Variance is squared standard deviation.
Variation (common cause)
Common cause variation is fluctuation caused by unknown factors resulting in a steady but random distribution of output around the average of the data. It is a
measure of the process potential, or how well the process can perform when special cause variation is removed; therefore, it is a measure of the process's
technology. Also called, inherent variation
Variation (special cause)
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, or how well the process is performing compared to its potential. Also called non-random variation.
Whisker
From box plot...displays minimum and maximum observations within 1.5 IQR (75th-25th percentile span) from either 25th or 75th percentile. Outlier are those that
fall outside of the 1.5 range.
Yield Yield is the percentage of a process that is free of defects.
Z
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.
Term Definition Training Link
Z bench Z bench is the Z value that corresponds to the total probability of a defect
Z lt
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 shift
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 st
ZST represents the process capability when special factors are removed and the process is properly centered. ZST is the metric by which processes are compared.
184
Tool What does it do? Why use? When use? Data Type P < .05 indicates Picture
1-Sample t-Test Compares mean to target
The 1-sample t-test is useful in identifying a
significant difference between a sample mean
and a specified value when the difference is
not readily apparent from graphical tools.
Using the 1-sample t-test to compare data
gathered before process improvements and
after is a way to prove that the mean has
actually shifted.
The 1-sample t-test is used with continuous data
any time you need to compare a sample mean to a
specified value. This is useful when you need to
make judgments about a process based on a sample
output from that process.
Continuous X & Y Not equal 1
1-Way ANOVA
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.
One-way ANOVA is useful for identifying a
statistically significant difference between
means of three or more levels of a factor.
Use 1-way ANOVA when you need to compare three
or more means (a single factor with three or more
levels) and determine how much of the total
observed variation can be explained by the factor.
Continuous Y, Discrete
Xs
At least one group
of data is different
than at least one
other group.
0
2-Sample t-Test
A statistical test used to detect differences between means of
two populations.
The 2-sample t-test is useful for identifying a
significant difference between means of two
levels (subgroups) of a factor. It is also
extremely useful for identifying important Xs
for a project Y.
When you have two samples of continuous data,
and you need to know if they both come from the
same population or if they represent two different
populations
Continuous X & Y
There is a
difference in the
means
0
ANOVA GLM
ANOVA General Linear Model (GLM) is a statistical tool used
to test for differences in means. ANOVA tests to see if the
difference between the means of each level is significantly
more than the variation within each level. ANOVA GLMis
used to test the effect of two or more factors with multiple
levels, alone and in combination, on a dependent variable.
The General Linear Model allows you to learn
one form of ANOVA that can be used for all
tests of mean differences involving two or
more factors or levels. Because ANOVA GLMis
useful for identifying the effect of two or more
factors (independent variables) on a
dependent variable, it is also extremely useful
for identifying important Xs for a project Y.
ANOVA GLMalso yields a percent contribution
that quantifies the variation in the response
(dependent variable) due to the individual
factors and combinations of factors.
You can use ANOVA GLMany time you need to
identify a statistically significant difference in the
mean of the dependent variable due to two or more
factors with multiple levels, alone and in
combination. ANOVA GLMalso can be used to
quantify the amount of variation in the response
that can be attributed to a specific factor in a
designed experiment.
Continuous Y & all X's
At least one group
of data is different
than at least one
other group.
0
Benchmarking
Benchmarking is an improvement tool whereby a company:
Measures its performance or process against other
companies' best in class practices, Determines how those
companies achieved their performance levels, Uses the
information to improve its own performance.
Benchmarking is an important tool in the
improvement of your process for several
reasons. First, it allows you to compare your
relative position for this product or service
against industry leaders or other companies
outside your industry who perform similar
functions. Second, it helps you identify
potential Xs by comparing your process to the
benchmarked process. Third, it may encourage
innovative or direct applications of solutions
from other businesses to your product or
process. And finally, benchmarking can help to
build acceptance for your project's results
when they are compared to benchmark data
obtained from industry leaders.
Benchmarking can be done at any point in the Six
Sigma process when you need to develop a new
process or improve an existing one
all N/A 1
Best Subsets
Tells you the best X to use when you're comparing multiple
X's in regression assessment.
Best Subsets is an efficient way to select a
group of "best subsets" for further analysis by
selecting the smallest subset that fulfills
certain statistical criteria. The subset model
may actually estimate the regression
coefficients and predict future responses with
smaller variance than the full model using all
predictors
Typically used before or after a multiple-regression
analysis. Particularly useful in determining which X
combination yields the best R-sq value.
Continuous X & Y N/A 0
Tool What does it do? Why use? When use? Data Type P < .05 indicates Picture
Binary Logistic
Regression
Binary logistic regression is useful in two important
applications: analyzing the differences among discrete Xs and
modeling the relationship between a discrete binary Y and
discrete and/or continuous Xs.
Binary logistic regression is useful in two
applications: analyzing the differences among
discrete Xs and modeling the relationship
between a discrete binary Y and discrete
and/or continuous Xs. Binary logistic
regression can be used to model the
relationship between a discrete binary Y and
discrete and/or continuous Xs. The predicted
values will be probabilities p(d) of an event
such as success or failure-not an event count.
The predicted values will be bounded between
zero and one (because they are probabilities).
Generally speaking, logistic regression is used when
the Ys are discrete and the Xs are continuous
Defectives Y /
Continuous & Discrete
X
The goodness-of-fit
tests, with p-values
ranging from 0.312
to 0.724, indicate
that there is
insufficient
evidence for the
model not fitting
the data
adequately. If the p-
value is less than
your accepted a
level, the test
would indicate
sufficient evidence
for a conclusion of
an inadequate fit.
0
Box Plot
A box plot is a basic graphing tool that displays the centering,
spread, and distribution of a continuous data set. In simplified
terms, it is made up of a box and whiskers (and occasional
outliers) that correspond to each fourth, or quartile, of the
data set. The box represents the second and third quartiles of
data. The line that bisects the box is the median of the entire
data set-50% of the data points fall below this line and 50%
fall above it. The first and fourth quartiles are represented by
"whiskers," or lines that extend from both ends of the box.
a box plot can help you visualize the centering,
spread, and distribution of your data quickly. It
is especially useful to view more than one box
plot simultaneously to compare the
performance of several processes such as the
price quote cycle between offices or the
accuracy of component placement across
several production lines. A box plot can help
identify candidates for the causes behind your
list of potential Xs. It also is useful in tracking
process improvement by comparing successive
plots generated over time
You can use a box plot throughout an improvement
project, although it is most useful in the Analyze
phase. In the Measure phase you can use a box plot
to begin to understand the nature of a problem. In
the Analyze phase a box plot can help you identify
potential Xs that should be investigated further. It
also can help eliminate potential Xs. In the Improve
phase you can use a box plot to validate potential
improvements
Continuous X & Y N/A 1
Box-Cox Transformation
used to find the mathematical function needed to translate a
continuous but nonnormal distribution into a normal
distribution. After you have entered your data, Minitab tells
you what mathematical function can be applied to each of
your data points to bring your data closer to a normal
distribution.
Many tools require that data be normally
distributed to produce accurate results. If the
data set is not normal, this may reduce
significantly the confidence in the results
obtained.
If your data is not normally distributed, you may
encounter problems in Calculating Z values with
continuous data. You could calculate an inaccurate
representation of your process capability. In
constructing control charts.... Your process may
appear more or less in control than it really is. In
Hypothesis testing... As your data becomes less
normal, the results of your tests may not be valid.
Continuous X & Y N/A 1
Brainstorming
Brainstorming is a tool that allows for open and creative
thinking. It encourages all team members to participate and
to build on each other's creativity
Brainstorming is helpful because it allows your
team to generate many ideas on a topic
creatively and efficiently without criticism or
judgment.
Brainstorming can be used any time you and your
team need to creatively generate numerous ideas
on any topic. You will use brainstorming many times
throughout your project whenever you feel it is
appropriate. You also may incorporate
brainstorming into other tools, such as QFD, tree
diagrams, process mapping, or FMEA.
all N/A 0
c Chart
a graphical tool that allows you to view the actual number of
defects in each subgroup. Unlike continuous data control
charts, discrete data control charts can monitor many product
quality characteristics simultaneously. For example, you could
use a c chart to monitor many types of defects in a call center
process (like hang ups, incorrect information given,
disconnections) on a single chart when the subgroup size is
constant.
The c chart is a tool that will help you
determine if your process is in control by
determining whether special causes are
present. The presence of special cause
variation indicates that factors are influencing
the output of your process. Eliminating the
influence of these factors will improve the
performance of your process and bring your
process into control
Control phase to verify that your process remains in
control after the sources of special cause variation
have been removed. The c chart is used for
processes that generate discrete data. The c chart
monitors the number of defects per sample taken
from a process. You should record between 5 and
10 readings, and the sample size must be constant.
The c chart can be used in both low- and high-
volume environments
Continuous X,
Attribute Y
N/A 0
CAP Includes/Excludes
A group exercise used to establish scope and facilitate
discussion. Effort focuses on delineating project boundaries.
Encourages group participation. Increases
individual involvement and understanding of
team efforts. Prevents errant team efforts in
later project stages (waste). Helps to orient
new team members.
Define all N/A 0
CAP Stakeholder
Analysis
Confirms management or stakeholder acceptance and
prioritization of Project and team efforts.
Helps to eliminate low priority projects. Insure
management support and compatibility with
business goals.
Defone all N/A 0
Tool What does it do? Why use? When use? Data Type P < .05 indicates Picture
Capability Analysis
Capability analysis is a Minitab
TM
tool that visually compares
actual process performance to the performance standards.
The capability analysis output includes an illustration of the
data and several performance statistics. The plot is a
histogram with the performance standards for the process
expressed as upper and lower specification limits (USL and
LSL). A normal distribution curve is calculated from the
process mean and standard deviation; this curve is overlaid
on the histogram. Beneath this graphic is a table listing
several key process parameters such as mean, standard
deviation, capability indexes, and parts per million (ppm)
above and below the specification limits.
When describing a process, it is important to
identify sources of variation as well as process
segments that do not meet performance
standards. Capability analysis is a useful tool
because it illustrates the centering and spread
of your data in relation to the performance
standards and provides a statistical summary
of process performance. Capability analysis
will help you describe the problem and
evaluate the proposed solution in statistical
terms.
Capability analysis is used with continuous data
whenever you need to compare actual process
performance to the performance standards. You
can use this tool in the Measure phase to describe
process performance in statistical terms. In the
Improve phase, you can use capability analysis
when you optimize and confirm your proposed
solution. In the Control phase, capability analysis
will help you compare the actual improvement of
your process to the performance standards.
Continuous X & Y N/A 1
Cause and Effect
Diagram
A cause and effect diagram is a visual tool that logically
organizes possible causes for a specific problem or effect by
graphically displaying them in increasing detail. It is
sometimes called a fishbone diagram because of its fishbone
shape. This shape allows the team to see how each cause
relates to the effect. It then allows you to determine a
classification related to the impact and ease of addressing
each cause
A cause and effect diagram allows your team
to explore, identify, and display all of the
possible causes related to a specific problem.
The diagram can increase in detail as
necessary to identify the true root cause of the
problem. Proper use of the tool helps the team
organize thinking so that all the possible
causes of the problem, not just those from one
person's viewpoint, are captured. Therefore,
the cause and effect diagram reflects the
perspective of the team as a whole and helps
foster consensus in the results because each
team member can view all the inputs
You can use the cause and effect diagram whenever
you need to break an effect down into its root
causes. It is especially useful in the Measure,
Analyze, and Improve phases of the DMAIC process
all N/A 0
Chi Square--Test of
Independence
The chi square-test of independence is a test of association
(nonindependence) between discrete variables. It is also
referred to as the test of association. It is based on a
mathematical comparison of the number of observed counts
against the expected number of counts to determine if there
is a difference in output counts based on the input category.
Example: The number of units failing inspection on the first
shift is greater than the number of units failing inspection on
the second shift. Example: There are fewer defects on the
revised application form than there were on the previous
application form
The chi square-test of independence is useful
for identifying a significant difference between
count data for two or more levels of a discrete
variable Many statistical problem statements
and performance improvement goals are
written in terms of reducing DPMO/DPU. The
chi square-test of independence applied to
before and after data is a way to prove that
the DPMO/DPU have actually been reduced.
When you have discrete Y and X data (nominal data
in a table-of-total-counts format, shown in fig. 1)
and need to know if the Y output counts differ for
two or more subgroup categories (Xs), use the chi
square test. If you have raw data (untotaled), you
need to form the contingency table. Use Stat >
Tables > Cross Tabulation and check the Chisquare
analysis box.
discrete (category or
count)
At least one group
is statistically
different.
0
Control Charts
Control charts are time-ordered graphical displays of data
that plot process variation over time. Control charts are the
major tools used to monitor processes to ensure they remain
stable. Control charts are characterized by A centerline,
which represents the process average, or the middle point
about which plotted measures are expected to vary
randomly. Upper and lower control limits, which define the
area three standard deviations on either side of the
centerline. Control limits reflect the expected range of
variation for that process. Control charts determine whether
a process is in control or out of control. A process is said to be
in control when only common causes of variation are present.
This is represented on the control chart by data points
fluctuating randomly within the control limits. Data points
outside the control limits and those displaying nonrandom
patterns indicate special cause variation. When special cause
variation is present, the process is said to be out of control.
Control charts identify when special cause is acting on the
process but do not identify what the special cause is. There
are two categories of control charts, characterized by type of
data you are working with: continuous data control charts
and discrete data control charts.
Control charts serve as a tool for the ongoing
control of a process and provide a common
language for discussing process performance.
They help you understand variation and use
that knowledge to control and improve your
process. In addition, control charts function as
a monitoring system that alerts you to the
need to respond to special cause variation so
you can put in place an immediate remedy to
contain any damage.
In the Measure phase, use control charts to
understand the performance of your process as it
exists before process improvements. In the Analyze
phase, control charts serve as a troubleshooting
guide that can help you identify sources of variation
(Xs). In the Control phase, use control charts to : 1.
Make sure the vital few Xs remain in control to
sustain the solution - 2. Show process performance
after full-scale implementation of your solution. You
can compare the control chart created in the
Control phase with that from the Measure phase to
show process improvement -3. Verify that the
process remains in control after the sources of
special cause variation have been removed
all N/A 0
Data Collection Plan
Failing to establish a data collection plan can
be an expensive mistake in a project. Without
a plan, data collection may be haphazard,
resulting in insufficient, unnecessary, or
inaccurate information. This is often called
"bad" data. A data collection plan provides a
basic strategy for collecting accurate data
efficiently
Any time data is needed, you should draft a data
collection plan before beginning to collect it.
all N/A 0
Tool What does it do? Why use? When use? Data Type P < .05 indicates Picture
Design Analysis
Spreadsheet
The design analysis spreadsheet is an MS-Excel workbook
that has been designed to perform partial derivative analysis
and root sum of squares analysis. The design analysis
spreadsheet provides a quick way to predict the mean and
standard deviation of an output measure (Y), given the means
and standard deviations of the inputs (Xs). This will help you
develop a statistical model of your product or process, which
in turn will help you improve that product or process. The
partial derivative of Y with respect to X is called the sensitivity
of Y with respect to X or the sensitivity coefficient of X. For
this reason, partial derivative analysis is sometimes called
sensitivity analysis.
The design analysis spreadsheet can help you
improve, revise, and optimize your design. It
can also:Improve a product or process by
identifying the Xs which have the most impact
on the response.Identify the factors whose
variability has the highest influence on the
response and target their improvement by
adjusting tolerances.Identify the factors that
have low influence and can be allowed to vary
over a wider range.Be used with the Solver**
optimization routine for complex functions (Y
equations) with many constraints. ** Note that
you must unprotect the worksheet before
using Solver.Be used with process simulation
to visualize the response given a set of
constrained
Partial derivative analysis is widely used in product
design, manufacturing, process improvement, and
commercial services during the concept design,
capability assessment, and creation of the detailed
design.When the Xs are known to be highly non-
normal (and especially if the Xs have skewed
distributions), Monte Carlo analysis may be a better
choice than partial derivative analysis.Unlike root
sum of squares (RSS) analysis, partial derivative
analysis can be used with nonlinear transfer
functions.Use partial derivative analysis when you
want to predict the mean and standard deviation of
a system response (Y), given the means and
standard deviations of the inputs (Xs), when the
transfer function Y=f(X1, X2, ., Xn) is known.
However, the inputs (Xs) must be independent of
one another (i.e., not correlated).
Continuous X & Y N/A 0
Design of Experiment
(DOE)
Design of experiment (DOE) is a tool that allows you to obtain
information about how factors (Xs), alone and in combination,
affect a process and its output (Y). Traditional experiments
generate data by changing one factor at a time, usually by
trial and error. This approach often requires a great many
runs and cannot capture the effect of combined factors on
the output. By allowing you to test more than one factor at a
time-as well as different settings for each factor-DOE is able
to identify all factors and combinations of factors that affect
the process Y.
DOE uses an efficient, cost-effective, and
methodical approach to collecting and
analyzing data related to a process output and
the factors that affect it. By testing more than
one factor at a time, DOE is able to identify all
factors and combinations of factors that affect
the process Y
In general, use DOE when you want toIdentify and
quantify the impact of the vital few Xs on your
process outputDescribe the relationship between Xs
and a Y with a mathematical modelDetermine the
best configuration
Continuous Y & all X's N/A 0
Design Scorecards
Design scorecards are a means for gathering data, predicting
final quality, analyzing drivers of poor quality, and modifying
design elements before a product is built. This makes
proactive corrective action possible, rather than initiating
reactive quality efforts during pre-production. Design
scorecards are an MS-Excel workbook that has been
designed to automatically calculate Z values for a product
based on user-provided inputs of for all the sub-processes
and parts that make up the product. Design scorecards have
six basic components: 1 Top-level scorecard-used to report
the rolled-up ZST prediction 2. Performance worksheet-used
to estimate defects caused by lack of design margin 3. Process
worksheet-used to estimate defects in process as a result of
the design configuration 4.Parts worksheet-used to estimate
defects due to incoming materialsSoftware worksheet-used
to estimate defects in software 5. Software worksheet-used
to estimate defects in software 6. Reliability worksheet-used
to estimate defects due to reliability
Design scorecards can be used anytime that a
product or process is being designed or modified
and it is necessary to predict defect levels before
implementing a process. They can be used in either
the DMADV or DMAIC processes.
all N/A 0
Discrete Data Analysis
Method
The Discrete Data Analysis (DDA) method is a tool used to
assess the variation in a measurement system due to
reproducibility, repeatability, and/or accuracy. This tool
applies to discrete data only.
The DDA method is an important tool because
it provides a method to independently assess
the most common types of measurement
variation-repeatability, reproducibility, and/or
accuracy. Completing the DDA method will
help you to determine whether the variation
from repeatability, reproducibility, and/or
accuracy in your measurement system is an
acceptably small portion of the total observed
variation.
Use the DDA method after the project data
collection plan is formulated or modified and before
the project data collection plan is finalized and data
is collected. Choose the DDA method when you
have discrete data and you want to determine if the
measurement variation due to repeatability,
reproducibility, and/or accuracy is an acceptably
small portion of the total observed variation
discrete (category or
count)
N/A 0
Discrete Event
Simulation (Process
ModelTM)
Discrete event simulation is conducted for processes that are
dictated by events at distinct points in time; each occurrence
of an event impacts the current state of the process.
Examples of discrete events are arrivals of phone calls at a call
center. Timing in a discrete event model increases
incrementally based on the arrival and departure of the
inputs or resources
ProcessModel
TM
is a process modeling and
analysis tool that accelerates the process
improvement effort. It combines a simple
flowcharting function with a simulation
process to produce a quick and easy tool for
documenting, analyzing, and improving
business processes.
Discrete event simulation is used in the Analyze
phase of a DMAIC project to understand the
behavior of important process variables. In the
Improve phase of a DMAIC project, discrete event
simulation is used to predict the performance of an
existing process under different conditions and to
test new process ideas or alternatives in an isolated
environment. Use ProcessModelTMwhen you
reach step 4, Implement, of the 10-step simulation
process.
Continuous Y, Discrete
Xs
N/A 0
Tool What does it do? Why use? When use? Data Type P < .05 indicates Picture
Dot Plot
Quick graphical comparison of two or more processes'
variation or spread
Quick graphical comparison of two or more
processes' variation or spread
Comparing two or more processes' variation or
spread
Continuous Y, Discrete
Xs
N/A
Failure Mode and Effects
Analysis
A means / method to Identify ways a process can fail,
estimate th risks of those failures, evaluate a control plan,
prioritize actions related to the process
Complex or new processes. Customers are
involved.
all N/A 0
Gage R & R--ANOVA
Method
Gage R&R-ANOVA method is a tool used to assess the
variation in a measurement system due to reproducibility
and/or repeatability. An advantage of this tool is that it can
separate the individual effects of repeatability and
reproducibility and then break down reproducibility into the
components "operator" and "operator by part." This tool
applies to continuous data only.
Gage R&R-ANOVA method is an important tool
because it provides a method to
independently assess the most common types
of measurement variation - repeatability and
reproducibility. This tool will help you to
determine whether the variation from
repeatability and/or reproducibility in your
measurement system is an acceptably small
portion of the total observed variation.
Measure -Use Gage R&R-ANOVA method after the
project data collection plan is formulated or
modified and before the project data collection plan
is finalized and data is collected. Choose the ANOVA
method when you have continuous data and you
want to determine if the measurement variation
due to repeatability and/or reproducibility is an
acceptably small portion of the total observed
variation.
Continuous X & Y 0
Gage R & R--Short
Method
Gage R&R-Short Method is a tool used to assess the variation
in a measurement system due to the combined effect of
reproducibility and repeatability. An advantage of this tool is
that it requires only two operators and five samples to
complete the analysis. A disadvantage of this tool is that the
individual effects of repeatability and reproducibility cannot
be separated. This tool applies to continuous data only
Gage R&R-Short Method is an important tool
because it provides a quick method of
assessing the most common types of
measurement variation using only five parts
and two operators. Completing the Gage R&R-
Short Method will help you determine
whether the combined variation from
repeatability and reproducibility in your
measurement system is an acceptably small
portion of the total observed variation.
Use Gage R&R-Short Method after the project data
collection plan is formulated or modified and before
the project data collection plan is finalized and data
is collected. Choose the Gage R&R-Short Method
when you have continuous data and you believe the
total measurement variation due to repeatability
and reproducibility is an acceptably small portion of
the total observed variation, but you need to
confirm this belief. For example, you may want to
verify that no changes occurred since a previous
Gage R&R study. Gage R&R-Short Method can also
be used in cases where sample size is limited.
Continuous X & Y 0
GRPI
GRPI is an excellent tool for organizing newly
formed teams. It is valuable in helping a group
of individuals work as an effective team-one of
the key ingredients to success in a DMAIC
project
GRPI is an excellent team-building tool and, as such,
should be initiated at one of the first team
meetings. In the DMAIC process, this generally
happens in the Define phase, where you create your
charter and form your team. Continue to update
your GRPI checklist throughout the DMAIC process
as your project unfolds and as your team develops
all N/A 0
Histogram
A histogram is a basic graphing tool that displays the relative
frequency or occurrence of data values-or which data values
occur most and least frequently. A histogram illustrates the
shape, centering, and spread of data distribution and
indicates whether there are any outliers. The frequency of
occurrence is displayed on the y-axis, where the height of
each bar indicates the number of occurrences for that interval
(or class) of data, such as 1 to 3 days, 4 to 6 days, and so on.
Classes of data are displayed on the x-axis. The grouping of
data into classes is the distinguishing feature of a histogram
it is important to identify and control all
sources of variation. Histograms allow you to
visualize large quantities of data that would
otherwise be difficult to interpret. They give
you a way to quickly assess the distribution of
your data and the variation that exists in your
process. The shape of a histogram offers clues
that can lead you to possible Xs. For example,
when a histogram has two distinct peaks, or is
bimodal, you would look for a cause for the
difference in peaks.
Histograms can be used throughout an
improvement project. In the Measure phase, you
can use histograms to begin to understand the
statistical nature of the problem. In the Analyze
phase, histograms can help you identify potential Xs
that should be investigated further. They can also
help eliminate potential Xs. In the Improve phase,
you can use histograms to characterize and confirm
your solution. In the Control phase, histograms give
you a visual reference to help track and maintain
your improvements.
Continuous Y & all X's N/A 1
Homogeneity of
Variance
Homogeneity of variance is a test used to determine if the
variances of two or more samples are different, or not
homogeneous. The homogeneity of variance test is a
comparison of the variances (sigma, or standard deviations)
of two or more distributions.
While large differences in variance between a
small number of samples are detectable with
graphical tools, the homogeneity of variance
test is a quick way to reliably detect small
differences in variance between large numbers
of samples.
There are two main reasons for using the
homogeneity of variance test:1. A basic assumption
of many statistical tests is that the variances of the
different samples are equal. Some statistical
procedures, such as 2-sample t-test, gain additional
test power if the variances of the two samples can
be considered equal.2. Many statistical problem
statements and performance improvement goals
are written in terms of "reducing the variance."
Homogeneity of variance tests can be performed on
before and after data, as a way to prove that the
variance has been reduced.
Continuous Y, Discrete
Xs
(Use Levene's Test)
At least one group
of data is different
than at least one
other group
1
I-MR Chart
The I-MR chart is a tool to help you determine if your process
is in control by seeing if special causes are present.
The presence of special cause variation
indicates that factors are influencing the
output of your process. Eliminating the
influence of these factors will improve the
performance of your process and bring your
process into control
The Measure phase to separate common causes of
variation from special causesThe Analyze and
Improve phases to ensure process stability before
completing a hypothesis testThe Control phase to
verify that the process remains in control after the
sources of special cause variation have been
removed
Continuous X & Y N/A 1
Tool What does it do? Why use? When use? Data Type P < .05 indicates Picture
Kano Analysis
Kano analysis is a customer research method for classifying
customer needs into four categories; it relies on a
questionnaire filled out by or with the customer. It helps you
understand the relationship between the fulfillment or
nonfulfillment of a need and the satisfaction or dissatisfaction
experienced by the customer. The four categories are 1.
delighters, 2. Must Be elements, 3. One - dimensionals, & 4.
Indeifferent elements. There are two additional categories
into which customer responses to the Kano survey can fall:
they are reverse elements and questionable result. --The
categories in Kano analysis represent a point in time, and
needs are constantly evolving. Often what is a delighter today
can become simply a must-be over time.
Kano analysis provides a systematic, data-
based method for gaining deeper
understanding of customer needs by
classifying them
Use Kano analysis after a list of potential needs that
have to be satisfied is generated (through, for
example, interviews, focus groups, or observations).
Kano analysis is useful when you need to collect
data on customer needs and prioritize them to focus
your efforts.
all N/A 0
Kruskal-Wallis Test Compare two or more means with unknown distributions
non-parametric
(measurement or
count)
At least one mean
is different
0
Matrix Plot
Tool used for high-level look at relationships between several
parameters. Matrix plots are often a first step at determining
which X's contribute most to your Y.
Matrix plots can save time by allowing you to
drill-down into data and determine which
parameters best relate to your Y.
You should use matrix plots early in your analyze
phase.
Continuous Y & all X's N/A
Mistake Proofing
Mistake-proofing devices prevent defects by preventing
errors or by predicting when errors could occur.
Mistake proofing is an important tool because
it allows you to take a proactive approach to
eliminating errors at their source before they
become defects.
You should use mistake proofing in the Measure
phase when you are developing your data collection
plan, in the Improve phase when you are developing
your proposed solution, and in the Control phase
when developing the control plan.Mistake proofing
is appropriate when there are :1. Process steps
where human intervention is required2. Repetitive
tasks where physical manipulation of objects is
required3. Steps where errors are known to occur4.
Opportunities for predictable errors to occur
all N/A 0
Monte Carlo Analysis
Monte Carlo analysis is a decision-making and problem-
solving tool used to evaluate a large number of possible
scenarios of a process. Each scenario represents one possible
set of values for each of the variables of the process and the
calculation of those variables using the transfer function to
produce an outcome Y. By repeating this method many times,
you can develop a distribution for the overall process
performance. Monte Carlo can be used in such broad areas as
finance, commercial quality, engineering design,
manufacturing, and process design and improvement. Monte
Carlo can be used with any type of distribution; its value
comes from the increased knowledge we gain in terms of
variation of the output
Performing a Monte Carlo analysis is one way
to understand the variation that naturally
exists in your process. One of the ways to
reduce defects is to decrease the output
variation. Monte Carlo focuses on
understanding what variations exist in the
input Xs in order to reduce the variation in
output Y.
Continuous Y & all X's N/A 0
Multi-Generational
Product/Process
Planning
Multigenerational product/process planning (MGPP) is a
procedure that helps you create, upgrade, leverage, and
maintain a product or process in a way that can reduce
production costs and increase market share. A key element of
MGPP is its ability to help you follow up product/process
introduction with improved, derivative versions of the original
product.
Most products or processes, once introduced,
tend to remain unchanged for many years. Yet,
competitors, technology, and the marketplace-
as personified by the ever more demanding
consumer-change constantly. Therefore, it
makes good business sense to incorporate into
product/process design a method for
anticipating and taking advantage of these
changes.
You should follow an MGPP in conjunction with
your business's overall marketing strategy. The
market process applied to MGPP usually takes place
over three or more generations. These generations
cover the first three to five years of product/process
development and introduction.
all N/A 0
Tool What does it do? Why use? When use? Data Type P < .05 indicates Picture
Multiple Regression
method that enables you to determine the relationship
between a continuous process output (Y) and several factors
(Xs).
Multiple regression will help you to
understand the relationship between the
process output (Y) and several factors (Xs) that
may affect the Y. Understanding this
relationship allows you to1. Identify important
Xs2. Identify the amount of variation explained
by the model3. Reduce the number of Xs prior
to design of experiment (DOE )4. Predict Y
based on combinations of X values5. Identify
possible nonlinear relationships such as a
quadratic (X12) or an interaction (X1X2)The
output of a multiple regression analysis may
demonstrate the need for designed
experiments that establish a cause and effect
relationship or identify ways to further
improve the process.
You can use multiple regression during the Analyze
phase to help identify important Xs and during the
Improve phase to define the optimized solution.
Multiple regression can be used with both
continuous and discrete Xs. If you have only discrete
Xs, use ANOVA-GLM. Typically you would use
multiple regression on existing data. If you need to
collect new data, it may be more efficient to use a
DOE.
Continuous X & Y
A correlation is
detected
0
Multi-Vari Chart
A multi-vari chart is a tool that graphically displays patterns of
variation. It is used to identify possible Xs or families of
variation, such as variation within a subgroup, between
subgroups, or over time
A multi-vari chart enables you to see the effect
multiple variables have on a Y. It also helps you
see variation within subgroups, between
subgroups, and over time. By looking at the
patterns of variation, you can identify or
eliminate possible Xs
Continuous Y & all X's N/A 0
Normal Probability Plot Allows you to determine the normality of your data.
To determine the normality of data. To see if
multiple X's exist in your data.
cont (measurement)
Data does not
follow a normal
distribution
1
Normality Test
A normality test is a statistical process used to determine if a
sample, or any group of data, fits a standard normal
distribution. A normality test can be done mathematically or
graphically.
Many statistical tests (tests of means and tests
of variances) assume that the data being
tested is normally distributed. A normality test
is used to determine if that assumption is
valid.
There are two occasions when you should use a
normality test:
1. When you are first trying to characterize raw
data, normality testing is used in conjunction with
graphical tools such as histograms and box plots.
2. When you are analyzing your data, and you need
to calculate basic statistics such as Z values or
employ statistical tests that assume normality, such
as t-test and ANOVA.
cont (measurement) not normal 0
np Chart
a graphical tool that allows you to view the actual number of
defectives and detect the presence of special causes.
The np chart is a tool that will help you
determine if your process is in control by
seeing if special causes are present. The
presence of special cause variation indicates
that factors are influencing the output of your
process. Eliminating the influence of these
factors will improve the performance of your
process and bring your process into control.
You will use an np chart in the Control phase to
verify that the process remains in control after the
sources of special cause variation have been
removed. The np chart is used for processes that
generate discrete data. The np chart is used to
graph the actual number of defectives in a sample.
The sample size for the np chart is constant, with
between 5 and 10 defectives per sample on the
average.
Defectives Y /
Continuous & Discrete
X
N/A 1
Out-of-the-Box Thinking
Out-of-the-box thinking is an approach to creativity based on
overcoming the subconscious patterns of thinking that we all
develop.
Many businesses are successful for a brief time
due to a single innovation, while continued
success is dependent upon continued
innovation
Root cause analysis and new product / process
development
all N/A 0
p Chart
a graphical tool that allows you to view the proportion of
defectives and detect the presence of special causes. The p
chart is used to understand the ratio of nonconforming units
to the total number of units in a sample.
The p chart is a tool that will help you
determine if your process is in control by
determining whether special causes are
present. The presence of special cause
variation indicates that factors are influencing
the output of your process. Eliminating the
influence of these factors will improve the
performance of your process and bring your
process into control
You will use a p chart in the Control phase to verify
that the process remains in control after the sources
of special cause variation have been removed. The p
chart is used for processes that generate discrete
data. The sample size for the p chart can vary but
usually consists of 100 or more
Defectives Y /
Continuous & Discrete
X
N/A 1
Pareto Chart
A Pareto chart is a graphing tool that prioritizes a list of
variables or factors based on impact or frequency of
occurrence. This chart is based on the Pareto principle, which
states that typically 80% of the defects in a process or product
are caused by only 20% of the possible causes
. It is easy to interpret, which makes it a
convenient communication tool for use by
individuals not familiar with the project. The
Pareto chart will not detect small differences
between categories; more advanced statistical
tools are required in such cases.
In the Define phase to stratify Voice of the
Customer data...In the Measure phase to stratify
data collected on the project Y..In the Analyze
phase to assess the relative impact or frequency of
different factors, or Xs
all N/A 0
Tool What does it do? Why use? When use? Data Type P < .05 indicates Picture
Process Mapping
Process mapping is a tool that provides structure for defining
a process in a simplified, visual manner by displaying the
steps, events, and operations (in chronological order) that
make up a process
As you examine your process in greater detail,
your map will evolve from the process you
"think" exists to what "actually" exists. Your
process map will evolve again to reflect what
"should" exist-the process after improvements
are made.
In the Define phase, you create a high-level process
map to get an overview of the steps, events, and
operations that make up the process. This will help
you understand the process and verify the scope
you defined in your charter. It is particularly
important that your high-level map reflects the
process as it actually is, since it serves as the basis
for more detailed maps.In the Measure and Analyze
phases, you create a detailed process map to help
you identify problems in the process. Your
improvement project will focus on addressing these
problems.In the Improve phase, you can use
process mapping to develop solutions by creating
maps of how the process "should be."
all N/A 0
Pugh Matrix
the tool used to facilitate a disciplined, team-based process
for concept selection and generation. Several concepts are
evaluated according to their strengths and weaknesses
against a reference concept called the datum. The datum is
the best current concept at each iteration of the matrix. The
Pugh matrix encourages comparison of several different
concepts against a base concept, creating stronger concepts
and eliminating weaker ones until an optimal concept finally
is reached
provides an objective process for reviewing,
assessing, and enhancing design concepts the
team has generated with reference to the
project's CTQs. Because it employs agreed-
upon criteria for assessing each concept, it
becomes difficult for one team member to
promote his or her own concept for irrational
reasons.
The Pugh matrix is the recommended method for
selecting the most promising concepts in the
Analyze phase of the DMADV process. It is used
when the team already has developed several
alternative concepts that potentially can meet the
CTQs developed during the Measure phase and
must choose the one or two concepts that will best
meet the performance requirements for further
development in the Design phase
all N/A 0
Quality Function
Deployment
a methodology that provides a flowdown process for CTQs
from the highest to the lowest level. The flowdown process
begins with the results of the customer needs mapping (VOC)
as input. From that point we cascade through a series of four
Houses of Quality to arrive at the internal controllable factors.
QFD is a prioritization tool used to show the relative
importance of factors rather than as a transfer function.
QFD drives a cross-functional discussion to
define what is important. It provides a vehicle
for asking how products/services will be
measured and what are the critical variables to
control processes.The QFD process highlights
trade-offs between conflicting properties and
forces the team to consider each trade off in
light of the customer's requirements for the
product/service.Also, it points out areas for
improvement by giving special attention to the
most important customer wants and
systematically flowing them down through the
QFD process.
QFD produces the greatest results in situations
where1. Customer requirements have not been
clearly defined 2. There must be trade-offs between
the elements of the business 3. There are significant
investments in resources required
all N/A 0
Reqression see Multiple Regression Continuous X & Y
A correlation is
detected
0
Risk Assessment
The risk-management process is a methodology used to
identify risks,analyze risks,plan, communicate, and implement
abatement actions, andtrack resolution of abatement actions.
Any time you make a change in a process,
there is potential for unforeseen failure or
unintended consequences. Performing a risk
assessment allows you to identify potential
risks associated with planned process changes
and develop abatement actions to minimize
the probability of their occurrence. The risk-
assessment process also determines the
ownership and completion date for each
abatement action.
In DMAIC, risk assessment is used in the Improve
phase before you make changes in the process
(before running a DOE, piloting, or testing solutions)
and in the Control phase to develop the control
plan. In DMADV, risk assessment is used in all
phases of design, especially in the Analyze and
Verify phases where you analyze and verify your
concept design.
all N/A 0
Root Sum of Squares
Root sum of squares (RSS) is a statistical tolerance analysis
method used to estimate the variation of a system output Y
from variations in each of the system's inputs Xs.
RSS analysis is a quick method for estimating
the variation in system output given the
variation in system component inputs,
provided the system behavior can be modeled
using a linear transfer function with unit ( 1)
coefficients. RSS can quickly tell you the
probability that the output (Y) will be outside
its upper or lower specification limits. Based
on this information, you can decide whether
some or all of your inputs need to be modified
to meet the specifications on system output,
and/or if the specifications on system output
need to be changed.
Use RSS when you need to quantify the variation in
the output given the variation in inputs. However,
the following conditions must be met in order to
perform RSS analysis: 1. The inputs (Xs) are
independent. 2. The transfer function is linear with
coefficients of +1 and/or - 1. 3. In addition, you will
need to know (or have estimates of) the means and
standard deviations of each X.
Continuous X & Y N/A 0
Tool What does it do? Why use? When use? Data Type P < .05 indicates Picture
Run Chart
A run chart is a graphical tool that allows you to view the
variation of your process over time. The patterns in the run
chart can help identify the presence of special cause variation.
The patterns in the run chart allow you to see
if special causes are influencing your process.
This will help you to identify Xs affecting your
process run chart.
used in many phases of the DMAIC process.
Consider using a run chart to 1. Look for possible
time-related Xs in the Measure phase 2. Ensure
process stability before completing a hypothesis
test 3. Look at variation within a subgroup; compare
subgroup to subgroup variation
cont (measurement) N/A 1
Sample Size Calculator
The sample size calculator simplifies the use of the sample
size formula and provides you with a statistical basis for
determining the required sample size for given levels of a and
b risks
The calculation helps link allowable risk with
cost. If your sample size is statistically sound,
you can have more confidence in your data
and greater assurance that resources spent on
data collection efforts and/or planned
improvements will not be wasted
all N/A 1
Scatter Plot
a basic graphic tool that illustrates the relationship between
two variables.The variables may be a process output (Y) and a
factor affecting it (X), two factors affecting a Y (two Xs), or
two related process outputs (two Ys).
Useful in determining whether trends exist
between two or more sets of data.
Scatter plots are used with continuous and discrete
data and are especially useful in the Measure,
Analyze, and Improve phases of DMAIC projects.
all N/A 0
Simple Linear Regression
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, where Y is the process output, b is a constant, m is a
coefficient, and X is the process input or factor
Simple linear regression will help you to
understand the relationship between the
process output (Y) and any factor that may
affect it (X). Understanding this relationship
will allow you to predict the Y, given a value of
X. This is especially useful when the Y variable
of interest is difficult or expensive to measure
You can use simple linear regression during the
Analyze phase to help identify important Xs and
during the Improve phase to define the settings
needed to achieve the desired output.
Continuous X & Y
indicate that there
is sufficient
evidence that the
coefficients are not
zero for likely Type I
error rates (a
levels)... SEE
MINITAB
0
Simulation
Simulation is a powerful analysis tool used to experiment with
a detailed process model to determine how the process
output Y will respond to changes in its structure, inputs, or
surroundings Xs. Simulation model is a computer model that
describes relationships and interactions among inputs and
process activities. It is used to evaluate process output under
a range of different conditions. Different process situations
need different types of simulation models. Discrete event
simulation is conducted for processes that are dictated by
events at distinct points in time; each occurrence of an event
Company's standard software tool for running discrete event
models.Continuous simulation is used for processes whose
variables or parameters do not experience distinct start and
running continuous models
Simulation can help you: 1. Identify
interactions and specific problems in an
existing or proposed process 2. Develop a
realistic model for a process 3. Predict the
behavior of the process under different
conditions 4. Optimize process performance
Simulation is used in the Analyze phase of a DMAIC
project to understand the behavior of important
process variables. In the Improve phase of a DMAIC
project, simulation is used to predict the
performance of an existing process under different
conditions and to test new process ideas or
alternatives in an isolated environment
all N/A 0
Six Sigma Process Report
A Six Sigma process report is a Minitab tool that provides a
baseline for measuring improvement of your product or
process
It helps you compare the performance of your
process or product to the performance
standard and determine if technology or
control is the problem
A Six Sigma process report, used with continuous
data, helps you determine process capability for
your project Y. Process capability is calculated after
you have gathered your data and have determined
your performance standards
Continuous Y & all X's N/A 0
Six Sigma Product Report calculates DPMO and process short term capability
It helps you compare the performance of your
process or product to the performance
standard and determine if technology or
control is the problem
used with discrete data, helps you determine
process capability for your project Y. You would
calculate Process capability after you have gathered
your data and determined your performance
standards.
Continuous Y, Discrete
Xs
N/A 0
Stepwise Regression
Regression tool that filters out unwanted X's based on
specified criteria.
Continuous X & Y N/A 0
Tree Diagram
A tree diagram is a tool that is used to break any concept
(such as a goal, idea, objective, issue, or CTQ) into
subcomponents, or lower levels of detail.
Useful in organizing information into logical
categories. See "When use?" section for more
detail
A tree diagram is helpful when you want to 1. Relate
a CTQ to subprocess elements (Project CTQs) 2.
Determine the project Y (Project Y) 3. Select the
appropriate Xs (Prioritized List of All Xs) 4.
Determine task-level detail for a solution to be
implemented (Optimized Solution)
all N/A 0
Tool What does it do? Why use? When use? Data Type P < .05 indicates Picture
u Chart
A u chart, shown in figure 1, is a graphical tool that allows you
to view the number of defects per unit sampled and detect
the presence of special causes
The u chart is a tool that will help you
determine if your process is in control by
determining whether special causes are
present. The presence of special cause
variation indicates that factors are influencing
the output of your process. Eliminating the
influence of these factors will improve the
performance of your process and bring your
process into control
You will use a u chart in the Control phase to verify
that the process remains in control after the sources
of special cause variation have been removed. The u
chart is used for processes that generate discrete
data. The u chart monitors the number of defects
per unit taken from a process. You should record
between 20 and 30 readings, and the sample size
may be variable.
N/A 1
Voice of the Customer
The following tools are commonly used to collect VOC data:
Dashboard ,Focus group, Interview, Scorecard, and Survey..
Tools used to develop specific CTQs and associated priorities.
Each VOC tool provides the team with an
organized method for gathering information
from customers. Without the use of structured
tools, the data collected may be incomplete or
biased. Key groups may be inadvertently
omitted from the process, information may
not be gathered to the required level of detail,
or the VOC data collection effort may be
biased because of your viewpoint.
You can use VOC tools at the start of a project to
determine what key issues are important to the
customers, understand why they are important, and
subsequently gather detailed information about
each issue. VOC tools can also be used whenever
you need additional customer input such as ideas
and suggestions for improvement or feedback on
new solutions
all N/A 0
Worst Case Analysis
A worst case analysis is a nonstatistical tolerance analysis tool
used to identify whether combinations of inputs (Xs) at their
upper and lower specification limits always produce an
acceptable output measure (Y).
Worst case analysis tells you the minimum and
maximum limits within which your total
product or process will vary. You can then
compare these limits with the required
specification limits to see if they are
acceptable. By testing these limits in advance,
you can modify any incorrect tolerance
settings before actually beginning production
of the product or process.
You should use worst case analysis : To analyze
safety-critical Ys, and when no process data is
available and only the tolerances on Xs are known.
Worst case analysis should be used sparingly
because it does not take into account the
probabilistic nature (that is, the likelihood of
variance from the specified values) of the inputs.
all N/A 0
Xbar-R Chart
The Xbar-R chart is a tool to help you decide if your process is
in control by determining whether special causes are present.
The presence of special cause variation
indicates that factors are influencing the
output of your process. Eliminating the
influence of these factors will improve the
performance of your process and bring your
process into control
Xbar-R charts can be used in many phases of the
DMAIC process when you have continuous data
broken into subgroups. Consider using an Xbar-R
chart in the Measure phase to separate common
causes of variation from special causes, in the
Analyze and Improve phases to ensure process
stability before completing a hypothesis test, or in
the Control phase to verify that the process remains
in control after the sources of special cause
variation have been removed.
Continuous X & Y N/A 1
Xbar-S Chart
An Xbar-S chart, or mean and standard deviation chart, is a
graphical tool that allows you to view the variation in your
process over time. An Xbar-S chart lets you perform statistical
tests that signal when a process may be going out of control.
A process that is out of control has been affected by special
causes as well as common causes. The chart can also show
you where to look for sources of special cause variation. The
X portion of the chart contains the mean of the subgroups
distributed over time. The S portion of the chart represents
the standard deviation of data points in a subgroup
The Xbar-S chart is a tool to help you
determine if your process is in control by
seeing if special causes are present. The
presence of special cause variation indicates
that factors are influencing the output of your
process. Eliminating the influence of these
factors will improve the performance of your
process and bring it into control
An Xbar-S chart can be used in many phases of the
DMAIC process when you have continuous data.
Consider using an Xbar-S chartin the Measure
phase to separate common causes of variation from
special causes, in the Analyze and Improve phases
to ensure process stability before completing a
hypothesis test, or in the Control phase to verify
that the process remains in control after the sources
of special cause variation have been removed.
NOTE - Use Xbar-R if the sample size is small.
Continuous X & Y N/A 1
Tool Summary
Regression Scatter plot Logistic regression
Time series plots Matrix Plot Time series plot
General Linear model Fitted line C chart
Multi-Vari plot Step wise Regression P chart
Histogram N chart
DOE NP chart
Best Subsets
ImR
X-bar R
ANOVA Kruskal-Wallis Chi Square
Box plots T-test Pareto
Dot plots Logistic Regression
MV plot
Histogram
DOE
Homogeneity of variance
General linear model
Matrix plot
Y's
X's
Continuous Data Attribute Data
C
o
n
t
i
n
u
o
u
s
D
a
t
a
A
t
t
r
i
b
u
t
e
D
a
t
a