LSS SIX SIGMA EXAM 1
X bar
Average of the raw data
Recorded values reflecting length, volume, and time
Measureable, Continuous, Variable
Distributions bounded at the left by zero
Lognormal, Weibull, and Exponential Distributions
5M and E version of the cause and effect diagram
Machine, Material, Method, Manpower, Measurement, and Environment
4M Version of the Cause and Effect Diagram
Machine, Material, Method, and Manpower
Continuous Probability Distributions
Normal, Log-normal, Exponential, Extreme Value, F, Student t, Chi-square, and Weibull
Project Scope
The boundaries of the project
Unintended Needs
The customer uses the product in an unintended manner
QFD
The desires of the customer and how to make a produce or process meet them; a customer driven process which is implemented by the organization; includes customer competitive assessment and technical results
Process Capability Analysis
The determination that the process can meet the product specifications as intended; Recognizing the nature of process variability the process capability target is usually tighter than product specifications
Bimodal
The distribution has two modes (two peaks on the curve).
Exponential
The distribution used to describe the time between failures which occur independently and at a constant rate. The mean and standard deviation are equal.
Market Segmentation
Targeted subsets of the market
Traceability
The accuracy of a measuring instrument linked to the U.S. National Standards.
Confidence Interval
A 90% confidence interval means that given the sample data, there is a 90% chance that the true population mean is contained in the interval. As sample size increases the width of the interval decreases.
Defector
A customer that has been lost
Terrorist
A customer who has turned against you and will spread ill-will regarding your company and product
Confidence interval for population variance
A function of n-1 based on the chi-square distribution
Balanced Scorecard
A method or process for managers to focus on business performance metrics, strategy management, financial metrics, stakeholder interests
Statistic
A number derived from sample data that describes the data in some useful way; Sample Value
Variables
A quality which can assume several (more than two) values
Perceptual Map
A specialized matrix diagram that captures the perceptions of a customer; items of customer importance vs customer's corresponding satisfaction level
Flowcharting
A tool frequently used in the audit. Can reveal wasted manpower or resources, excess handling, or extra processing. Can find holes, gaps, or weak areas in the control system; There can be multiple paths through the flowchart, there can only be a single process flow start point, flow charts can have parallel processes, a flow chart can have multiple end points; Asking why we do it this way, asking what would make it perfect, analyzing each step in detail, a comparison with processes different than your own
Customer Life Cycle
Acquisition, Retention, Attrition, Defection, and Reaquisition
Conformance
An affirmative indication that a product or service has met the requirements.
Ratio
An extension of the interval level that includes an inherent zero starting point. Data is interval data with a natural zero point. For example, time is ratio since 0 time is meaningful. Degrees Kelvin has a 0 point (absolute 0) and the steps in both these scales have the same degree of magnitude.
Sample Data
Any sample size if randomly selected can be suitable for audit purposes, since we are not directly performing lot acceptance or rejection; Coding and rounding affect both the mean and standard deviation
Checklists and Flowcharts
Basic quality tools most applicable for a work team to use when there is a desire to follow procedures and work instructions more closely
Hierarchy of Customer Expectations
Basic, Expected, Desired, Unanticipated
Tools that display the same data reads on a continuous scale
Boxplots, histograms, and stem and leaf plots
Fishbone (AKA Cause and Effect Session, AKA Ishikawa Diagram) Parts
Brainstorming, Prioritizing, Action plan development; problem statement is at far right; it takes time to perform and prioritize and it does not develop an action plan; Separate a problem into smaller components, show how various causes interact, display many possible causes in a graphical manner
Organization Chart
Can show organizational deficiencies
Team Membership
Composition of the Improvement Team
Truncated
Cut off in some way and is not normal
Purpose of Milestones
Keeping the project on track
Interval
Data is like ordinal except we can say the intervals between each value are equally split. The most common example is temperature in degrees Fahrenheit. The difference between 29 and 30 degrees is the same magnitude as the difference between 78 and 79. With attitudinal scales and the Likert questions you usually see on a survey, these are rarely interval, although many points on the scale likely are of equal intervals.
Variable Data
Data that are measured with some sort of instrument, such as a micrometer, tape measure, or watch.
Attribute data
Data that can be counted
Nominal
Data that consists of names or categories only. Basically refers to categorically discrete data such as name of your school, type of car you drive or name of a book. This one is easy to remember because nominal sounds like name (they have the same Latin root).
Ordinal
Data that is arranged in order (and differences between values cannot be determined or are meaningless). Refers to quantities that have a natural ordering. The ranking of favorite sports, the order of people's place in a line, the order of runners finishing a race or more often the choice on a rating scale from 1 to 5. You cannot state with certainty whether the intervals between each value are equal. For example, we often using rating scales (Likert questions). On a 10 point scale, the difference between a 9 and a 10 is not necessarily the same difference as the difference between a 6 and a 7. This is also an easy one to remember, ordinal sounds like order.
Problem Statement
Details the issue that the team wants to improve and a reference to the baseline measurement
Process Variation Establishment
Determined by examining the variation between part averages that are averaged among inspectors
Reproducibility
Determined by examining the variation between the average of the individual inspectors for all parts measured
Repeatability
Determined by examining the variation between the individual inspectors and within their measurement readings
Venn Diagram (AKA Set Diagram)
Diagrams that show all possible logical relations between a finite collection of sets (aggregation of things). Typically circles.
Histogram (Relative frequency chart or graph)
Displays the distribution of a sample (not a population), often the readings are grouped into uniform intervals
Scatter Diagram
Displays the relationship between variables; produces correlation coefficients
Process Shift
Due to rapid shifts in the process pattern being plotted. Events that could prompt such a change include a change in crew (machine settings) or a change in measuring device or method (not gradual tool wear or a reduction in defective level due to Kaizen techniques).
Calibration department duties
Ensuring traceability of all calibrations to a standard laboratory, maintaining and adequate record system, suspending measuring equipment from use when conditions warrant, identifying equipment with a label indicating calibration status
Recording Checksheets
Generally used for tally counts or attribute data, including machine, operator, characteristic, and so on; subjective data can be recorded on a checksheet; can record variable, attribute, and locational data
Accuracy
Getting an unbiased true value; The accuracy level of an instrument when compared to a standard can only be less than or equal to the standard to which it is compared
Precision
Getting consistent results repeatedly, the agreement or closeness of measurements on the same item
Stem and Leaf Plot
Graphical data method that can show the value of all individual readings
Cumulative Distribution Function
Graphical display of the total percentage of results below a certain measurement value
Discrete (attribute based) Distributions
Hypergeometric, binomial, and Poisson
Measles Charts
Identify locational data; useful to show visually where x occurs
Matrix (AKA Prioritization Matrix) Diagrams
Identify the impact that various process input variables could have on key process output variables
Benchmarking
Normally undertaken by a company or organization for the purpose of finding a leader in an area felt to be deficient, developing methods of measuring performance, and identifying gap between the present and desired performance; typically ignored because of the perceived barriers to sharing internal company information; Sequence: Understand your own processes, identify improvement criteria, measure competitive performance, and implement significant improvements
Skewed
Not symetrical and not normal
Checklists
Often used for attribute or counted information
Problem with Complaint Cards
Only 10% of the complaints are recorded
Parameter
Population value
Main disadvantage of presenting a team with an initial project lasting more than 160 days
Possibility that the team will expand the project boundaries
Normally distributed process
Predictable
Sensitivity
Reading to one decimal greater than the reported dimension; the ability to detect differences in measurement
Standardization
Reduces the nuber of characteristics or features of a system
R&R Study allows you to determine
Reproducibility, Process Variation, and Repeatability; can determine measurement error
Alpha Risk (AKA Type I)
Risk to reject a true hypothesis
Best approach when selecting quality measuring devices
Select those which integrate most efficiently with the entire quality system
Project Business Case
Short summary of strategic reasons for the project
Indicating Gage
Shows the amount of variation in size from the specification
House of Quality
Side walls = indicated by customer needs and customer competitive assessment; foundation = the technical competitive assessment; ceiling = design features
Focus Groups
Small groups with a specific topic
Cultural Needs
Status of the product (a BMW)
Total Defects Per Unit (TDPU) Formula
TDPU = -ln(RTY)
Capability
The long term performance level after a process has attained statistical control.
Weibull Scale Parameter
The point at which 63.21% of all values fall below
General term for the binomial distribution
The probability of occurrence of an event of interest (termed as a success) with n trials and with f failures, then the number of occurrences follows this type of distribution
Rolled Throughput Yield Calculation
The product of the yields of all process steps
Beta Risk (AKA Type II)
The risk of a hypothesis not being rejected when it is false. The risk when the null hypothesis is not rejected and it should be.
Coefficient of Variation
The standard deviation as a percent of the mean; = (Standard Deviation / Mean) * 100
Variance
The sum of the squared deviations of a group of measurements from their mean divided by the number of measurements
Master (AKA Reference Gage)
The working gage for accuracy prior to measuring the product
Random Selection
Theoretically means that each item in the lot had an equal chance to be selected
Process Management
Ties together the activities of a company
F distribution
To test for equality of variances from two normal populations
Business Process Management
Understanding, controlling and improving an organization's processes to create value for all stakeholders
Poisson Distribution
Used to model rates. The probability of exactly r events occuring can be computed using this (get a Poisson Table); has a mean equal to the variance; use ex: can tell you the # of defects per disk drive or the # of defects per automobile; widely used in queuing theory
Pareto Diagram
Used to prioritize problems
Process Mapping
Used to visualize the process being described, check current processes for duplication or redundancy (unnecessary complexity), and to assist in work simplification
Hypergeometric distribution
Used when there are two possible outcomes on each trial, but the probability of success on each trial differs because there is sampling without replacement; can model discrete data when the population size is small compared to sample size
Real Needs
What the customer really wants (transportation)
Perceived Needs
What the customer thinks is desired (a new car)
Stated Needs
What the customers say they want (a car)
Mode
measure of the central location for the nominal scale, a very low level statistic
Lifetime worth
the best measurement of the value of a customer
Cumulative Frequency Graph (AKA Ogive)
the frequencies are cumulative, each class frequency is added to the total of all previous class frequencies
t distribution
to compensate for error in the estimated standard deviation of small sample size
Chi-square distribution
to make decisions and construct confidence intervals by summing the square of normal random variables
Sampling plans for both inspection and auditing consider three things
validity, applicability, and known risks