Term
| five Lean Six Sigma steps applied to specific improvement projects |
|
Definition
| DMAIC: Define - Measure - Analyze - Improve - Control |
|
|
Term
| The five Six Sigma principals |
|
Definition
Identify Customers and specify value
Map the value stream
Create flow
Respond to Pull
Pursue perfection |
|
|
Term
| Parts of a thought process map |
|
Definition
First, create a problem statement.
Then: Question, Action, Answer |
|
|
Term
|
Definition
| Cost (Investment) to do it right the first time. Training, error-proofing, pre-production pilots, design for capability (DFSS - Design For Six Sigma). |
|
|
Term
|
Definition
| Cost of testing and inspection to detect defects internally. |
|
|
Term
| Define Internal Failure Cost |
|
Definition
| Defects detected internally: Scrap, rework, and "Seconds" sold off-price. |
|
|
Term
| Define External Failure Cost |
|
Definition
| Defects detected by customers, including warranty, replacements, allowances, product liability, customer dissatisfaction and lost revenue. |
|
|
Term
| Acronym with words for criteria for picking a project |
|
Definition
| SMART: Specific, Measurable, Achievable, Relevant, Time bounded |
|
|
Term
|
Definition
| A level that goes beyond the given entitlement of a project or process |
|
|
Term
|
Definition
| Tool used to organize and schedule the timeline for completing a project. |
|
|
Term
|
Definition
| Life does not stand still. Where there is no progress, there is disintegration |
|
|
Term
|
Definition
Insures that all team members are informed and able to do their jobs.
Responsible-The Do'er, performer of the action
Accountable-Who approves, and is accountable for the responsible's actions.
Consulted-Makes no decisions and is not held accountable, but must be approached for advice prior to final decisions
Informed-Informed before or after the action taken by the team. May have to make a decision after the action is taken based upon results. |
|
|
Term
|
Definition
| Critical to Quality Characteristics |
|
|
Term
| Three levels of Kano Model |
|
Definition
Basic - Dissatisfiers - Presence of these features or functions does not produce satisfaction, but their absence creates strong dissatisfaction.
Performance - Satisfiers - Increasing these features or functions leads to higher satisfaction.
Excitement - Delighter - Presence of these unexpected features or functions leads to "delight" or customers being "pleasantly surprised". |
|
|
Term
|
Definition
| Quality Function Deployment: Often referred to as the "House of Quality", QFD is a Hoshin Planning tool - a matrix used to translate the Voice of the Customer into Product Features, then Product Specifications, and ultimately, Process Parameters. |
|
|
Term
| Six sigma uses of (f)'s, X's and Y's |
|
Definition
| All of the X's are inputs into a process (f), which creates the output y. So y = (f) x |
|
|
Term
|
Definition
| The complete sequence of activities an organization performs in order to produce and deliver its end product or service. |
|
|
Term
| Name the 5 players in a Value Stream |
|
Definition
| It encompasses suppliers, internal processes, customers and end-users Supplier-Input-Processing-Output-Customer |
|
|
Term
| What does SIPOC stand for |
|
Definition
| Suppliers, Inputs, Processes, Outputs, and Customers |
|
|
Term
| What is the difference between variable and attribute data |
|
Definition
| Variable data comes from measurements on a continuous scale, such as: temperature, time, distance, weight. Attribute data is based on upon discrete distinctions such as good/bad, percentage defective, or number defective per hundred. |
|
|
Term
| What are the meanings of the following different symbols for a flow chart? Arrow, Square, small arrow, diamond, bullet shaped object, square with wavy bottom |
|
Definition
| Arrow = beginning or end, Square = activities, small arrow = Process flow direction, diamond = decision, bullet shaped object = delay, square with wavy bottom = document |
|
|
Term
| What are the 8 forms of waste? |
|
Definition
| DOWNTIME: Defects, Overproduction, Waiting, Neglected talents, Transportation, Inventory, Motion, Excess Processing (adding more value than the customer is willing to pay for) |
|
|
Term
|
Definition
| The amount of time taken to produce one product when the rate of production = customer demand exactly (no inventory, no shortfall created) |
|
|
Term
|
Definition
| The amount of time it takes to create a product from raw material receipt to shipment |
|
|
Term
|
Definition
| "We shall not cease from exploration, and the end of all our exploring will be to arrive where we started and know the place for the first time." |
|
|
Term
|
Definition
| The numerical characteristic calculated from the entire population |
|
|
Term
| For what are "Descriptive Statistics" used (as opposed to Inferential Statistics) |
|
Definition
| Summarize the important features of a population or process (Graphs, pie charts) |
|
|
Term
|
Definition
| Use sample data to help make comparisons through inference of the overall population. Regression, hypothesis tests |
|
|
Term
| Distinguish Discrete from Continuous measurements |
|
Definition
| Discrete measurement is a measurement that cannot be broken down further along the same lines ie. Boy vs girl. Continuous can be, time, size, etc. (fractions continuous broken down) |
|
|
Term
| Measurements: Distinguish continuous, counts, ordinal, nominal |
|
Definition
| Nominal has no order, ordinal has order but no number other than one, counts has a measurement other than one, and continuous can be broken down further |
|
|
Term
| 3 criteria to test the quality of your measurements? |
|
Definition
| Need to make sure that they do not have bias, that they are linear, and are stable |
|
|
Term
|
Definition
| Repeatable and reproducable results. Same person can perform repeatably, and another person can get the same results is reproducable. The term GRR is used for gauge reproducability and repeatability |
|
|
Term
|
Definition
| Throughput yield is a measurement taken at each step of the process (back to the issue of collecting reliable in-process defect information), based on the number of defects, the number of units processed, and the number of defect opportunities per unit. |
|
|
Term
| Define Rolled Throughput Yield |
|
Definition
| Rolled Throughput Yield is a process-wide metric used to express the probability that a given unit will make it through the whole system without a defect. Rolled Throughput yield is calculated by multiplying out all of the individual Throughput Yields |
|
|
Term
|
Definition
| Defects Per million Opportunities: Standard quantity for Six Sigma. Defects should be defined as each separate opportunity to fail to meet customer requirements - not each possible mode of failure. For example, consider a written document as the product. It's the misspelled word matters to customer. One, two letters within a word doesn't matter |
|
|
Term
| What are the two sources of variation |
|
Definition
| Chance (inherent in the process) and assignable or uncontrolled variation (changes over time) |
|
|
Term
What are the 6 out of control conditions: |
|
Definition
1) If one or more points falls outside of the upper control limit (UCL), or lower control limit (LCL). The UCL and LCL are three standard deviations on either side of the mean - see section A of the illustration below.
2) If two out of three successive points fall in the area that is beyond two standard deviations from the mean, either above or below - see section B of the illustration below.
3) If four out of five successive points fall in the area that is beyond one standard deviation from the mean, either above or below - see section C of the illustration below.
4) If there is a run of six or more points that are all either successively higher or successively lower - see section D of the illustration below.
5) If eight or more points fall on either side of the mean - see section E of the illustration below.
6) If 15 points in a row fall within the area on either side of the mean that is one standard deviation from the mean - see section F of the illustration below. |
|
|
Term
| For the XMR chart, what is the formula for the UCL |
|
Definition
| UCLx = Xbar + (2.66 x mean mR) |
|
|
Term
| For the XMR chart, what is the formula for the LCL |
|
Definition
| LCL(X) = Xbar - (2.66 x mean mR) |
|
|
Term
| For the XMR chart, what is the formula for the moving range UCL |
|
Definition
|
|
Term
What is the equation for calculating Cp and CpK |
|
Definition
Cp = (USL-LSL)/(6*Stddev)
Cpk = min {(XDBAR-LSL)/(3*STDDev),(USL-XDBAR)/(3*STDDev)} |
|
|
Term
| What are the three primary categories of investigation in the Analyze phase of the DMAIC cycle: |
|
Definition
Characterize the Process (What is the current state of affairs?) - Analyze I
Compare Treatments (Which treatment, or action, is more effective?) - Analyze II
Model the Process (Understand Relationships, How does X impact Y?) - Analyze III |
|
|
Term
| Assumptions underlying the Multiple Linear Regression model |
|
Definition
The response variable is continuous.
The predictor variables are justified by experience or theory.
The relationship between the response variable and each predictor variable is linear after controlling for all the other predictor variables in the model.
Each predictor variable is strongly correlated with the response variable but NOT with any other predictor variable in the model.
The relationship of each predictor variable with the response variable remains constant over the range of all the other predictor variables and over time.
The errors are independent, are normally distributed (with mean=0) and have constant variance (homoscedasticity). |
|
|
Term
What are the 6 factors you should observe when determining Sample Size |
|
Definition
| Parameters (limit what you're observing), Variance (in the population (not people)), Precision of Estimate (does it need to be if high then sample size increases), Significance Level, Cost and practicality |
|
|
Term
|
Definition
Rejecting the null hypothesis when it is true. Probability of this error is denoted by alpha. Also known as the significance level of a test |
|
|
Term
|
Definition
Accepting the null hypothesis when the alternative is true. Probability of this error is denoted by beta. Both errors exist at the same time |
|
|
