The flashcards below were created by user
RocketRN
on FreezingBlue Flashcards.

Steps of the project definition process
 1. Determine the Y {what needs to be improved
 2. Identify the associated processes and locations
 3. Determine the baseline performance for each Y
 4. Identify the cost and impact of problem
 5. Write the problem statement
 6. Write the objective statement
 7. Identify candidates for project team
 8. Obtain approvals and launch

Savings Categories
 Hard Savings  reduced expenses
 Soft Savings  happy customers buy more
 Potential savings  savings after implemetation

SIPOC Steps
{Suppliers, Inputs, Process, Outputs, Customers}
  Categorizing the process
  Categorizing the outputs
  Defining the outputs by their name, title, or organizational entity
  Defining the customer requirements
  Defining the inputsCategorizing the sources of the inputs

Fishbone Diagrams
Cause and Effect Diagram
Ishikawa Diagram
 Identifies 6 Categories:
 Measure
 Materials
 Men
 Methods {operating procedures}
 Machines {equipment}
 Mother Nature {environment}

Steps in Statistical Significance Testinng
  Form the research Hypothesis
  Form the Null Hypothesis
  Identify a probability of error level
  Identify and calculate the test for statistical significance
  Define the results

Chisquare Test
The Chisquare test uses three types of analysis:
Goodness of Fit It determines if the sample being used was taken from the population.
Test for Homogeneity It is based on the proposition that population is homogeneous in character.
Test for Independence It takes into consideration the null hypothesis.

Design of Experiments Tools
 Factorial Designs  help to analyze the effect of multiple factors on the process or the product
 Response Surface Designs appraise the relationship between one or more response variables and set of experimental variables
 Taguchi Designs These experiments help to locate the settings that aid in the consistency of the product or service over a variety of conditions.

Project Scope
Must include:
 Project Leader {Black Belt/ Green Belt}
 The Mentor/Master Black Belt
 Project Commencement Date
 Projected Project Conclusion Date

Product Attribute Classifications
 Basic/Threshold Attributes are those, which the customer normally assumes to be present in the product
 Performance/Linear Attributes The presence of performance attributes is directly proportional to customer satisfaction
 Exciters/Delighters These are hidden attributes which delight the customer and lead to high levels of satisfaction if they are present, but do not cause any dissatisfaction if the product lacks this feature

Survey Construction
{Measure of the Survey}
 Openended questions
 Ranking Questions
 Fillinthe blank
 Yes/No
 Likert’s scale  15 is better than 110
 Semantic differentials  very good and very bad.

Survey Construction Steps
 1. Develop measure of survey
 2. Design the Samples  how many people
 3. Develop the questionnaire
 4. Pilot Study  test small group of people
 5. Produce final questionnaire
 6. Dispatch Sample {mailings}
 7. Collect completed questionnaires
 8. Collate and reduce data to enable analysis
 9. Analyze the data

Critical to Quality Tree Steps
1. Identify the Customer
2. Identify the Customer's Needs
3. Identify the first set of requirements for this need {2 or 3 measures}
4. Try to take each level 2 element to another degree
5. Validate the requirements with the customer

The Project Charter Should Include
 A full account stating the motive of undertaking the project
The final product of the process/project and its characteristics
The association linking the business need and the final product/result
The approval to apply the various resources available to the project/process

A good Six Sigma Project should have
They have to be given the go ahead by the management
They should be in tangent with the organization's goals
They should have clearly demarcated goals
They should be of manageable size

Important steps in developing a Process Map
  Select a process to be mapped
  Define the process
  Map the primary process
  Map alternative path
  Map inspection points
  Use map to improve the process

Steps for Interrelationship Diagram
1. The group has to agree on the particular issue or question.
2. Write down the all the factors on chits of paper.
3. Link each factor to all others. An arrow also known as “influence arrow” to link related factors can be used.
4. Draw the “influence arrows” from the factors that influence to those which are influenced.
5. If two factors influence each other, the arrow should be drawn to reflect the stronger influence.
6. Count the arrows.
7. The elements with the most outgoing arrows will be root causes or drivers.
8. The ones with the most incoming arrows will be key outcomes or results.

Tree Diagram Uses
Tree diagrams are used to break down a large idea, problem or solution into smaller and more manageable parts. This helps to understand the problem or implement the solutions more effectively

Matrix Shapes
 Lshaped matrix relates two set of elements with each other, and sometimes one set of elements with itself. The elements are compared by placing them in the first row and top column.
 Tshaped matrix relates three set of elements in such a way that sets X and Y are related to Z, but X and Y are not related to each other.
 Yshaped matrix also relates three set of elements in such a way that each set is related to the other two set of elements. Suppose X and Y are related to Z, then X and Y must also be related to each other.
 Xshaped matrix relates four set of elements and each set is related to two other set of elements in a circular manner.
 Cshaped matrix relates three set of elements and that too simultaneously, in a 3dimensional manner.

Common Symbols in Matrix Charts

Key Ojectives of the Measure Phase
 Identify key measures, make a data collection plan and execute the same
 Establish current process capability, improvement and goal
 Display variation

A Data Collection Plan Includes
• A list of questions, which should be answered by the data collected
• A brief overview of the project, along with the problem statement
• Determining the data type which will be suitable for the data a process is generating
• Determining the number of iterations of the data collected that will be enough to present the change in the chart
• A list of the measures to be taken, once the data has been collected

Types of Data
 Attribute Data {Category Data}  cannot be broken down into smaller units ie: medium + large doesn't yield a value
 Variable Data  {Continuous Data}  data that can have any value on a continuous scale

Steps to creating a Trend Chart
  Data Gathering
  Data Organizing
  Preparing the chart
  Interpreting the chart

Types of Attribute Control Charts
 C Chart  This control chart deals with the number of defects and nonconformities
 produced by a manufacturing process
 PCharts  This control chart deals with the proportion or a fraction of a defective product
 UCharts  chart which handles defects per unit. The average number of nonconformity per unit of product is plotted.
 XBar Charts  a set of control charts for variable data. This chart is advantageous when changes in mean value are to be shown.

Three Types of Probability Sampling
 Simple Random Sampling  each element in the sample space has an equal change of getting selected
 Stratified Sampling  non homogeneous data is divided into homogeneous strata. Each strata gets a random sampling.
 Systematic Sampling  Each n^{th }element is selected from the sample space. n=number in population/number in sample
 Clustered Sampling  all units are grouped into clusters and a number of clusters are selected randomly.

The logical way to initiate analysis:
 • list all the possible factors of the problem
 • segment and stratify these factors
 • prioritize the list of vital few factors
 • verify and quantify the root causes of variation

Analysis can be done in two ways:
In the Measure phase when the goal if the team is to improve effectiveness {data analysis}
In the Define Phase if the goal is to improve efficiency {process analysis}

Categories of Nonvalue adding steps
Inhouse failures: These are procedures involving rectification of errors or defects in a process. These usually begin with the word ‘re’. They are signs of inhouse failures. For e.g. retest, recall etc.
Peripheral failures: These are procedures involving rectification of errors or defects pointed out by the customers.
Control/ inspection: These are procedures involving reviewing, checking, verifying, the previous or the value adding steps. They are considered as nonvalue adding steps.
Delays or hold up: These are the most common non valueadding step. These could be hold up in a process or waiting for delivery of the supplies.
Groundwork time: These are procedures, which set up the process for following activity.
Moves or shifts: It involves moving of the parts from one place to another to get them assembled, build, or moving the finished parts to the warehouse or stockroom for storage. It is a non valueadding step. There is also the possibility of damage to the finished product in this step.

Rot Cause Analysis Goal
to identify the most specific underlying reasons, which are responsible for the problem. This will help in arriving at suggestions and recommendations to improve it.

Steps of Root Cause Analysis
 Open
 1. Brainstorming
 2. Cause and effect Diagram (Fishbone)
 Narrow
 1. Clarification and Duplication
 2. MultiVoting {group prioritizes brainstormed ideas}
 3. Five Why Diagram  gets to the root cause

Types of Correlations
Strong Correlation  almost all the points fall on the line.
Moderate Correlation  an average number of points fall along the line
No Correlation  all points are randomly scattered

Run Charts
{Line Graphs}
Run charts are basically used for keeping a check on the process’ performance.
Run charts are useful in discovering the patterns that occur over time.
Run charts are easy to interpret; any one can guess from the chart’s behavior whether the process’ performance is normal or abnormal.

Steps to a Hypothesis Test
Create Null Hypothesis (H0)  the problem is due to a random chance
Create Alternate Hypothesis (H1)  created if it can be statistically proven that the H0 is false
Identify a Test Statistic  the quantity calculated from the data values that will be the subject of the test
Obtain the Null Distribution  the sample distribution of the test statistic provided that H0 is true.
Comparing the observed statistic to the H0  H0 is rejected as unlikely if the test statistic falls in a satisfactorily questionable area of H0. H0 is not rejected if the test statistic falls within the scale of normal values depicted by the null distribution.

