RMS Six Sigma Training 2010 Final

1
RMS Six Sigma Training
Credit to multiple data sources including Villanova University Black Belt
and Green Belt Courses, Six Sigma Memory Jogger I and II, and Lean Six Sigma
Pocket Toolbook.
Define Measure Analyze Improve ControlMeasure

2
Define Measure Analyze Improve Control
What is Six Sigma?
The Six Sigma methodologies are a business philosophy and initiative
that enables world-class quality and continuous improvement to
achieve the highest level of customer satisfaction. Metrics are
established that align an Organizations’ strategic goals and values to
that of their customer’s needs and expectations.
MeasureMeasure

3
How Does it Work?
• Uses Data and Statistical Tools to Systematically
Improve Processes and Sustain Results
• Process Metrics are Evaluated
• Comparison of Average and Variation to Performance
Specifications or Targets
• Methodology is a Project-Focused Approach
Consisting of Five Phases-DMAIC

4
Who Uses Six Sigma?
The following companies claim to have successfully implemented Six Sigma in some form or another:
• 3M
• Advanced Micro Devices
• Air Canada
• ALCAN
• Amazon.com
• Bank of America
• Boeing
• Caterpillar Inc.
• CIGNA
• Dell
• Delphi Corporation
• DHL
• Deutsche Telekom
• Dow Chemical Company
• DuPont
• Ecolab
• Ford Motor Company
• General Electric
• GlaxoSmithKline
• Heinz Co.
• Honeywell
• HSBC Group
• Ingram Micro
• LG Group
• Lockheed Martin
• Merrill Lynch
• Merck
• Motorola
• Nielsen Company
• Nortel Networks
• Northrop Grumman
• Penske Truck Leasing
• Quest Diagnostics
• Samsung Group
• Siemens AG
• Staples Inc.
• Target Corporation
• Teradyne
• The Hertz Corporation
• Toshiba
• United States
Armed Forces
• Vodafone
• Whirlpool
• Xerox
Source: Wikipedia
Measure

5
Affinity
Diagram
Comm Plan
CTQ Tree
Data Collection
Kano Model
Pareto Chart
Run Chart
SIPOC
Tollgate
VOC
Control Charts
Frequency Plots
Check sheet
Flowchart
Histogram
Kano Model
Pareto Charts
Process Sigma
Run Chart
Loss Function
Tollgate Review
Brainstorming
Cause and Effect
Diagram
Design of
Experiments
Control Charts
Histogram
Hypothesis Test
Interrelationship
Diagraph
Scatter chart
Tree Diagram
Tollgate Review
Gantt Chart
Brainstorming
Control Charts
FMEA
Histogram
Design of
Experiments
Pareto Chart
PDCA
Prioritization
Matrix
Process Sigma
Run Chart
Tollgate
Communication
Plan
Control Charts
PDCA Cycle
Process Mgmt
Chart
Run Chart
Six Sigma
Storyboard
Pareto Chart
Prioritize Matrix
Affinity Chart
Pareto Chart
Activity Network
PDPC
QFD
Tollgate Review
Control Charts
The Tools of Six
Sigma
Source: Villanova University Six Sigma Lectures
Measure

6
DMAIC Overview
DMAIC – Tollgate Subdivisions by George Eckes
Measure
Project Charter
ID & validate customer needs and requirements
High level picture of the target process
Create a collection plan
Implement plan, compute baseline sigma
Examine data
Watch the process
Determine root cause
Generate solutions
Select solutions
Implement solutions
Pick the right control method
Document the response planControl
Define
Measure
Analyze
Improve

7
Team Roles
within a Six Sigma Organization
Master Black
Belt
Trains and coaches Black Belts and Green Belts. Functions more at the Six Sigma program
level by developing key metrics and strategic direction. Acts as an organization's Six Sigma
technologist and internal consultant
Black Belt Leads problem solving projects. Trains and coaches project teams
Green Belt
Assists with data collection and analysis for Black Belt projects. Leads Green Belt projects
or teams.
Yellow Belt
Participates as a project team member. Reviews process improvements that support the
project.
White Belt
Can work on local problem-solving teams that support overall projects, but may not be part of
a Six Sigma team. Understands basic Six Sigma concepts from an awareness perspective.
Measure

8
Executive Roles
within a Six Sigma Organization
Champions
Translate the company's vision, mission, goals and metrics to create an
organizational deployment plan and identify individual projects. Identify
resources and remove roadblocks.
Executives
Provide overall alignment by establishing the strategic focus of the Six
Sigma program within the organization's culture and vision.
Measure

9
Purpose
• Define
Business
Metrics
• Identify
Projects for
Process
Improvement
• Identify
Resources for
Process
Improvement
Tools
• SIPOC
• Understanding
the Voice of the
Customer
• Kano
• QFD
Key Outputs
• Project Charter
• Project Team
• Management
Commitment

10
Projects and Process Improvements are based on Customer’s Needs and Requirements
Definition
Needs Establishes the relationship between the company &
the customer
Requirements Characteristics that determine whether the
customer is satisfied
Notes:
• It is very important to establish
clear metrics and goals to validate
satisfaction levels

11
 Projects begin with understanding
 Projects end with meeting
Six Sigma and VOC

12
In order to improve upon a process, you must first understand the process.
The SIPOC Method can help…
SIPOC is used to document a process at a high level
and visually show the process

13

14
Supplier Inputs Process Outputs Customer
News Newspaper /
Internet
Select
Dealership
Dealership Car Test Drive
Manufacturer Brochure Select Option
Package
Car Chosen Purchaser
Customer Information /
Offer
Negotiate Financing /
Price
Purchaser’s
Family
Finance
Company
Credit Info Finance Contract
SIPOC Diagram

15

16
Another SIPOC
Example
Inputs Process Output CustomerSuppliers
Nurse
Doctor
Diagnosis
Admis
Discharge
Prescrip
Billing
Referral
Treatment
Hospital
Patient
Family
Insurance
Drugs
Medical
Equip
Patient
records
911
Paramedic
Drug man
Medical
Equip man
Inputs Process Output CustomerSuppliers
Nurse
Doctor
Diagnosis
Admis
Discharge
Prescrip
Billing
Referral
Treatment
Hospital
Patient
Family
Insurance
Drugs
Medical
Equipment
Supplier
Patient
records
911
Paramedic
Pharmaceutical
Supplier
Medical
Supplier

17

18
Take care of your customers’ expectations in sequence
from expected to normal to exciting!
• Our customer’s basic
servicing expectations

19

20

21

22

23

24

25
Develop Affinity Heading Cards
• What do our customers want?

26

27

28

29

30

31
Post the QFD where all the teams can refer to it
often, to better understand why decisions are made!
Usage:
• Fully understand BPO
customer needs at initiation
of services
• Clearly prioritize key
requirements (DSO, Aging
Reduction, AHT)
• If possible, learn from
competition

32
What is a Project Charter?
The project charter defines all interactions of the project and sets the
stage for a successful completion.
A project charter is the first step in the Six Sigma methodology. It
takes place in the Define step of DMAIC, and the charter can make or
break a successful project. It can make it by specifying necessary
resources and boundaries that will in turn ensure success; it can
break it by reducing team focus, effectiveness and motivation.
Usage:
• Provides written and agreed upon
details for short term projects

33
Project Title: Sales Analysis
Business Case:
(A broad definition of the issue as well as the
rationale for why this project should be a business priority.)
Sales at Company X has been growing annually, but it has experienced unusually
low sales during July/Aug. Management is concerned about implications to their
stock price.
Document Your Project Using a Project Charter

34
Problem/Opportunity Statement:
1 or 2 sentences describing the symptoms, such as where is the problem,
how big is the problem, or what is the impact.
Low July/Aug sales in the eastern region have declined 20%. Other
regions have not seen a decline in sales.
Gap between desired state and current state

35
Problem/Opportunity Statement:
Low July/Aug sales in the eastern region have declined 20%.
Goal Statement
Problem Statement and Goal statement are a matched pair.
Measurable target for desired results and completion target date.
SMART – Simple, measurable, accurate, realistic, timely
Identify & eliminate the cause of low sales
in the Eastern region by December 1 so that
Eastern region sales rebound by 25%
by the end of 1st quarter 2007.
Benchmark – George Eckes – 50% improvement
Usage:
• Use the “SMART” tip when writing
goals for clear down and backlog
reduction plans

36
Project Scope:
Where does the project start and stop? Where does the
process start and stop? Identify
constraints and assumptions.
The 7 member team will begin analysis of the Eastern sales
process on September 1 and report their findings on
November 1.
Budget $25,000. Analyze process from 1st sales call to thru
close of sale. Does not
includes all sales leads.
Usage:
• Very important in the
front end of initiating
services with new
customers
• FTE Analysis
• Scope Creep
• Clearly defined for the
customer

37
Purpose
• Establish
Baseline
Performance
• Identify
Validate
Measurements
for Project
Improvement
Tools
• Descriptive
Statistics
• Central
Tendency
• Dispersion
• Basic Statistical
Process
Control SPC
• Process Flow
Diagram
Key Outputs
• Data Collection
Plan
• Performance
Baseline-
DPMO
• Six Sigma Level
• Current
Process Flow
Chart

38
A Data Collection Plan will help organize and validate what is to be measured.
Data Collection Plan
WhattoMeasure
Typeofmeasure
TypeofData
OperationalDefinition
Specification
Target
DataCollectionForm
Sampling
BaselineSigma
Data Collection Plan
WhattoMeasure
Typeofmeasure
TypeofData
OperationalDefinition
Specification
Target
DataCollectionForm
Sampling
BaselineSigma
Measure

39
Usage:
• ACD Stats
• Aging Reduction
• AR Roll
• DSO
• Productivity
Examples
Quality • Product or Service Features
• Attributes
• Dimensions
• Scrap
• Rework
• Reliability
Cost • Labor
• Material
• Overhead
• Repair Costs
Speed • Lead Times
• Delivery Times
• Turnaround Times
• Setup Times
• Cycle Times
• Delays
What to Measure?
Measure

40
Measure

41
Input Metrics Process Metrics Output Metrics
• Accuracy of Customer Order
• Quality of Ingredients
• Cooking Time
• Preparation Sequence
Taste Quality
• Time to Receive Order
• Time to Gather Ingredients
• Time to Prep Food
• # of Process Steps
• Time to Cook Food
• Wait Time between Steps
Door to Door lead time Speed
• # and $ of Ingredients • # of Process Steps $$$ Cost
What is Important to the Customer?
Measure

42
Measure

43
Measure

44
Measure

45
Measure

46
Measure

47
Measure

48
Operational definitions are clear and precise instructions on
how to take a particular measurement.
Connection:
• 8 hour day vs. 7.5 hour
day
• Productivity Calculation:
• Unique Touches by
Account
• Touches per Week at
Invoice Level
Source: http://www.isixsigma.com/index.php?option=com_k2&view=item&id=1265:&Itemid=49
Measure

49
The customer’s ideal
performanceThe customer’s least
acceptable product
or service
VOC: Voice of the CustomerSource: Villanova University Six Sigma Lectures
Measure

50
Measure

51
Measure

52
Measure

53
Usage:
• Root Cause
• Synergy Categories
(Start-up / Promises)
• Aging Results
Measure

54
Usage:
• Synergy Categories
(Start-up / Promises)
• Aging Results
Measure

55
Measure

56
Measure

57
Usage:
• Calls per Hour
• Actions per Hour
• ACD Statistical Analysis
(AHT, Abrate)
Measure

58
Measure

59
Usage:
• Visual Displays
• Correlation Analysis
• Tenure of Employees &
Productivity Rate
Measure

60
Measure

61
Usage:
• Production Rates
• Collection Rates
• ACD Statistics
Measure

62
Measure

63
 = level of precision (margin of error) desired from
the sample in the same units as the “s” measurement
Example:
• The standard deviation for
collector production is +/- 4
calls per hour. Average is 10
calls per hour
• See page 80 for a simple
definition of standard deviation
Measure

64
Measure

65
Measure

66
What is Sigma?
A Simple Definition
• Six Sigma is a statistical term that equates to 3.4 defects per one
million opportunities.
• Today, most organizations operate at around three
sigma, which translates into roughly 67,000 defects
per million opportunities.
• This methodology eliminates defects from existing
processes, products, and services, saving millions
of dollars every year and increasing customer satisfaction.
Measure

67
Performance
Level SIGMA DPMO
A+
A
B
6
5
4
3.4
233
6,210
C 3 66,811
D 2 308,770
F 1 697,672
Handbook – Appendix XII-3
Sigma Levels
Measure

68
What is an Opportunity?
Opportunity is any area in a product or service where a defect could
be produced. Opportunities are things which must go right to satisfy
the customer.
• Exact name on credit card
• Billing address of credit card
• Credit card number
• Expiration date
• Product ID being ordered
• Quantity
Six Sigma Term
• DPMO = Defects per Million Opportunities
Measure

69
Example:
Formula
Defects
(# of Opportunities *
Sample Size)
Measure
DPMO =

70
Simplify Sigma
±6s
mLSL USL
1s 2s 3s 4s 5s 6s1s2s3s4s5s6s
As my sigma (standard deviation of my data set) gets smaller,
I am able to‘fit in’ more sigmas before I reach my customer specs.
The sigma value(or the standard deviation) gets smaller (3.2 to 1.6),
but the sigma levelsgets larger. We want the sigma level to increase.
SigmaValue/
StandardDeviation
Customer
Specification
Upper Limit
Customer
Specification
Lower Limit
Average
Measure

71
What is Standard Deviation?
A Simple Definition
• The statistical measure of spread and variability in a distribution of data.
(Variability will always exist in a data set because not every individual is going to have
the exact same value)
Examples:
• Prices of Homes vary from House to House and Year to Year
• Grades in a Class vary among Students
• Household Income varies from Household to Household
• Standard Deviation represents the typical distance from any point in the data
set to the center
Formula
S=
Measure

72
Standard Deviation - A Simple Example
S=2
2 2
6
4 8
X = Average = (4+8) / 2 = 6
Steps:
1. Find the arithmetic mean (or average) of 4 and 8
(4+8) / 2 = 6
2. Find the deviation of each number from the mean
4-6= -2 and 8-6 = 2
3. Square each of the deviations (amplifying larger deviations
and making negative values positive)
(-2) * (-2) = 4
2 * 2 = 4
4. Sum the obtained squares (as the 1st step to obtain an
average)
4+4 = 8
5. Divide the sum by the number of values, which here is 2
(giving an average)
8 / 2 = 4
6. Take the non-negative square root of the quotient
(converting squared units back to regular units)
 4 = 2
Suppose we wished to find the standard deviation of the set of the numbers 4 and 8.
So, the standard deviation of the set = 2.
Mean
Source: Wikipedia
Measure

73
Standard Deviation – Calls per Hour
Jan Feb Mar Apr
Mary 21 18 23 20
John 20 21 19 23
Joe 19 22 21 N/A
Sandy 22 19 23 21
Melissa 20 22 24 20
Dave N/A N/A 21 22
Name
Month
DataCalculation
X X X-X (X-X)
Result Average Deviation Deviation Squared
21 21 0 0
20 21 1 1
19 21 2 4
22 21 -1 1
20 21 1 1
18 21 3 9
21 21 0 0
22 21 -1 1
19 21 2 4
22 21 -1 1
23 21 -2 4
19 21 2 4
21 21 0 0
23 21 -2 4
24 21 -3 9
21 21 0 0
20 21 1 1
23 21 -2 4
21 21 0 0
20 21 1 1
22 21 -1 1
441 50
1) Calculate the Average. This is done by dividing the Sample Size by the Number of Results. The
calculation is 441/21=21. The average is 21. All information used to calculate the Average is
located in the Data Table.
2) Calculate the Deviation for each Result. This done by subtracting each Result from the
Average. Examples of these calculations are 21-20 = 1 (1 is the deviation), 21-21=0 (0 is the
deviation) etc. The Deviation for each Result is located in the Deviation Column on the
Calculation Table.
3) Square each Deviation. The Squared Deviation for each Result is located in Deviation Squared
Column on the Calculation Table.
4) Total the Squared Deviation. In our example the total is 50. The Total Squared Deviation is
located at the bottom of the in Deviation Squared Column on the Calculation Table.
5) Calculate the total sample size (N), and subtract 1. The calculation is 21-1=20.
The information used to calculate N is located in the Data Table.
6) Calculate the Standard Deviation. This is done by dividing the Total Square Deviation by the
total Sample Size –1, and then taking the square root. The calculation in our example would be
50/20. The Standard Deviation is 1.58
7) Calculate Sigma Level. How many standard deviations can fit between the average and upper
limit, and the average and lower limit? Take the average and subtract the lower limit. Take this
value and divide by the standard deviation. The answer is how many sigma can fit between the
lower limit and the average. Repeat the same step for the upper limit. In our example, the
calculations are as follows:
 21 - 11.5 (lower limit) / 1.58 = 6.012 (# of Std. Deviations between average & lower limit)
 30.5 (upper limit) - 21/ 1.58 = 6.012 (# of Std. Deviations between average & upper limit)
Measure
2

74
Standard Deviation – Calls per Hour
Jan Feb Mar Apr
Mary 21 18 23 20
John 20 21 19 23
Joe 19 22 21 N/A
Sandy 22 19 23 21
Melissa 20 22 24 20
Dave N/A N/A 21 22
Name
Month
DataCalculation
LSL USL
11.5 30.521
X X X-X (X-X)
Result Average Deviation Deviation Squared
21 21 0 0
20 21 1 1
19 21 2 4
22 21 -1 1
20 21 1 1
18 21 3 9
21 21 0 0
22 21 -1 1
19 21 2 4
22 21 -1 1
23 21 -2 4
19 21 2 4
21 21 0 0
23 21 -2 4
24 21 -3 9
21 21 0 0
20 21 1 1
23 21 -2 4
21 21 0 0
20 21 1 1
22 21 -1 1
441 50
Sum of all Results 441
Number of Results 21
Average 21
Sample Size 20
Upper Limit 30.5
Lower Limit 11.5
Standard Deviation 1.58
Sigma Level 6 Sigma
21
20 21 22
19 20 21 22 23
19 20 21 22 23
18 19 20 21 22 23 24
Measure
2

75
Performance
Level SIGMA DPMO
A+
A
B
6
5
4
3.4
233
6,210
C 3 66,811
D 2 308,770
F 1 697,672
Handbook – Appendix XII-3
Recap
Measure

76
In order to apply Six Sigma, you must understand
the impact of Variation…
What is Variation?
Simply stated, Variation is the degree to which something differs
from a former state or value, from others of the same type, or from
a standard.
Formal Definition:
Variation: Inevitable change in the output or result of a system (process)
because all systems vary over time. Two major types of variations are (1)
Common, which is inherent in a system, and (2) Special, which is caused by
changes in the circumstances or environment.
Measure

77
Measure

78
Measure

79
Connection:
• Excessive tardiness
• Personal Calls
• Invoice Issues
• System Issue
• Misapplied Payments
• Incorrect Terms
Measure

80
Connection:
Man=
Machine=
Material=
Method=
Measurement=
Mother
Nature=
Measure

81
• Tells you how tightly data is
clustered around a center
point.
Usage:
• Analyzing Average Calls
per Hour
• Analyzing Average
Promises to Pay
• Analyzing Synergy Actions
• RMS Salaries
Measure

82
Definitions
Mean
Sum total of all data values divided by
# of data points (the average)
Median
Middle value when data is ascending
or descending (midpoint)
Mode Value occuring most frequently
Measure

83
Measure

84
Measure

85
Measure

86
Measure

87
Eliminate highly skewed results
Measure

88
Measure

89
Measure

90
Measure

91
Measure

92
Measure

93
Additional Comments
The Mean:
• Is Sensitive to Extreme Observations/data
• Most Affected by Skewed Data
• Most Frequently Used
The Median:
• Is Most Effective When Data is Skewed
• Is Best if Data is “Messy”
• Not Affected as Much by Outliers
Measure

94
• Tells you how data is distributed around a center point
• Describes expected amount of variation (variability) in
normally distributed data.
= Population
= Sample
Examples:
• On average, what is the variability in calls per hour?
• On average, what is the variability in Synergy actions per hour?
Measure

95
S =
Note: In most cases data used
in process improvement is a
sample (subset) taken from a
population.
Measure

96
Recap
• Tells you how tightly data is clustered
around a center point.
• Tells you how the data is distributed
around the center point.
• Large Amount of Variation = Large
Spread
Why is this important?
Connection:
Example: Calls per Hour
• If tightly centered:
- Effective training
• If skewed:
- Time of day?
- Skill set of employees
• Are the calls inbound or
outbound?
Central
Tendency
Mean
Median
Mode
Spread
(Standard Deviation)
Measure

97
Flowchart Techniques - Overview
• Prepare a Current State Map to Document the Current Process
• Identify all Decision Points to Ensure Path Leads to Final Outcome
• Strive for the Proper Level of Detail
• Too Little-Flowchart Useless
• Too Much-Bog Down the Process
• Tip: If mapping out process documentation,
you can never have enough detail
• Use Supplemental Charts to Limit Size
• Keep the Flowchart Moving in One Direction-Top to Bottom / Left to Right
Measure

98
Flowchart Techniques - Create a Process Map
Source: George, M.L., Rowlands, D., Price, M., & Maxey, J. (2005). The Lean Six Sigma Pocket Toolbook, 40 – 41, 43 – 44.
Measure

99
Flowchart Techniques - Tips
Measure

100
Another Type of Process Map – Swim-lane Flowchart
Measure

101
Another Type of Process Map – Swim-lane Flowchart
Measure

102
Flowchart Techniques - Common Symbols
Manual Input
Decision Point
Document
File
Process
Manual Operation
Connector
Measure

103
Purpose
• Set
Performance
Objectives
• Indentify
Sources of
Variation
Tools
• Control Charts
• Hypothesis
Testing
• Cause and
Effect
Diagrams
• FMEA
• Value Stream
Mapping
Key Outputs
• Defined List of
Potential
Sources of
Variation
• Cost Benefit
Analysis
Define Measure Analyze Improve ControlAnalyze

104
Review

105
Strategies to Control Variation
Common Cause Special Cause
Reduce common cause variation by
reducing the spread of the process.
No one factor is unduly influencing
the process. Numerous small
factors.
Reduce special cause variation by
identifying it and eliminating it – 6M’s
– key source of special cause
variation.
factors.
identifying it and eliminating it – 6M’s
variation.
Six Sigma team will analyze 6M’s
Identify the source of variation and
eliminate it.
eliminate it.
Design of Experiments –
Lecture 68-75 – Systematically
test influence of various factors
Expected Variation Six Sigma team will analyze 6M’s,
identify the source of the variation,
and eliminate it.

106
Normal Curve
50%50%
Common Cause Bell Curve
Normal Curve Normal Distribution
Gaussian Curve Chance
Random variation Expected variation
Most commonly used
distribution in Six Sigma

107
VARIATION - 6 M’s
• Man
• Machine
• Material
• Method
• Measurement
• Mother Nature
Bonus points – Money, Mgmt
Drivers of Special Cause
Variation
Variation - 6M’s

108
Run Charts
191715131197531
6
5
4
3
2
1
0
191715131197531
6
5
4
3
2
1
0
Tools to Control Variation
Basic – preliminary analysis – least sensitive of SPC
Sketch a quick run chart before more complex analysis
Tools to Analyze Variation

109
Run Charts
1. Allows team to study data for trends or patterns
2. No control limits are drawn – no points out of control
3. Data collected in order of occurrence
4. Collected over a specified time period
191715131197531
6
5
4
3
2
1
0
191715131197531
6
5
4
3
2
1
0
X axis (time or sequence scale)
Y
a
x
is
scale
Usage:
• Analyzing Calls/Actions
per Hour against the average
over time, in order to
identify variation
X Axis (time or sequence scale)
YAxis(results)

110
Run Chart with
statistically
based limits
Control Chart – Sophisticated
Sample
SampleMean
191715131197531
602
601
600
599
598
__
X= 600.072
UCL= 601.722
LCL= 598.422
1
Xbar Chart of L ength
Sample
SampleMean
191715131197531
602
601
600
599
598
__
X= 600.072
UCL= 601.722
LCL= 598.422
1
Xbar Chart of L ength
Upper and Lower Control limits

111
A Little History on Control Charts…
Walter Shewhart, 1891-1967
Shewhart Control Chart
Responsible for defining…
assignable cause variation
chance cause variation
Developed the control chart specifically
to distinguish between the two.

112
Understanding Variation
Two types of Variation we are looking for in control charts
• Special Cause
• Detrimental
• Beneficial
• Common Cause
The goal is a stable and predictable process!
Connection:
• Provide an example of a
special cause variation with
a beneficial outcome.

113
Out-of-Control
A process is considered to be
“out of control” when any one or
more of the following symptoms
occur

114
Analyze

115

116

117

118
Control Chart – Objectives
1. Study variation and its source
2. Monitors process behavior
3. Identifies if operating as expected or if
corrective action is needed
4. Changes are only made when a) points
on the control chart are outside acceptable ranges or
b) freak patterns – otherwise leave alone
Sample
SampleMean
191715131197531
602
601
600
599
598
__
X= 600.072
UCL= 601.722
LCL= 598.422
1
Xbar Chart of Length

119
Analyzing Variation - A Demonstration

120
Define Measure Analyze Improve ControlMeasure ImproveDefine Measure Analyze Improve Control
Six Sigma Tools & Techniques
Analyze
Tool Hypothesis Testing
Process Overview  Used to evaluate whether making a change to a process input (x) significantly changes the output (y) of a
process.
 Hypothesis testing assists in using sample data to make decisions about population parameters such as
averages, standard deviations and proportions.
 Testing a hypothesis using statistical methods is equivalent to making an educated guess based on
probabilities associated with being correct.
Process Steps 1.Define the problem or issue to be studied.
2.Define the objective.
3.State the null hypothesis, identified as Ho. A null hypothesis is a statement of no difference between the
before and after states. (Similar to a defendant being not guilty in court. The goal of the test is to either
reject or not reject Ho.
4.State the alternative hypothesis, identified as Ha.
5.Determine the practical difference.
6.Establish the risk levels and the number of samples needed to obtain the desired risk levels.
7.Collect the samples and conduct the test.
8.Determine whether to reject or not reject the null hypothesis Ho.
Examples  Analyzing the impact of training on associate performance. Null Hypothesis-Ho: Productivity levels did
not significantly change after training program.
 Example of Impact of Teachers on Grade Average: Within a school district, students were randomly
assigned to one of two Math teachers - Mrs. Smith and Mrs. Jones. After the assignment, Mrs. Smith had 30
students, and Mrs. Jones had 25 students. At the end of the year, each class took the same standardized
test. Mrs. Smith's students had an average test score of 78, with a standard deviation of 10; and Mrs. Jones'
students had an average test score of 85, with a standard deviation of 15.
Test the hypothesis that Mrs. Smith and Mrs. Jones are equally effective teachers. Use a 0.10 level of
significance. (Assume that student performance is approximately normal.)

121
Analyze
Tool Hypothesis Testing
Examples  Bon Air Elementary School has 300 students. The principal of the school thinks that the average IQ of
students at Bon Air is at least 110. To prove her point, she administers an IQ test to 20 randomly selected
students. Among the sampled students, the average IQ is 108 with a standard deviation of 10. Based on
these results, should the principal accept or reject her original hypothesis? Assume a significance level of
0.01.
An inventor has developed a new, energy-efficient lawn mower engine. He claims that the engine will run
continuously for 5 hours (300 minutes) on a single gallon of regular gasoline. Suppose a simple random
sample of 50 engines is tested. The engines run for an average of 295 minutes, with a standard deviation of
20 minutes. Test the null hypothesis that the mean run time is 300 minutes against the alternative
hypothesis that the mean run time is not 300 minutes. Use a 0.05 level of significance. (Assume that run
times for the population of engines are normally distributed.)

122
0
-3 -2 -1 1 2 3
Critical region to
reject the null
Our t test statistic must be > our t critical value in order to conclude that
the difference in the means of the two sets of data is statistically significant.
The light yellow part is not enough evidence due to the small sample size.
Cannot say two data set are different unless they pass the critical value.
Critical region to
reject the null
t=
X-m
s/ √√ n
Hypothesis Testing
Connection:
• Confidence on Conclusion
• Analyze Risk Levels

123
Another Tool for Analyzing Problems
Also called The Fishbone Diagram or Ishikawa Diagram
Source: Wikipedia

124
Sample Fishbone Diagram
(Collections / Customer Service)
Inconsistent Measurements Lack of Training Material Lack of Documented Procedures
High Level of Noise
on Floor
Lack of Training
Measurement Materials Methods
Environment Man Power Machines
Phone Outages
Lack of
Contiguous Seats Employee Turnover
Time
System Downtime
Low
Production
Not Making
Production
Goals

125
Determine the Root Cause (the 5 Whys)
5 whys as part of lean manufacturing is a problem solving technique that allows you to get at the root
cause of a problem fairly quickly. It was made popular as part of the Toyota Production System
(1970’s.) Application of the strategy involves taking any problem and asking “Why - what caused this
problem?”
By repeatedly asking the question "Why" (five is a good rule), you can peel away the layers of
symptoms that can lead to the root cause of a problem. Very often the first reason for a problem will
lead you to another question and then to another. Although this technique is called "5 Whys," you may
find that you will need to ask the question fewer or more times than five before you find the issue
related to a problem.
Benefits Of The 5 Whys.
• It helps to quickly identify the root cause of a problem.
• It helps determine the relationship between different root causes of a problem.
• It can be learned quickly and doesn't require statistical analysis to be used.
• Can be used with the Fishbone Diagram
When Is 5 Whys Most Useful?
• When problems involve human factors or interactions.
• In all types of business situations whether solving a lean manufacturing or for any other business
problem.
Source: http://www.govcomm.harris.com/suppliers/become/Problem_Solving_Tools.pdf

126
Example of a Five Whys Analysis
… Here is our “Wheel” Life Example:
1. Why is our largest customer unhappy? Because our deliveries of
bicycles have been late for the last month
2. Why have our bicycle deliveries been late for the last month? Because
production has been behind schedule.
3. Why has production been behind schedule? Because there is a
shortage of wheels.
4. Why are we having a shortage of wheels? Because incoming
inspection has rejected a large number of wheels for not being round.
5. Why are we rejecting so many parts? Because purchasing switched to
a cheaper wheel supplier that has inconsistent quality.
Source: http://www.govcomm.harris.com/suppliers/become/Problem_Solving_Tools.pdf

127
Purpose
• Prioritize the
Vital Few
Causes of
Variation
• Establish
Relationships
between
Output and
Input Variables
Tools
• FMEA
• Design of
Experiments
• Principles of
Lean
Manufacturing
• Process
Capability
Analysis
Key Outputs
• Proposed
Process
Settings
• Impact of
Proposed
Solutions
• Improved
Processes and
/or Products
Define Measure Analyze Improve ControlImprove

128
FMEA – A Simple Explanation
Improve
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.
• FMEA relies on team experience to put
safeguards in place.
• FMEA is applicable to any system

129
Tool FMEA-Failure Mode Effects Analysis
Process
Overview
 Methodical approach to examine proposed designs for potential points of failure.
 Uses a Risk Priority Number to Identify the critical focus areas.
o RPN= FOC x SEV x COD
o FOC=Frequency of Occurrence, SEV=Severity, COD=Chance of Detection
 Identifies the actions which could prevent failures.
Process
Steps
1.List the key process steps in the first column.
2.List the potential failure mode for each process step. (How could this process step fail?)
3.List the effects of this failure mode.
4.Rate how severe this effect is (SEV). (1 Not Severe, 10 Most Severe)
5.Identify the causes of the failure mode/effect and rank how likely this cause will occur in the
occurrence column (FOC).
6.Identify the controls in place to detect the issue and rank its effectiveness in the detection
column (COD).
7.Calculate the RPN by multiplying FOC x SEV x COD.
8.Sort by RPN number to identify the most critical issues.
9.Take action and access results.
Example  The aerospace industry used the FMEA during the Apollo missions in the 1960’s.
 1974-US Navy developed MIL-STD-1629 which is a document that outlines the standards and
proper use of the FMEA process.
 A new toaster design team uses FMEA to identify flaws in the design. This highlights ways in
which the handle can stick and cause the toast to catch fire. This is prevented by adding a specific
thermostatic safety release to the design.
 A secretary uses FMEA to highlight the possible undesirable effects of a room booking system
not working properly, and consequently includes checks to reduce the chance of key effects of
overbooking and key staff not being able to find rooms.
Improve

130
Define Measure Analyze Improve ControlMeasure Improve
Severity
Seriousness of
impact
Occurrence
Likelihood will
occur
Detection
Ability to detect
10 Hazardous Very high >1/day Cannot detect
9 Illegal Every 3-4 days Spot checks
8 Unfit for use Once/week Samples
7 Dissatisfaction Once a month Inspected
6 Malfunction Once 3 months Mistake proof
5 Complaint Once 6 months SPC
4 Minor loss Once/year SPC+
3 Nuisance Once 1-3 years SPC++
2 Unnoticed Once 3-6 years All inspected
1 No effect Failure unlikely Certain detect
Severity
Seriousness of
impact
Occurrence
Likelihood will
occur
Detection
Ability to detect
10 Hazardous Very high >1/day Cannot detect
9 Illegal Every 3-4 days Spot checks
8 Unfit for use Once/week Samples
7 Dissatisfaction Once a month Inspected
6 Malfunction Once 3 months Mistake proof
5 Complaint Once 6 months SPC
4 Minor loss Once/year SPC+
3 Nuisance Once 1-3 years SPC++
2 Unnoticed Once 3-6 years All inspected
1 No effect Failure unlikely Certain detect
Which of the 3 columns is your priority?
Risk Priority Number (RPN)
Improve

131
Define Measure Analyze Improve ControlMeasure Improve
Self –Service Gas - FMEA
Find
Gas
Pump
Credit
Card
Select
Gas
type
Return
Hose
Initialize
Pump
1. Team familiar with the process
2. Brainstorm failure modes or points (may be lengthy)
Tip – Look at desired outcome of each step
then consider 6Ms to identify possible failures
6 Ms - list
FMEA Example – Self Service Gas
Usage:
• Collection Process Potential Failure
Points
• File Drop not Received/Processed
• Attrition/Turnover
• Hiring Issues
• Letter Issues
• Synergy Issues
• Lack of Client System Access
• Plan for Failures and take
Preventative Measures
• Client Start-Up and Giving ETA’s
Improve

132
FMEA (Failure Mode & Effects Analysis)
Responsible : Name Prepared by: Name
Original Date: Date Revised Date: Date
Process Step/
Input
Potential
Failure Mode
Potential Failure
Effects Severity(SEV) Potential Causes
Occurance(FOC)
Current
Controls
Detection(COD)
RPN
Actions Recommended Resp. Actions Taken
Add Milk to Cake
Mix
Wrong amount
of Milk
Cake too Dry of too
Soggy 5
Samll Marks on
Measuring Cup 10 None 6 300
Use Large Print on
Measuring Cups JW Replacing Measuring Cups
5
Faded Marks on
Measuring Cup 5
Visual
Inspection 3 75
Replace Faded Measuring
Cups JW
Replaced Cups and Retrained
Inspectors
5 Milk Spilled 4 None 8 160 Train Bakers HH Not Yet Complete
Flour Still in
Measuring Cup
Too Little Milk-Cake
to Dry or too Soggy 5
Employee
Careleness 5
Training
(Appears to
be
Ineffective) 9 225
Create Standard Operating
Procedure and Improve
Training Program HH
Created Documented SOP's and
Scheduled Refresher Training
Lumps in Cake 6
Employee
Careleness 2
Training
(Appears to
be
Ineffective) 9 108
Create Standard Operating
Procedure and Improve
Training Program HH
Created Documented SOP's and
Scheduled Refresher Training
A Simple Example-Baking a Cake
Notice that ther can be several
failure modes per step and
several effercts and causes per
failure mode.
Risk Priority Number (RPN)=
Severity X Occurrence X
Detection
Plan for both preventative
actions and contingent
actions (how to limit damage
if it happens)
Improve

133
factors.
identifying it and eliminating it– 6M’s
variation.
factors.
identifying it and eliminating it– 6M’s
variation.
eliminateit.
eliminateit.
Design of Experiments–
Lecture 68-75 – Systematically
test influence of various factors
Systematically test influence
of various factors
Improve

134
Tool DOE-Design of Experiments
Process
Overview
 Manipulating factors at different levels to see their effect on a desired result.
 DOE investigates a list of potential factors whose variation might impact the process output.
 Enables the study of multiple factors simultaneously.
 These factors can be derived from a variety of sources including process maps, Fishbone Diagrams, brainstorming
techniques and Cause and Effect Matrices.
 Factors are set at usually two levels (High and Low) and multiple tests are conducted to evaluate the output level
based upon the factor changes.
 DOE is an expensive evaluation process but can be very effective.
Process Steps 1.Define Objective
2.Gather Knowledge about Process
3.Develop List of Variables
4.Assign Levels to Variables
5.Conduct Experiments
6.Data Analysis and Conclusions
Example  Testing the impact of call scripts on call outcome. Does Script A have more of an impact than script B?
 Health Care Examples: Investigating the causes for emergency room wait times and determining which treatments in
the operating room yield the fastest patient recover times.
 Improve Yield by Investigating Factor A (Temperature) and Factor B (Pressure)
 Output=Popped Kernels / Factors: Coil Temperature, Pan Type, Cooking Time
oExamples of Levels
Coil Temperature: High / Low
Pan Type: Copper / Stainless Steel
Cooking Time: 4 Minutes/ 3 Minutes
Improve

135
DOE – A Simple Example – Popcorn
Improve

136
• Taguchi’s methods and DOE are tools that “make something happen,”
unlike many statistical methods that tell us “what happened.” They
are PROACTIVE instead of REACTIVE.
• Meeting customer specifications is not enough – the benefit of
continually reducing variation
• Xerox is the most advanced user of Taguchi’s methods
“Variation is the Enemy!”
Dr. Genichi Taguchi
1 • Popularized the concept of robust design in Japan
– Robustness derives from consistency or lack of variation
– Robustness is a function of product design
2 • Popularized quality loss function
3 • Popularized the signal-to-noise ratio
– Noise factors are uncontrollable influences
Improve

137
$ Loss
500 600 700
$ $
Target
Quality Loss
• Quality loss increases as the
product or service stray from its
target
• $ Loss any time a product or
service varies from a defined
target
• Loss to Society
• Capital ($)
• Natural Resources
• Human Capital
Taguchi’s Loss Function
Improve

138
Lean Overview
• Lean is a systematic approach to identifying and eliminating waste
through continuous improvement, flowing the product at the pull of
the customer in pursuit of perfection.”
Source: National Institute of Standards and Technology NIST
• More value to the customer and the company, with less of everything
that negatively impacts profits
• The Lean Approach:
• Identifies and eliminates waste
• Reduces cost
• Improves quality
• Generates new profit
• Improves delivery & customer satisfaction
• Empowers employees to make improvements
Connection:
• FTE Analysis
• Increase Production (more with less)
• Quality Reviews (eliminate re-work)
Improve

139
Lean Overview – Batch Processing vs. Continuous Flow
Batch Continuous
Considered to be convenient for the
company, but not for the customer
Each process makes or completes only
the one piece that the next process
needs
Makes a company less agile/flexible in
the marketplace
The batch size is one
More sensitive to variables (time
sequencing, process routing, etc.)
Each item is passed immediately from
one process step to the next without
any stagnation
Inventory = Possible Waste No inventory = No waste
Also known as “Just in Time”
Improve

140
Define Measure Analyze Improve ControlControl
Process Capability
Definition: The Ability of the Process to Meet Customer Requirements
USLLSL
Voice of the Customer
(Specifications)
Leeway
Created
by Tighter
Controls and
Less Variation
Leeway
Created
by Tighter
Controls and
Less Variation
Voice of the Process
(Process Variation)
• Is Your Process Capable?
• Use Process Capability
Studies
• The Ideal Situation is to Have
Some Leeway between
Performance and
Specification Limits
(Customer Goals)
Actions
• Center the Process
• Modify the Process
• Purchase New Equipment
• Use Problem Solving to
Improve Capability
• Revise Specification Limits
• Inspect 100%
Connection:
• Tighten Your Processes to Perform Well within
Goal Range and Decrease Variation in Performance
• Look at the 6M’s for Drivers of Variation
Improve

141
Purpose
• Ensure
Solutions are
Sustained
• Document Case
Studies and
Lessons
Learned
Tools
• Mistake
Proofing
• 5S Organization
Approach
• Documentation
Key Outputs
• Improved
Processes (In
Control)
• Robust
Products
• Project
Documentation
• Opportunity to
Transfer
Lessons
Learned

142
• Poka Yoke is a Japanese term that translates into “Avoid
Inadvertent Errors,” or “Mistake Proofing.”
• Poka Yoke is a technique that ensures that an operation
cannot be performed incorrectly
• Poka Yoke makes mistakes obvious at a glance so that the
error does not turn into a defect for the customer
Preventative Measures – Poka Yoke
Usage:
• Benefits Wizard Vista Templates
• Required Fields
• Sign Offs
• Audits
Control

143
Future State Process Map
• Don’t Wait Until Your Current State Process Map is Perfect
• Your Current State Process Map Will Never be Perfect
• You Want Your Future State Process Map to Produce Product or
Services Based on the Rate of Sales (Takt Time)
• If You Build Faster, You Build Inventory

144
Treated
patient
Billings to
Ins Co.
Health Insurance Claim Processing
Receipt
Verify
Claim
Calculate
payment
Print &
Mail check
Doctor
Hospital
Doctor
Hospital
2 min
2 days
10 min
2 days
1 min
2 days
1 min
6 days
14 min
6 days
14 min
Insurance
Company
Database

145
• 5 S - Method of creating a clean and orderly
workplace that exposes waste and errors
• Elements of a 5S program
– Sort
– Straighten/Store (Set in order)
– Shine
– Standardize
– Sustain/Self Discipline
– Safety (+1)
Organize Your Environment
The 5S Approach

146
• Do Not Rely on Associates to Remember Critical Processes
• Lack of Documentation puts you at Major Risk during Attrition
• Obtain Customer Sign-off where Possible
• Start with High Level Flow-Charts
• Use Screen Prints for Each Step
• Create a Wrap-up Sheet Showing all Steps
• Job Aide / Quick Reference
• Schedule Process Review and Refresh Often
• Post on Intranet Site when Possible
Document Your Processes

147
• Step 1 – Create Process Flow
• Step 2 – Document Each Step with Screen Prints
• Step 3 – Create Condensed Step by Step Reference Guide
Documentation
Control

148
• Always include a Table of Contents
• Create sections in logical order and group by topic
1. Company Overview
2. Contacts
• RMS & Client
3. Treatment Overview
• Matrix
• Rules
4. Letters
• Samples
• Process
5. Disputes / Research
• Types
• Codes
• Process / SLA’s
6. Systems
• Synergy Reference
• Client System Reference
7. Common Forms / Samples
8. Glossary of Common Terms
Goal:
Goal:
Your manual should be so good that it would be titled
“Collections Process for Dummies.”
Documentation – Manual Tips
Do not skip steps or combine too many on one page.

149
Relevance of Change to Six Sigma?
• Six Sigma philosophy demands we look for
opportunities to initiate change
• Responsible for managing change in a
systematic way
• Make ‘change routine’
Measure

150
Change Management
Define
Change
Communicate
and train
End of
old way
Duration of disruption
Due to change
Valley of
despair
This is normal
Prepare for it!
Source: http://www.isixsigma.com/library/content/c020812a.asp

151
Plan
Change
Communicate
and train
End of
old way
Duration of disruption
Due to change
Valley of
discomfort
Agile company
Change Management
Source: http://www.isixsigma.com/library/content/c020812a.asp
Measure

152
8 Stage Process of Creating Change
1) Sense of Urgency
2) Powerful Coalition
3) Vision
4) Communication
5) Empower Action – training, coaching participation
6) Short term wins - metrics
7) Momentum of change
8) Anchor in culture - celebrate
Warm up or defrosting activities
Necessary to real change
Source: Leading Change by John Kotter, 1996
Measure

153
Raise Urgency for Change
1) Expose employees to competitive data
2) Expose employees to unsatisfied customers
3) Limit ‘Happy Talk’ from senior management -honest discussion of problems
4) Set targets so high can’t reach by doing business as usual
5) Hold people accountable for broader measures – no subunit goals
6) Bombard with ideas on opportunities in marketplace
Source: Leading Change by John Kotter, 1996
Measure

154
• In 1962, Thomas Kuhn wrote The Structure of Scientific
Revolution, and popularized the concept of "paradigm shift”
• Think of a Paradigm Shift as a change from one way of
thinking to another.
• It just does not happen, but rather it is driven by
agents of change.
Paradigm Shift

155
Negotiation
• Change agent has to be skilled in negotiation – strive for
win-win
• Negotiation is a business decision-making process not a
competition
(This is NOT desirable)
Do’s and Don’ts
Do not negotiate in a hurry, nor under pressure.
Know what you want and what the other party wants.
Prepare thoroughly and comprehensively – fact & figures.
Listen, empathize and observe.
Be optimistic and never give up.
Measure

156
Negotiation Techniques
“Going to the balcony” – Strategic Break
Mental position from where you can view the
action up to a certain point, regain your
composure and plan positive further action.
a) Brief pause or silence
b) Rewind – “Let me make sure I understand what you’re saying”
c) Remove yourself – get a drink of water
Measure

RMS Six Sigma Training 2010 Final

Recommended

Recommended

More Related Content

What's hot

What's hot (20)

Viewers also liked

Viewers also liked (20)

Similar to RMS Six Sigma Training 2010 Final

Similar to RMS Six Sigma Training 2010 Final (20)

More from Michael Camp

More from Michael Camp (6)

RMS Six Sigma Training 2010 Final