15-Aug-21

LEAN SIX SIGMA

JOURNEY
IQ

Why to fill Registration form?

1. Certification (Name & Photo)

2. Payment Verification

3. Registration in MSME Sampark Job Portal

4. Address Details for mailing the Certificate by India Post

1
 15-Aug-21

When you will get the

certificate? (Classroom)
 All will receive the certificate on the last day (6 th
day) after completing the examination.

 Certificates will be provided only if the full batch

participants have submitted the Registration Form

 If anybody is not able to qualify the exam,

Free retake will be given to pass the examination.

Social Media Forum

1. Candidates will be added to IQ discussion forum after completion of

the training.

2. Active participation in the WhatsApp group is expected

3. Please feel free to share contents, questions, case studies related to

Lean Six Sigma or topics related.

4. Kindly refrain from sharing personalized messages in the group/forum.

5. You will receive regular job alerts related to six sigma in the group

2
 15-Aug-21

About US
Our Vision : To become an Improvement Catalyst for our client in building a
strong & lucrative business using Technology

Our Mission : To continuously Improve the people & processes and add value
to their skill & knowledge.

Vendors with Partnered with Trained about Implemented

30+ Courses 20,000 Leaners 100+ projects
50+ corporates 30+ colleges

About US
LSS Corporate
Training

Leadership LSS
Training Implementation

IQ
MSA PMP Training

5S Implementation

3
 15-Aug-21

Our Course List

• Lean Six Sigma • 5S Boot Camp
• Lean Workshop • TQM
• Lean Boot Camp • Pokayoke
• Measurement System • SMED
Analysis • Leadership Training
• Design of Experiments • Project Management
• Minitab Workshop • Data Visualization
• FMEA workshop • DFSS
• 7 QC Tools

Client list

4
 15-Aug-21

Institutional Clients

Online Reputation

5
 15-Aug-21

LinkedIn Profile

• We suggest you to follow IQ and

your trainer in LinkedIn
• Request to endorse the trainer
and the also IQ
• The trainer will be endorsing
each and every participant
• Stay connected for more
professional discussions and
support

Recent Industry Programs

MSME GB TRAINING MURUGAPPA GROUP

6
 15-Aug-21

Recent Industry Programs

YB for Operators WEG Industries

Recent Academic Programs

MOU: SAVEETHA UNIVERSITY GREEN BELT TRAINING

7
 15-Aug-21

RECENT ACADEMY PROGRAMS..

MOU: KALASALINGAM UNIVERSITY GREEN BELT TRAINING

Corporate Training

Training Experiential
Need training Mentoring
Analysis delivery

1 2 3 4 5

Customize Measuring
the content Training
as per effectiveness
requirement

8
 15-Aug-21

Partnering in Lean Six Sigma Journey

19 LSS Implementation – Nine stages

1 • Formation of infrastructure and deployment team

2 • Selection of project through assessment

3 • Transformation event

4 • LSS phase 1- Define

5 • LSS phase 2- Measure

6 • LSS phase 3- Analyze + Improve

7 • LSS phase 4- Improve + Control

8 • Closing ceremony + Next Phase of LSS declaration

9 • Fixed post project audits by IQ

WELCOME BACK

9
 15-Aug-21

MSA can improve the process

A TRUE

B FALSE

Should we plot control chart for

A) Y only

B) f(X) only

C) both of the above

10
 15-Aug-21

Arrange in the sequence

A. Process Capability => MSA => Control Chart

B. MSA => Control Chart => Process Capability

C. Control Chart => MSA => Process Capability

D. Control Chart => Process Capability => MSA

Which of the following is NOT possible

A.Cp = Cpk

B. Cp ≠ Cpk ≠ 1

C.Cp = -1

D.Cpk = -1

11
 15-Aug-21

Pareto Diagram

 Vital Few from Trivial Many

 Ideally have 8-10 categories of defects

Cat egory Frequency Cumulat ive frequency

Unreadable print ing 180 180
Ink blot ches 60 240
Colours not t o specificat ion 18 258
Incorrect ‘use by’ dat e 12 270
Ot her 10 280
Wrong label 9 289
Torn label 8 297
Label on crooked 3 300
Tot al 300

12
 15-Aug-21

Stratification

1. Subdivisions
2. Multi-perspective analysis
3. Repeat analysis

13
 15-Aug-21

Subdivisions

Multi-perspective analysis

14
 15-Aug-21

Repeat analysis

Fishbone / C&E / Ishikawa Diagram

➢ C-E diagram (Cause and Effect diagram) is an effective way to

summarize and list various causes and root causes.
➢ In C-E diagram, the most important thing is to show correlation
between cause-effect, and all possible causality needs to be
considered.
➢ Two ways of developing Fishbone diagram
o Put first level causes in main bones
o Or use 5M+1E on main bones
- Men - Materials - Methods
- Machines - Measurements - Environment

15
 15-Aug-21

Fishbone Diagram: Cause-and-

Effect
CAUSE EFFECT
FAST
INCOME FOOD AERATED
DRINKS
EXERCISE JUNK
FOOD

Obesity
Transportation Local Location
New Food
technology New Food
Cooking
Reduced Centre/Stor
Outdoor Skill Time Unhygienic es
Games Price
Cooking
TECHNOLO Variety
MACHINE METHOD
GY

16
 15-Aug-21

37

Why – Why Analysis

• Dirty Road
Why

• Oil Leak
Why

• Leak Oil Tanker

Why

• Poor Maintenance
Why

• Untrained and Careless Drivers

Why

FMEA

 Formally developed and applied by NASA in the 1960’s to improve and

verify reliability of space program hardware during APOLLO missions.

 In 1974, the NAVY developed the MIL-STD-1629 regarding the use of

FMEA.

17
 15-Aug-21

WHEN IS AN FMEA CARRIED OUT?

 When a process, product or service is being designed or redesigned,

after quality function deployment.

 When improvement goals are planned for an existing process, product

or service.

 When analyzing failures of an existing process, product or service.

FMEA – Operating Definition

Failure Mode and Effects Analysis is a structured and systematic process
to identify potential design and process failures before they have a chance to occur with the
ultimate objective of eliminating these failures or at least minimizing their occurrence or
severity.

Design FMEA Process

FMEA FMEA

During design, it is advantageous to Performed to identify and address

know: areas of potential risk within existing
a) How and where customer will process.
use end product?
b) How customer may “abuse” end Helps proactively manage risks in a
product? process

18
 15-Aug-21

KEY

INGREDIENTS

OF AN

FMEA

WHAT IS FMEA?

 Simply put FMEA is:

A process that identifies all the possible types of failures that
could happen to a product and potential consequences of those
failures.

OPERATION

FUNCTION

FAILURE MODE EFFECT

CURRENT
CAUSE
CONTROL

19
 15-Aug-21

Severity
A numerical measure of how serious is the effect of the failure.
Effect Design or Process: Customer Effect Process: Manufacturing/Assembly Effect

10 Hazardous Very high severity ranking when a potential failure mode Or may endanger operator (machine or assembly) without warning
without affects safe vehicle operation and/or involves noncompliance
warning with government regulation without warning.

9 Hazardous Very high severity ranking when a potential failure mode Or may endanger operator (machine or assembly) without warning.
with affects safe vehicle operation and/or involves noncompliance
warning with government regulation with warning.

8 Very High: Vehicle/item inoperable (loss of primary function). Or 100% of product may have to be scrapped, or vehicle/item
repaired in repair department with a repair time greater than one
hour.
7 High Vehicle/item operable, but at a reduced level of performance. Or product may have to be sorted and a portion (less than 100%)
Customer very dissatisfied. scrapped, or vehicle/item repaired in repair department with a
repair time between a half-hour and an hour.

6 Moderate Vehicle/item operable, but Comfort/Convenience item(s) Or a portion (less than 100%) of the product may have to be
inoperable. Customer dissatisfied. scrapped with no sorting, or vehicle/item repaired in repair
department with a repair time less than a half-hour.

5 Low Vehicle/item operable, but Comfort/Convenience item(s) Or 100% of product may have to be reworked, or vehicle/item
operable at a reduced level of performance. repaired off-line but does not go to repair department.

4 Very Low Fit & Finish/Squeak & Rattle item does not conform. Defect Or product may have to be sorted, with no scrap, and a portion
noticed by most customers (greater than 75%). (less than 100%) reworked.

3 Minor Fit & Finish/Squeak & Rattle item does not conform. Defect Or a portion (less than100%) of the product may have to be
noticed by 50% of customers. reworked, with no scrap, on-line but out-of-station.

2 Very minor Fit & Finish/Squeak & Rattle item does not conform. Defect Or a portion (less than100%) of the product may have to be
noticed by discriminating customers (less than 25%). reworked, with no scrap, on-line and in-station.

1 None No discernable effect Or slight inconvenience to operation or operator, or no effect.

Occurrence
Occurrence: A measure of probability that a particular failure will
actually happen.
The degree of occurrence is measured on a scale of 1 to 10,where
10 signifies the highest probability of occurrence.
Likelihood Either … Or … Cpk

10 Very High: More than 100 per thousand machines/items/ 1 in 10 or less <0.55
pieces

9 Persistent Failures 50 per thousand machines/items/pieces 1 in 20-50 0.55 to 0.78

8 High: 20 per thousand machines/items/pieces 1 in 50-100 0.78 to 0.86

7 Frequent Failures 10 per thousand machines/items/pieces 1 in 100-200 0.86 to 0.94

6 Moderate: 5 per thousand machines/items/pieces 1 in 200 -500 0.94 to 1.00

5 Occasional 2 per thousand machines/items/pieces 1 in 500-1000 1.00 to 1.10

4 Failures 1 per thousand machines/items/pieces 1 in 1000-2000 1.10 to 1.20

3 Low: Relatively 0.5 per thousand machines/items/pieces 1 in 2,000-10,000 1.20 to 1.30

2 Few Failures 0.1 per thousand machines/items/pieces 1 in 10,000-100,000 1.30 to 1.67

1 Remote: Failure is unlikely Less than 0.010 per thousand machines/item/ 1 in 100,000 or more >=1.67
pieces

20
 15-Aug-21

Detection
A measure of probability that a particular failure or cause in our operation shall be
detected in current operation and shall not pass on to the next operation. (would
not affect the internal/ external customer)
Detection Criteria: Likelihood of Detection by PROCESS control A B C Suggested Range of Detection Methods
10 Absolute certainty of Design Control will not and/or cannot detect a potential X Cannot detect or is not checked.
non-detection cause/mechanism and subsequent failure mode; or there is
no Design Control.

9 Controls will Very remote chance the Design Control will detect a potential X Control is achieved with indirect or random checks only.
probably not detect cause/mechanism and subsequent failure mode.
8 Controls have poor Remote chance the Design Control will detect a potential X Control is achieved with visual inspection only.
chance of detection cause/mechanism and subsequent failure mode.
7 Controls have poor Very low chance the Design Control will detect a potential X Control is achieved with double visual inspection only.
chance of detection cause/mechanism and subsequent failure mode.
6 Controls may detect Low chance the Design Control will detect a potential X X Control is achieved with charting methods, such as SPC
cause/mechanism and subsequent failure mode. (Statistical Process Control)
5 Controls may detect Moderate chance the Design Control will detect a potential X Control is based on variable gauging after parts have left
cause/mechanism and subsequent failure mode. the station, or Go/No Go gauging performed on 100% of
the parts after parts have left the station.

4 Controls have a Moderately high chance the Design Control will detect a X X Error detection in subsequent operations OR gauging
good chance to potential cause/mechanism and subsequent failure mode. performed on setup and first-piece check (for set-up
detect causes only).

3 Controls have a High chance the Design Control will detect a potential X X Error detection in-station, or error detection in subsequent
good chance to cause/mechanism and subsequent failure mode. operations by multiple layers of acceptance: supply,
detect select, install, verify. Can’t accept discrepant part.

2 Controls almost Very high chance the Design Control will detect a potential X X Error detection in-station (automatic gauging with
certain to detect cause/mechanism and subsequent failure mode. automatic stop feature.) Cannot accept discrepant part.

1 Controls certain to Design Control will certainly detect a potential X Discrepant parts cannot be made because item has been
detect cause/mechanism and subsequent failure mode. error-proof by process/product design.

* Inspection Types: A= Error Proofed, B= Gauging, C= Manual Inspection

Failure Mode/Cause Relationship

46 In Different FMEA Levels
Inadequate
Electrical
Connection
Failure
Cause Mode
Motor
Stops
Failure
Mode Inadequate
Electrical Connection

Inadequate Causes Harness

Locking Too Short
Feature

21
 15-Aug-21

Risk Priority Numbers (RPN)

It is a numerical and relative “measure of overall risk” corresponding to a

particular failure mechanism and is computed by multiplying the
Severity, Occurrence and Detection numbers.

RPN = S * O * D

The RPN provides prioritization of potential failure mechanisms.

Normally RPN values more than 125 need a recommendation and

action.

FMEA Concept

Effect

Severity

Risk Action
Failure Mode Cause Priority Plan
Occurrence Number

Control

Detection

22
 15-Aug-21

Notes on Reduction in RPN Numbers

Severity

This number cannot usually be changed. Only a revision of the

design/process can bring about a reduction in severity ranking.
E.g. Brake system failure could result in a Severity number = 10

Occurrence

Design/process revisions and prevention controls can reduce

occurrence ranking.

Detection

This number can be reduced by instituting good detection

techniques (inspection, testing, visual controls etc.)

RPN Reduction
Assume that the Severity number cannot be reduced. Indicate the
order of importance that you would assign as far as addressing
these processes so as to reduce overall risk.

Item Severity Occurrence Detection RPN

a 8 10 2 160
b 10 8 2 160
c 8 2 10 160
d 10 2 8 160

23
 15-Aug-21

51 Evaluation by RPN Only

 Case 1
 S=5 O=5 D=2 RPN = 50
 Case 2
 S=3 O=3 D=6 RPN = 54
WHICH ONE
 Case 3 IS WORSE?
 S=2 O=10, D=10 = 200
 Case 4
 S=9 O=2 D=3 = 54

EXAMPLES
Failure Mode :Very high RPN/ One RPN

Effect :Confusion among the FMEA team.

Cause :Ranking error.

Control : Training and analysis.

24
 15-Aug-21

WHY IS AN FMEA IMPORTANT?

 Preventing problems is cheaper and easier than cleaning them up.

 Some things are too risky or costly to incur mistakes.

 Regulatory reasons

WHY IS AN FMEA IMPORTANT?

 Reduce the likelihood of customer complaints

 Reduce maintenance and warranty costs

 Reduce the possibility of safety failures

25
 15-Aug-21

55 Analyze Basics

Sampling
When to Sample

Study Parameter Conditions Favoring the Use

of Sampling

1. Budget Small
Population
2. Time available Short

3. Population size Large

4. Variance in the characteristic Small

5. Cost of sampling errors Low Sample

6. Cost of nonsampling errors High

7. Nature of measurement Destructive

8. Attention to individual cases Yes

Hypothesis Testing Overview

➢Understand terms related with hypothesis testing

➢Understand hypothesis testing in practical sense

- how to develop hypothesis

- how to carry out hypothesis tests

- how to determine acceptance of hypothesis

26
 15-Aug-21

Hypothesis

A hypothesis is an educated guess about something in the world around you. It

should be testable, either by experiment or observation.

For example:

• A new medicine you think might work.

• A way of teaching you think might be better.
• A possible location of new species.
• A fairer way to administer standardized tests.

It can really be anything at all as long as you can put it to the test.

What is a Hypothesis Statement?

If you are going to propose a hypothesis, it’s customary to write a statement. Your
statement will look like this:
“If I…(do this to an independent variable)….then (this will happen to the dependent
variable).”

For example:

• If I (decrease the amount of water given to herbs) then (the herbs will increase in size).
• If I (give patients counseling in addition to medication) then (their overall depression
scale will decrease).
• If I (give exams at noon instead of 7) then (student test scores will improve).
• If I (look in this certain location) then (I am more likely to find new species).

27
 15-Aug-21

Hypothesis Testing Examples #1: Basic Example

A researcher thinks that if knee surgery patients go to physical therapy twice a week (instead
of 3 times), their recovery period will be longer. Average recovery times for knee surgery
patients is 8.2 weeks.

Next, you’ll need to state the null hypothesis (See: How to state the null hypothesis). That’s
what will happen if the researcher is wrong. In the above example, if the researcher is wrong
then the recovery time is less than or equal to 8.2 weeks. In math, that’s:
H0 μ ≤ 8.2

The hypothesis statement in this question is that the researcher believes the average recovery
time is more than 8.2 weeks. It can be written in mathematical terms as:
H1: μ > 8.2

Hypothesis Testing
Develop the hypothesis for population and make statistical decision by
determining the acceptance of hypothesis using sample data.
➢ Null Hypothesis (H0) : Argument made so far, or hypothesis saying that
there is no change or difference
➢ Alternative Hypothesis (H1) : New argument, that is a hypothesis that
you want to prove with solid ground obtained from sample

Example) Medicine B for headache that is newly developed by a pharmaceutical company has 30
minutes longer effect than existing Medicine A.

H0 : Medicine A and B have same effect.

H1 : Medicine B has 30 minutes longer effect than Medicine A.

28
 15-Aug-21

61
Analyze Basics
Null Hypothesis (Ho)

▪ Null Hypothesis is represented by Ho

▪ It is a statement of Innocence.

▪ It is something that has to be assumed if you

cannot prove otherwise.

▪ It is a statement of No Change or No
Difference.

62
Analyze Basics

Alternate Hypothesis (Ha)

▪ The statement that will be considered valid if null

hypothesis is rejected is called Alternate Hypothesis
(Ha)
▪ Just like a court case, we first assume that the
accused (X) is innocent and then try to prove it
otherwise based on evidence (Data).
▪ If evidence (Data) does not show significant
difference, we cannot reject the innocence (Ho)
▪ But if Evidence (Data) is strong enough, we reject
the Innocence (Ho) and pronounce the suspect
Guilty (Ha).

29
 15-Aug-21

63
Analyze Basics

Type of errors
Null Hypothesis

Good Bad
Alternate Hypothesis

Accept

ERROR
Correct Decision
TYPE II
Reject

ERROR
Correct Decision
TYPE I

64
Analyze Basics

Understanding Risk
What Actually Is

Good Bad
What was Your Decision

Accept

Confidence Beta Risk

1- α β
Reject

Alfa Risk Power

α 1-β

30
 15-Aug-21

P-Value
The probability of significance

If P > 0.05 Accept Null Hypothesis

If P < 0.05 Reject Null Hypothesis.

Example: Hypothesis Testing

Before VS. After
➢ It is claimed that a process has been
improved in terms of yield by bringing Process A Process B
89.7 84.7
a change in an important factor X.
81.4 86.1
Yield data is collected from old and
84.5 83.2
new processes. 84.8 91.9

➢ Random samples are drawn from 87.3 86.3

79.7 79.3
yield data from old process A and
85.1 82.6
improved process B. 81.7 89.1
83.7 83.7
84.5 88.5

“Is there real difference between Process A and Process B?”

31
 15-Aug-21

Example: Hypothesis Testing

➢Real Question :
Can we say that the yield of improved Process B is greater
than old Process A?

Descriptive Statistics
Variable Process N Mean Std. Dev.
Yield A 10 84.24 2.90
B 10 85.54 3.65

➢Statistical Question :
Is there a statistically significant difference between mean of
Process B (85.54) and mean of Process A (84.24)? Or, is this
difference in mean just due to chance?

Hypothesis Testing
➢ Test Statistic
Statistic that is used as criteria for selecting null or alternative hypothesis
Need to set appropriate test statistic such as Z, t , F distribution if necessary.

➢ Two Errors in Hypothesis Testing

Actual Ho is true H1 is true Accept null hypothesis?
Testing Result Accept alternative hypothesis?

Accept Ho Right decision Type 2 Error



Accept H1 Type 1 Error Right decision



❖ TypeⅠError : Error that you reject null hypothesis although null hypothesis is true
❖ TypeⅡ Error : Error that you accept null hypothesis although null hypothesis is false
❖ p value : Calculated probability of type I error.

32
 15-Aug-21

Hypothesis Testing The acceptance of

hypothesis is determined
Procedure of Hypothesis Testing using p-value as follows!
1. Develop null and alternative hypothesis

2. Select test statistic

3. Determine significance level 

4. Determine rejection criteria
 5. Calculate significant probability p -value
5. Calculate test statistic Or from test statistic

6. Determine the acceptance of hypothesis
6. Determine whether to accept
using p-value
hypothesis based on test statistic
If p is less than α, reject H0 and accept H1
If p is greater than α, accept H0 and reject H1

Hypothesis Testing & Graphical Techniques

If Output and Input Appropri Graphic Examples
Y is… X is … ate Test al Tool
Continuous Discrete more ANOVA Box plot, Compressive strength of
than 2 (single frequency concrete using various brands
categories factor) plots, of cement.
histogram
Continuous Discrete in 2 t-Test Same as Average handling time
categories above compared for two teams
carrying out same process

Continuous Continuous Regression Scatter Diesel consumed vs speed

Plot

Discrete Discrete Chi-square Pareto Number of errors in coding vs

test Analysis number of defects in testing

33
 15-Aug-21

Question

There are two agents Rohit & Mohit, working with problem
resolution process. The data shows the times they take to
resolve problems. Their performance is to be judged and
one of them is to be promoted. Data given 12 transactions.
Give your judgement.

Example: Team Performance

➢ Analyze the performance of turn around times for three teams Team
1, Team 2, and Team 3.
Team 1 (3m) Team 2 (9 m) Team 3 (15m)
➢ Comparing two teams (lets say team 1 &
2 7 .6 5 24.45 2 0 .7 3
team 2)
2 6 .3 6 25.06 2 1 .1 8

2 6 .4 8 24.69 2 1 .2 5
Test: 2 sample t test
2 6 .2 5 25.95 2 1 .2 1 ❑ H0: There is no difference in team 1 and
2 6 .3 6 24.6 2 2 .3 9 team 2
2 6 .6 2 24.51 2 1 .2 5 or
2 6 .2 4 26.6 2 1 .4 8 ❑ H0: Population Mean for A= Population
2 5 .5 5 25.71 2 0 .9 9 Mean for B.
2 5 .4 2 25.35 2 1 .9 9

2 6 .6 9 25.74 2 1 .4 1
➢ Comparing all three teams
Test: ANOVA
❑ H0: All population means are equal
Teams.mtw

34
 15-Aug-21

Normality Test

• Stat>Basic Statistics>Normality test

• Check Anderson-Darling p-value
• Check normality for all samples

• Data follows normal

H0 distribution

• Data do not follow

Ha normal distribution

2 Variances Test

• Stat>Basic Statistics>2-Variances
• Check F- test p-value

H0 • s2A = s2B
• s2A ≠ s2B
Ha

35
 15-Aug-21

2 – Sample t test

• Stat>Basic Statistics>2 sample t-test

• Check “Assume equal variances’ if F-
test indicates equal variances
• Check t-test p-value

H0 • mA = mB
• mA ≠ mB
Ha

Frequently Asked Questions

Why do we check whether the data follows normal
distribution?

• 2- independent sample t-test assumes that the data follows normal distribution and
therefore we carry out normality test. We may carry out Anderson-Darling normality test
and if p-value is more than alpha, we consider that data follows normal distribution

What is F-test for?

• F-test is used compare variances of two groups. It tests the hypothesis whether there is
any difference between two population variances
• F-test results help us determine whether we should assume equal variances or not
while carrying out 2-independent sample t test

What is 2-independent sample t-test for?

• 2- independent sample t-test compares and tests the difference between the means of
two independent populations
• 2 –independent sample t- test are of two types and we choose one of them depending
on F-test results
• 2-independent sample t-test assuming equal variances
• 2-independent sample t-test assuming unequal variances

36
 15-Aug-21

Stacking Data
➢ For ‘Test for Equal Variances’, data
cannot be entered in columns, it
has to be stacked.
➢ Data > Stack > Columns

Transaction Time.mtw

Normality Test

• Stat>Basic Statistics>Normality test

• Check Anderson-Darling p-value
• Check normality for all samples

Transaction Time.mtw

37
 15-Aug-21

Test for Equal Variances

• Stat>ANOVA>Test for Equal Variances

• Check Levene p-value

• All variances are

H0 equal

• Not all variances are

Ha equal

ANOVA- One Way

• Stat>ANOVA>One-Way(Unstacked)
• Check p-value

• All means are equal

H0
• Not all means are
Ha equal

38
 15-Aug-21

Frequently Asked Questions

Why do we check whether the data follows normal
distribution?
• ANOVA One- Way assumes that the data follows normal distribution and therefore we
carry out normality test. We may carry out Anderson-Darling normality test and if p-
value is more than alpha, we consider that data follows normal distribution

What is Levene and Bartlett test for?

• Levene and Bartlett tests can be used to test variances of several groups.
• Bartlett test for variances assumes that the data follows normal distribution however
Levene doesn’t make any such assumption.
• Test for equal variances is carried out to satisfy assumption of homoscedasity (equal
variances) for ANOVA-One way

What is ANOVA for?

• Analysis of Variances- One Way tests to determine whether means of several groups
are equal or not
• Underlying Assumptions of ANOVA- One way
• Within each sample, the values are independent
• The k samples are normally distributed
• The samples are independent of each other
• The k samples are all assumed to come from populations with the same variance

39
15-Aug-21

40
15-Aug-21

41
 15-Aug-21

Scatter Diagram Interpretation

n=30 r=0.9 n=30 r=-0.9 n=30 r=-0.6

y-effect y-effect

x-cause x-cause Negative Correlation May Be Present

Positive Correlation Negative Correlation

n=30 r=0.6 n=30 r=0.0 n=30 r=0.0

Positive Correlation May Be Present No Correlation No Linear Correlation

42
 15-Aug-21

USES OF SCATTER DIAGRAM

❖ If an increase in Y depends on increase in X, then, if

X is controlled, Y will be naturally controlled.

❖ If X is increased, Y will increase somewhat. Then Y

seems to have causes other than X.

Scatter Diagram of Automotive Speed vs. Mileage

40

35
Mileage (km/Lit)

30

25

20

15
25 30 35 40 45 50 55 60 65 70

Speed (km/h)

93

43
 15-Aug-21

Scatter Plot
➢ Graph>Scatterplot

CaloriesConsumed.mtw

Correlation Analysis
➢ Scatter diagrams or plots provides a graphical representation of the
relationship of two continuous variables
➢ Correlation Analysis measures the degree of linear relationship
between two variables
o Range of correlation coefficient : -1 to +1
• Perfect positive relationship +1
• No relationship 0
• Perfect negative relationship -1

o If the absolute value of the correlation coefficient is greater than 0.85,

then we say there is a good relationship.
• Example: r = 0.9, r = -0.95, r = 1.0, r = -0.9 describe good relationship
• Example: r = 0.0, r = -0.3, r = +0.24 describe poor relationship.

o R squared is between 0.65 and 0.8 – Moderate correlation

o R squared in greater than 0.8 – Strong correlation

44
 15-Aug-21

Correlation Analysis

Coefficient of determination :

0 < | r | < .3 weak correlation

0.3 < | r | < .7 moderate correlation
| r | > 0.7 strong correlation

Is there any relation between your weight and your income.?

Is there any relation between your Income and the amount of

food you consume.?

Is there any relation between your weight and your phone

screen timing of your phone?

Is there any relation between the screen timing and Number

of Facebook friends.?

Is there any relation between your weight and weight of your

spouse.?

Is there any relation between your weight and the amount of water
you consume.?

Is there any relation between your weight and your sleeping time
(mins).?

Is there any relation between your phone screen timing and

sleeping time (mins).?

45
 15-Aug-21

Regression Analysis

• Regression analysis is used to:

– Predict the value of a dependent variable based on the value of at least one
independent variable
– Explain the impact of changes in an independent variable on the dependent variable

Dependent variable: the variable we wish to explain

Independent variable: the variable used to explain the dependent variable

R-sqr more than 70% is a good model

Regression Analysis
Delivery Time Sorting time
16.68 7
11.5 3
To arrive at an equation (best fit) to 12.03 3
predict correlation. 14.88 4
13.75 6
18.11 7
Delivery time (y) versus sorting time (x).
8 2
Are they perfectly correlated? 17.83 7
21.5 5
Value of R squared greater than 0.8 21 10
13.5 4
shows good fit. 19.75 6
24 9
29 10
15.35 6
19 7
DeliveryTime.mtw 9.5 3
17.9 10
18.75 9
19.83 8
10.75 4

46
 15-Aug-21

Example: Regression Analysis

Weight gained Calories Consumed
➢ Is there a relationship between
calories consumed and weight
gained? 0 1500
200 2300
900 3400
➢ Please find the following 200 2200
300 2500
o Rsq=
0 1600
o r=
0 1400
o Regression Equation 10 1900
600 2800
1100 3900
➢ If 3300 calories are consumed, 100 1670
how much weight will be gained? 150 1900
350 2700
700 3000

CaloriesConsumed.mtw

Correlation
➢ Stat>Basic Statistics>Correlation

CaloriesConsumed.mtw

47
 15-Aug-21

Regression
➢ Stat>Regression>Regression

CaloriesConsumed.mtw

Is there any relation between the sales of liquor and the atmospheric
temperature..?

48
 15-Aug-21

Output

Continuous Discrete

Graphical : Scatter Graphical : Histogram

Continuous Diagram

Statistical : Z test, T test,

Statistical : Regression ANOVA, F test
Input

Graphical : Pareto

Statistical : Logistic
Regression Statistical : 1 Proportion, 2
Discrete

Proportion, Chisquare

Taiichi Ohno’s 7 Wastes (muda)

Types of waste:

❖ Transport

❖ Inventory

❖ Motion

❖ Waiting time

❖ Overproduction

❖ Over processing

❖ Defective goods

49
 15-Aug-21

106 Types of Waste

Transportation
Definition: Irrational movement of material and
information.
Effects:
 Poor Ergonomics
 Safety Hazards
 Increased Lead time

107 Types of Waste

Inventory
Definition:
 A company's merchandise, raw materials, and
finished and unfinished products which have not
yet been sold but stored in different stages.

Effects:
 Huge Investments Lock

50
 15-Aug-21

Lean Tool Box 6

Inventory

Just in time Inventory: the minimum

inventory necessary to keep a perfect
system running.

“Inventory is evil” Shigo Shingo

• Holding cost

• Hide problems in the production system

Inventory

51
 15-Aug-21

110 Types of Waste

Motion
Definition:
 Any unnecessary motion of people.

Effects:
 Poor Ergonomics
 Very Low productivity(silent killer)

111 Types of Waste

Waiting Time
Definition:
 Man, Material and Machine waiting for information
and inputs.

Types:
 Process Delays
 Lot Delays

52
 15-Aug-21

112 Types of Waste

Over Processing
Definition:
 Providing or creating MORE than the customer
specification requirement.

Effects:
 Erosion in Profitability

113 Types of Waste

Over Production
Definition:
 Producing more, sooner or faster than is required
by the next process

Effects:
 Erosion in Profitability
 Increase in Inventory

53
 15-Aug-21

114 Types of Waste

Defects
Definition:
 Producing bad quality parts, services or
information

Effects:
 Increase in production cost
 Results in rework
 Results in shortage

Taiichi Ohno’s 7 Wastes (muda)

Types of waste:

❖ Transport

❖ Inventory

❖ Motion

❖ Waiting time

❖ Overproduction

❖ Over processing

❖ Defective goods

Any other wastes to be added…??

54
 15-Aug-21

Let’s do it!
Click once
when
Now ready.
wait for
45 1. - 6. -
seconds
30
15 Take 45
.
45
20
35
42
41
43
44
2
1
3
4
5
seconds
left
2. - 7. - seconds to
memorize
these new
3. - That was 8. -
easy! symbols for
the
4. - 9. - numbers
1 – 10.

5. -
10. - X

Write down as
many of the new
symbols as you
can remember?
Click when read
To check answers

55
 15-Aug-21

Check your answers

1. - 6. -

2. - 7. -

3. - 8. -

4. - 9. -

5. - 10. - X

Now, for you lean thinkers…

1 2 3 4 5 6 7 8 9 10

X
Does this help?

56
 15-Aug-21

KAIZEN

1 2 3

4 5 6

8 9
7

X
10

VA and NVA
Value-Added Step:
o Customers are willing to pay for it.
o It transforms the product/ service.
o It’s done right the first time.

Non value-Added Step:

Everybody looks o Is not essential to produce output.
busy but the o Does not add value to the output.
real work is idle o Includes:
90% of the • Defects, errors, omissions.
• Preparation/setup, control/inspection.
time..How? • Over-production, processing, inventory.
• Transporting, motion, waiting, delays.

Non Value Added Steps can be further classified

❑ Required NVA
❑ Business necessity (e.g. accounting)
❑ Employee necessity (e.g. payroll)
❑ Process necessity (e.g. inspection)
❑ NVA---Waste

57
 15-Aug-21

Why Value Stream Mapping ?

What is Wrong in this Picture?

House Sky
Window Chimney
Door Man Dog Mountain
Boy

Tree Cloud
Sun
Dress Dec Road Suit
Path

k
Woman Bird Fire

Why Value Stream Mapping?

A Picture is Worth a Thousand Words

58
 15-Aug-21

Value Stream Mapping

Time available
Takt Time =
Demand

Calculate Taktime if a customer requires 300 products within 8

days.?

Value stream C
125
ORDER CASH

$
ORDER CASH

$
ORDER CASH

NON VALUE ADD

$ VALUE ADD

59
 15-Aug-21

X is an identified cause for Y and Y is a negative undesirable effect. Is

the following statement True or False.?

It is possible that critical X is neither necessary

nor sufficient for Y to occur.

Outputs of Analyze Phase

➢ Identification Potential X’s

➢ Validated Root Causes

➢ Gap Analysis

The main output of the

Analyze phase is a list
of validated vital X’s

60
 15-Aug-21

www.iq6sigma.com

61