Six Sigma Process Improvement Lecture

Six Sigma 2
Lean Manufacturing and Process

Improvement
Lecture 8, November 12, 2020
Week 10 Lean Manufacturing/ Process Improvement Slide 1

Understanding Process - (re-cap)
Suppliers Customers
Process
Internal/External Internal/External
Transformation
(Creating/ Adding
Value)
Requirements and Feedback Requirements and Feedback

Understanding Process - (re-cap)
Methods
Procedures
Process rules
X’s Customer requirement Y’s
Inputs Process Outputs
Information Activity
Materials Tasks
People Blending of Inputs
Energy
Tools
Equipment
Start Finish

Y=f(x) - (re-cap)
One of the most important

aspects of the Six Sigma
approach to problem solving is
understanding the concept.

Cause and effect
Y is equal to a function of (X)
This is the
• Y “Blending” or • X1 . . . Xn
• Dependent the way in • Independent
which the
• A Process Output process • A Process Input
• The Effect combines the • The Cause of a
inputs together
• It is a Symptom with various Problem
• Can Only be process • What Needs to be
activities. Controlled
Monitored
Th e p e rform ance of an outp ut or a ch aracte ri stic we are inte re ste d i

ni s
a functi on of th e p roce ssi np uts, calle d (X ’
s) and th e m anne r i n wh ich
th e p roce sscom b i ne sth e m toge th e r i
n orde r to p rovide th e re sultant
outp ut (Y ). W ritte n asY = f(X ).
Y=f(x) - Pizza Delivery Example
Output/ Measure = On time pizza deliveries

Y = The percent of on time deliveries
f(x)=The x's or reasons or things that heavily
influence on time deliveries
1. X1: Oven Cycle time
2. x2: traffic
3. x3: # of delivery's en route
4. x4: directions
5. x5: reliability of delivery vehicle

Y=f(x) - Pizza Delivery Example
 This problem solving methodology takes you through the process of determining all potential
"x's" that influence on time deliveries and then determining through measurements & analysis
which "x's" are significant. Those will become the "x's" that are used in the Y=f(x) equation.
 This problem solving strategy ensures that our pizza company does not spend $900,000 dollars
on a GPS system for it's delivery vehicles when the root cause is not actually "directions".
 The Y=f(x) equation is a very powerful concept and requires an ability to measure your output
and quantify your inputs. Measuring process inputs and outputs is crucial to effectively
determining the significant influences to any process.
 The Six Sigma methodology walks you through the steps of defining your problem, your goal,
your primary metric. Then, measuring your process, evaluating your measurement system,
determining all possible x's etc.
 The Six Sigma approach to problem solving leads you to the identification of the "critical" x's and
from there establishing an improvement plan as well as a means to control & maintain your
improvement. At the core of it all is the philosophy of Y=f(x).

World of measurement
Data is critical for problem solving!
Process improvement is all about
narrowing down to;
the vitalfew fac tors thatinflu enc e
the behaviorof a system ora proc ess.
Measure and observe process

characteristics and critical-to-quality
characteristics.
M easu re phase is generally the m ostd iffic u ltand tim e-
c onsu m ing bu t
if itis d one rightthe firsttim e,itwillsave lotof trou ble atthe later
stage and m axim ize the c hanc e of im provem ent.
Measure
1. What is the actual process being performed compared to
what I think it is (Process Map) ?
2. How are the processes associated with this problem

really working (Capability)?
3. Is my ability to measure/detect accurate enough to make

good decisions (Measurement System Analysis)?
4. Which inputs (Critical X’s) seem to have the greatest

effect on the outputs (Y’s)?
Identify the tru e proc ess and determine the m ostlikely c ontribu tors
including the statistic aldetermination of the ac c u rac y and
repeatability of the data that characterize the process.
The leverage funnel
You will find many X’s at

Start of project
Number of X’s keeps

reducing as you work through project
The number of X’s after

DMAIC implemented should be minimum

MEASURE
De ve lop Data colle cti on Plan
• What, why, where, how data will be collected and who will do it
Conduct data colle cti on
• (50 to 100) for attribute data • Be nch m ark
• At least 30 data • Cap ab i li
ty of give n p roce ss
Pe rform Grap h i calanaly si s
(Pareto, Histogram, Box plot, run chart) • Focuson CTQ
Pe rform Me asure m e nt sy ste m sanaly si s: minimize measurement
variation to ensure only process variation is reflected by the data. Using:
• Operational definitions
• Gage R&R
Conduct Base li ne cap ab i lity analy sis: to show if the current process is
capable of meeting customer requirements and what is the percentage of
defects of the process
• Attribute data: calculate DPMO to determine % yield and current sigma
level
• Variable data :
» Cp (the amount of variation in the process) (USL-LSL)/ 6* Std.De v
» Cpk (compares the natural tolerance of a process against its
specification limits to reveal if there is a problem with specification
centering).
Data and Measurement Scales
 Data
 Two Types
 Quali tati
ve Data – Placed into distinct categories,
according to some characteristics or attributes. e.g.
Subjects classified according to gender, religious
preferences, or geographic locations
 Quantitative Data: Numerical and can be ordered or

ranked. e.g. age, height, weight
 Discre te data – can be assigned values such as, 0, 1, 2 and

countable. e.g. number of children
 Conti nuousdata - assumes an infinite number of values

between two specific values. Include decimal and fractions e.g.
1.2, 1.3

 Measurement Scales – how data are categorized, counted
or measured
 Four Types
 Nom i nal– Classifies data into mutually exclusive
(non-overlapping), exhausting categories in which no
order or ranking can be imposed on the data
 Ordi nal- classifies data into categories that can be
ranked; however, precise differences between the
ranks do not exist
 Inte rval– ranks data and precise difference between
units of measure do exist; however, there is no
meaningful zero.
 Rati o – possesses all the characteristics of interval
measurement, and there exists a true zero. Also, true
ratios exist when the same data is measured on two
different members of population

 Measurement Scales
Nominal Ordinal Interval Ratio
Postal code Grade (A,B,C,D,F) SAT score Height
Gender (Male, Judging(First IQ Weight
Female) place, second Temperature Time
Eye color ( Blue, place, etc) Salary
brown, green, Rating (Poor, Age
hazel) Good, Excellent)
Political affiliation

Data Collection Methods and Sampling
 Data Collection Methods
There are many methods used to collect or
obtain data for statistical analysis. Three of
the most popular methods are:
• Direct Observation
• Experiments, and
• Surveys

 Survey
A su rvey solicits information from people; e.g. Gallup
polls; pre-election polls; marketing surveys.
The Response Rate (i.e. the proportion of all people

selected who complete the survey) is a key survey
parameter.
Surveys may be administered in a variety of ways,
e.g.
» Personal Interview,
» Telephone Interview,
» Self Administered Questionnaire
» Internet

 Questionnaire Design
Over the years, a lot of thought has been put into the
science of the design of survey questions. Key design
principles:
- Keep the questionnaire as short as possible.
- Ask short, simple, and clearly worded questions.
- Start with demographic questions to help respondents get
started comfortably.
- Use dichotomous (yes/ no) and multiple choice questions.
- Use open-ended questions cautiously.
- Avoid using leading-questions.
- Pretest a questionnaire on a small number of people.
- Think about the way you intend to use the collected data when
preparing the questionnaire.

 Sam p li
ng
 Recall that statistical inference permits us to draw
conclusions about a population based on a sample.
 Sampling (i.e. selecting a sub-set of a whole population)

is often done for reasons of c ost(it’s less expensive to
sample 1,000 television viewers than 100 million TV
viewers) and prac tic ality (e.g. performing a crash test
on every automobile produced is impractical).
 In any case, the sam pled popu lation and the target
popu lation should be si mi lar to one another.

 Sam p li
ng Plans
 A sam pling plan is just a method or procedure for
specifying how a sample will be taken from a population
 We will focus our attention on these three methods:

• Simple Random Sampling,
• Stratified Random Sampling, and
• Cluster Sampling
• Random sampling, by far, is the most commonly used

 Si
m p le Random Sam p li
ng
A sim ple rand om sam ple is a sample selected in such a way that every
possible sample of the same size is equally likely to be chosen.
 Drawing three names from a hat containing all the names of the
students in the class is an example of a simple random sample: any
group of three names is as equally likely as picking any other group
of three names.
 VERY EASY TO DEFINE!
 VERY, VERY DIFFICULT TO DO!
• Random sample of 100 cokes bottles today at the coke plant.
• Random sample of 50 pine trees in a 1000 acre forest.
• Random sample of 5 deer in a national forest.
If we are studying whether a certain die is fair or weighted, the population would be all
possible tosses of the die

 Si
m p le Random Sam p li ng
A government income tax auditor must choose a
sample of 5 of 11 returns to audit…[Can do many
different ways]
Generate Sorted
Person Random # Person Random #
baker 0.87487 1 mark 0.08350
george 0.89068 2 ralph 0.11597
ralph 0.11597 3 joe 0.24662
mary 0.58635 4 sally 0.34346
sally 0.34346 5 aaron 0.37239
joe 0.24662 andrea 0.47609
andrea 0.47609 greg 0.53542
mark 0.08350 mary 0.58635
greg 0.53542 kim 0.73809
aaron 0.37239 baker 0.87487
kim 0.73809 george 0.89068

 Strati fi
e d Random Sam p li ng
A stratified rand om sam ple is obtained by separating the
population into mutually exclusive sets, or strata, and then
drawing simple random samples from each stratum.
Strata 1 : Gender Strata 2 : Age Strata 3 : Occupation
Male < 20 professional
Female 20-30 clerical
31-40 blue collar
41-50 other
51-60
> 60
We can acquire about the total population, make inferences within a stratum
or make comparisons across strata

 Strati fi
e d Random Sam p li ng
After the population has been stratified, we can use sim ple
rand om sam pling to generate the complete sample:
If we only have sufficient resources to sample 400 people total,

we would draw 100 of them from the low income group…
…if we are sampling 1000 people, we’d draw
50 of them from the high income group.

 Cluste r Sam p li ng
A c lu stersam ple is a simple random sample of groups or
clusters of elements (vs. a simple random sample of
individual objects).
This method is useful when it is difficult or costly to develop
a complete list of the population members or when the
population elements are widely dispersed geographically.
Used more in the “old days”.
Cluster sampling may increase sampling error due to

similarities among cluster members.

 Sam p le Si ze
 Numerical techniques for determining sample
sizes will be described later, but suffice it to say
that the larger the sample size is, the more
accurate we can expect the sample estimates to
be.

 Sam p li
ng and Non-Sam p li
ng Errors
Two major types of error can arise when a sample of observations is
taken from a population:
 sam pling errorand non- sam pling error.
• S am pling errorrefers to differences between the sample and the

population that exist only because of the observations that happened
to be selected for the sample. They are random and we have no
control over.
• N on-sam pling errors are more serious and are due to mistakes
made in the acquisition of data or due to the sample observations
being selected improperly. Most likely caused by poor planning, sloppy
work, act of the Goddess of Statistics, etc.

 S am pling E rror
S am pling erroris the error caused by observing a
sample instead of the whole population. It is the
difference between a sample statistic used to
estimate a population parameter and the actual but
unknown value of the parameter (Bunns & Grove,
2009).
Increasing the sample size willreduce this type of

error.

 Non-Sam p li
ng Error
N on-sam pling errors are more serious and are due to
mistakes made in the acquisition of data or due to the
sample observations being selected improperly. Three types
of non sampling errors:
 Errors in data acquisition,

 Nonresponse errors, and
 Selection bias.
Note: increasing the sample size wi
llnot reduce this type of
error.

 Errorsi
n data Acqui
siti
on
…arises from the recording of incorrect responses, due to:
— incorrect measurements being taken because of
faulty equipment,
— mistakes made during transcription from primary
sources,
— inaccurate recording of data due to
misinterpretation of terms, or
— inaccurate responses to questions concerning
sensitive issues.

 Nonre sp onse Error
…refers to error (or bias) introduced when responses are
not obtained from some members of the sample, i.e. the
sample observations that are collected may not be
representative of the target population.
As mentioned earlier, the Response Rate (i.e. the

proportion of all people selected who complete the survey)
is a key survey parameter and helps in the understanding in
the validity of the survey and sources of nonresponse error.

 Se le cti
on Bi as
…occurs when the sampling plan is such that some
members of the target population cannot possibly
be selected for inclusion in the sample.

Descriptive Statistics
Descriptive statistics are summary measures which

define some important characteristics of data.
1. Measures of location
i. Measures of central tendency
ii. Measures of position
2. Measures of dispersion (variation)

Measures of Location
Measures of central tendency
Measures of central tendency are numerical values that tend

to locate in some sense the middle of a set of data.
• Arithmetic Mean
• Median
• Mode

Arith m e ti
c Me an (Me an)
The arithmetic mean is the most common measure of
the central tendency and is commonly used for
symetrical distributions. It is used to summarize
quantitative data.
n
Sum of all the observations  xi divided by the

i 1
number of the observations (n).
n
x i
X  i 1
n
Example:
Age distribution of seven children attending to a children

clinic is given below
{1,3,6,7,2,3,5}
n 7
x x i i
1  3  6  7  2  3  5 27
X  i 1
 i 1
 
n 7 7 7
X  3.9 years
M ed ian
The median is the middle value of the set of data when the
data are ranked in order according to magnitude.
When the data are put in order 50 % of the observations

are less than or equal to the median, the rest is greater
than the median .
th
 n  1 observation.
Median value is
 
 2 

Example:
n is odd: 5, 28, 8, 10, 9
Ordered data 5, 8, 9, 10, 28
i =(5+1)/2=3
Median is 3rd value which is 9.
n is even: 19, 20, 17, 27, 6, 21
Ordered data 6, 17, 19, 20, 21, 27
i=(6+1)/2=3.5
Median is halfway between the 3rd and 4th values, which
is 19.5.
Mode
The mode is the value of x that occurs most frequently.
Data {1,3,7,3,2,3,6,7}
• Mode : 3
Data {1,3,7,3,2,3,6,7,1,1}
• Mode : 1 and 3
Data {1,3,7,0,2,-3, 6,5,-1}

• Mode : No mode

Ex am p le :
Suppose the age in years of the first 10 subjects enrolled in your
study are:
34, 24, 56, 52, 21, 44, 64, 44, 42, 46
Find;
Mean
Median
Mode

Ex am p le :
Suppose the age in years of the first 10 subjects enrolled in your
study are:
34, 24, 56, 52, 21, 44, 64, 44, 42, 46
Then the mean age of this group is 42.7 years
To find the median, first order the data:

21, 24, 34, 42, 44, 44, 46, 52, 56, 64
The median is (10+1)/2 = 5.5

The median is 44
The mode is 44 years.
Measures of position
Measures of position are used to decribe the location of a
specific piece of data in relation to the rest of the sample.
Quartiles and percentiles are two most popular measures of
position.

Quartiles
Quartiles are numeric values of variable that divide the
ordered data into quarters; each set of data has three
quartiles.
The first quartile, Q1, is a number such that at most one-
fourth of the data are smaller in value than Q1 and at most
three-fourths are larger.
n 1
Q1  th
4
The second quartile, Q2, is the median.
2( n  1) n  1
Q2   th
4 2
The third quartile, Q3, is a number such that at most three-

fourths of the data are smaller in value than Q3 and at most
one-fourth are larger.
3(n  1)
Q3  th
4

Example: Birthweights of 24 infants are as follows:
Obs. Weight Obs. Weight Obs. Weight Obs. Weight
1 2850 7 3150 13 3250 19 3700
2 2900 8 3200 14 3400 20 3800
3 2930 9 3200 15 3450 21 3900
4 2980 10 3200 16 3500 22 4100
5 3000 11 3250 17 3500 23 4400
6 3100 12 3250 18 3600 24 4500

25
First quartile=Q1=  6.25 th obs. is the fist quartile.
4
6th obs.=3100gr 7th obs.=3150gr
50x0.25=12.5gr
Q1=3112.5gr.
25
Second quartile=Median=Q2=  12.5 th obs. is the second
quartile or median. 2
Q2=3250gr.
3x 25
Third quartile=Q3=  18.75 th obs. is the third quartile
4

100x0.75=75gr.
Q3=3675gr.
25% of the infants have birthweights less than 3112,5gr.
Half of the infants have birthweights less than 3250gr.
75%of the infants have birthweights less than 3675 gr.

Measures of variation
Range
The range is the simplest measure of dispersion. It is the
difference between the highest valued (H) and the lowest
valued (L) of the observations.
Range= H-L

Pop ulati on consistsof allsub je ct (h um an or oth e rwi

se ) th at
are b e i
ng studied
Sam p le isa group of sub je ctsse le cte d from a

p op ulati
on.

Pop ulation Standard de vi ati

on is the average distance of
observations to arithmetic mean.
N
 i
( x   ) 2
 i 1
N
Pop ulati
on Vari
ance is square of standard deviation.
N
 i
( x   ) 2
2  i 1
N

Sam p le Standard de viati on is the average distance of

observations to arithmetic mean.
n  x  2
 i   i 
2 2 i
( x x ) x
s n
s i 1
or
n 1 n 1
Sam p le Vari ance is square of standard deviation.

n
  xi 
2

2
( x i x ) xi 
2
s 2  i 1 or s2  n
n 1 n 1


Step 1 Step 3 Step 4
x 25
x (xx) (xx)2 Step 2 x  5
n 5
6 1 1
3 -2 4
8
5
3
0
9
0 Step 5 s 
2  ( x  x ) 2

18
 4.5
n 1 4
3 -2 4
25 0 18 s  s 2  4.5  2.12

Graphical Method
• A frequ enc y d iagram shows the number of times each
of the measured values occurred when the data were
collected. This diagram can be created either from
measurements taken from a process or from data taken
from the occurrences of events.

Graphical Method
 To create a frequency diagram:

• 1. Collect the data. Record the measurements or counts of the
characteristics of interest.
• 2. Count the number of times each measurement or count occurs.
• 3. Construct the diagram by placing the counts or measured values
on the x axis and the frequency or number of occurrences on the y
axis. The x axis must contain each possible measurement value
from the lowest to the highest, even if a particular value does not
have any corresponding measurements. A bar is drawn on the
diagram to depict each of the values and the number of times the
value occurred in the data collected.
• 4. Interpret the frequency diagram. Study the diagrams you create
and think about the diagram’s shape, size, and location in terms of
the desired target specification.
Graphical Method

Graphical Method
• Histograms
– Similar to frequency diagrams.
• The most notable difference between the two is that on a histogram
the data are grouped into cells. Each cell contains a range of
values.

Graphical Method
 To create a histogram:
• Step 1: Collect the data and construct a tally sheet
• Step 2: Calculate the range
• Step 3: Create the cells by determining the cell intervals,
midpoints, and boundaries
• Step 4: Label the axes
• Step 5: Post the values
• Step 6: Interpret the histogram

Graphical Method
• Analy si
sof Hi
stogram s
– Shape, spread, and location are the characteristics used to
describe a distribution

Graphical Method
– Shape: refers to the form that the values of the

measurable characteristics take on when plotted
or graphed.
– Shape is based on the distributions symmetry, skewness, and
kurtosis
– Spread: the distance between the highest and
lowest values
– Location: Where is the distribution in relation to
the target?

Cause and effect
Y is equal to a function of (X)
This is the
• Y “Blending” or • X1 . . . Xn
• Dependent the way in • Independent
which the
• A Process Output process • A Process Input
• The Effect combines the • The Cause of a
inputs together
• It is a Symptom with various Problem
• Can Only be process • What Needs to be
activities. Controlled
Monitored
Th e p e rform ance of an outp ut or a ch aracte ri stic we are inte re ste d i

ni s
a functi on of th e p roce ssi np uts, calle d (X ’
s) and th e m anne r i n wh ich
th e p roce sscom b i ne sth e m toge th e r i
n orde r to p rovide th e re sultant
outp ut (Y ). W ritte n asY = f(X ).
Correlation vs Causation
Correlation:
A correlation is a relationship between two or more things which
change (variables) that can be described mathematically. Correlation
refers to how closely two sets of information or data are related.
A positive correlation means that when one thing goes up, the other
goes too. A negative correlation is the opposite, when one goes up,
the other goes down.
Correlation is often described statistically, utilizing what is known as

the square of the correlation coefficient or R2.
The closer R2 is to one, the better the correlation. (0.98)
Example:
when the demand for a certain product goes up, its price tends to go
up as well, so there is a positive correlation between the two things.

Correlation vs Causation
Correlation:
That is, a causal relationship between two things or events exists if
one occurs because of the other.
A cause that produces an effect, or that which gives rise to an action,
phenomenon, or condition, is termed causation. E.g. If a change in “X”
produces a change in “y”, then X is said to be the cause of “Y”
3.Causation, on the other hand, means that one thing will cause the
other. For example, when you exercise the amount of calories you are
burning per minute will go up, as the former is causing the later.
4.Correlation and causation can happen at the same time. In the
example above about exercising, for example, there’s both correlation
and causation in place.
5.However, having a correlation doesn’t imply that you also have
causation, and this is where most people get confused.
6.For example, there is a positive correlation between the number of
firemen fighting a fire and the size of the fire. However, this doesn’t
mean that bringing more firemen will cause the size of the fire to
increase (this is called reverse causation).
Scatter Plot
A scatter plot provides

a complete picture of
the relationship
between two variables

Correlation Coefficient
The correlation coefficient, r, provides the strength

and direction of the relationship between the
independent and dependent variables.

Correlation coefficient is calculated using the following
formula:

Example
Relationship between Exercise time and weight loss
Hours of Weight
exercise in a reduction in xy x2 y2
week (x) lbs (y)
3 2 6 9 4
5 4 20 25 16
10 6 60 100 36
15 8 120 225 64
2 1 2 4 1
3 3 9 9 9
∑x = 38 ∑y = 24 ∑xy =217 ∑x2= 372 ∑y2= 130

6(217) – (38 x 24)

r=
[6(372) – (38)2] [ 6(130) – (24)2]
r = 0.972
The value of r shows that there is a strong correlation
between hours of Exercise and weight loss.

Simple Regression
 Simple regression is used to describe a straight
line that best fits a series of ordered pairs (x, y)
 Determining the regression where correlation (r)

is not significant and then making predictions
using the regression line are meaningless
 The purpose of the regression line is to see the

trend and make predictions on the basis of the
data

Simple Regression
The closer the points are to the line, the better the fit and the
prediction will be.

Simple Regression Equation
y = a + bx
Where,
or, a = y – b x

Simple Regression Example
Month (x) Complaints (y) x2 xy y2
1 8 1 8 64
2 6 4 12 36
3 10 9 30 100
4 6 16 24 36
5 10 25 50 100
6 13 36 78 169
7 9 49 63 81
8 11 64 88 121
∑x = 36 ∑y = 73 ∑x2= 204 ∑xy =353 ∑y2= 707
X = 4.5 Y = 9.125
Simple Regression Equation: Example
8 (353) – (36) (73)

b= b = 0.5833
8 (204) – (36)2
a=y–bx a= 9.125 – 0.5833 (4.5) = 6.5
y = a + bx y = 6.5 + 0.5833 x
Since, slope (b) of the equation is positive, there is evidence that the
number of complaints increase over time


Six Sigma Process Improvement Lecture

Uploaded by

Document Information

Original Description:

Original Title

Copyright

Available Formats

Share this document

Share or Embed Document

Sharing Options

Did you find this document useful?

Is this content inappropriate?

Copyright:

Available Formats

Six Sigma Process Improvement Lecture

Uploaded by

Copyright:

Available Formats

Six Sigma 2

Lean Manufacturing and Process

Week 10 Lean Manufacturing/ Process Improvement Slide 1

Week 10 Lean Manufacturing/ Process Improvement Slide 2

Week 10 Lean Manufacturing/ Process Improvement Slide 3

One of the most important

Week 10 Lean Manufacturing/ Process Improvement Slide 4

Th e p e rform ance of an outp ut or a ch aracte ri stic we are inte re ste d i

Output/ Measure = On time pizza deliveries

Week 10 Lean Manufacturing/ Process Improvement Slide 6

Week 10 Lean Manufacturing/ Process Improvement Slide 7

Measure and observe process

2. How are the processes associated with this problem

3. Is my ability to measure/detect accurate enough to make

4. Which inputs (Critical X’s) seem to have the greatest

You will find many X’s at

Number of X’s keeps

The number of X’s after

Week 10 Lean Manufacturing/ Process Improvement Slide 10

 Quantitative Data: Numerical and can be ordered or

 Discre te data – can be assigned values such as, 0, 1, 2 and

 Conti nuousdata - assumes an infinite number of values

Week 10 Lean Manufacturing/ Process Improvement Slide 12

Week 10 Lean Manufacturing/ Process Improvement Slide 13

Week 10 Lean Manufacturing/ Process Improvement Slide 14

Week 10 Lean Manufacturing/ Process Improvement Slide 15

The Response Rate (i.e. the proportion of all people

Week 10 Lean Manufacturing/ Process Improvement Slide 16

Week 10 Lean Manufacturing/ Process Improvement Slide 17

 Sampling (i.e. selecting a sub-set of a whole population)

Week 10 Lean Manufacturing/ Process Improvement Slide 18

 We will focus our attention on these three methods:

• Random sampling, by far, is the most commonly used

Week 10 Lean Manufacturing/ Process Improvement Slide 19

Week 10 Lean Manufacturing/ Process Improvement Slide 20

Week 10 Lean Manufacturing/ Process Improvement Slide 21

Week 10 Lean Manufacturing/ Process Improvement Slide 22

If we only have sufficient resources to sample 400 people total,

Week 10 Lean Manufacturing/ Process Improvement Slide 23

Cluster sampling may increase sampling error due to

Week 10 Lean Manufacturing/ Process Improvement Slide 24

Week 10 Lean Manufacturing/ Process Improvement Slide 25

• S am pling errorrefers to differences between the sample and the

Week 10 Lean Manufacturing/ Process Improvement Slide 26

Increasing the sample size willreduce this type of

Week 10 Lean Manufacturing/ Process Improvement Slide 27

 Errors in data acquisition,

Week 10 Lean Manufacturing/ Process Improvement Slide 28

Week 10 Lean Manufacturing/ Process Improvement Slide 29

As mentioned earlier, the Response Rate (i.e. the

Week 10 Lean Manufacturing/ Process Improvement Slide 30

Week 10 Lean Manufacturing/ Process Improvement Slide 31

Descriptive statistics are summary measures which

Week 10 Lean Manufacturing/ Process Improvement Slide 32

Measures of central tendency

Measures of central tendency are numerical values that tend

Week 10 Lean Manufacturing/ Process Improvement Slide 33

Sum of all the observations  xi divided by the

Age distribution of seven children attending to a children

When the data are put in order 50 % of the observations

Week 10 Lean Manufacturing/ Process Improvement Slide 36

Data {1,3,7,0,2,-3, 6,5,-1}