six sigma black belt week 1 - institute of industrial and ...€¦ · six sigma black belt week 1...
TRANSCRIPT
© 2009 Institute of Industrial Engineers1-3-1
Six
Sig
ma
Bla
ck B
elt
We
ek
1S
ix S
igm
a B
lack
Be
lt W
ee
k 1
Six
Sig
ma
Bla
ck B
elt
We
ek
1
Chapter 1-3
Introduction to Statistics
© 2009 Institute of Industrial Engineers1-3-2
Six
Sig
ma
Bla
ck B
elt
We
ek
1S
ix S
igm
a B
lack
Be
lt W
ee
k 1
Six
Sig
ma
Bla
ck B
elt
We
ek
1 Definitions - Statistics
The science that looks into the study of generic phenomena, normally complex and framed in a variable universe by means of the employment of reduction models of information and validation analysis of the results in representative terms.
The science and practice of developing human knowledgethrough the use of empirical data. It is based on statistical theory which is a branch of applied mathematics. Within statistical theory, randomness and uncertainty are modeled by probability theory.
© 2009 Institute of Industrial Engineers1-3-3
Six
Sig
ma
Bla
ck B
elt
We
ek
1S
ix S
igm
a B
lack
Be
lt W
ee
k 1
Six
Sig
ma
Bla
ck B
elt
We
ek
1 Descriptive Statistics
In order to be meaningful, data must be
presented and summarized so as to transmit the
information they represent.
© 2009 Institute of Industrial Engineers1-3-4
Six
Sig
ma
Bla
ck B
elt
We
ek
1S
ix S
igm
a B
lack
Be
lt W
ee
k 1
Six
Sig
ma
Bla
ck B
elt
We
ek
1 Methods of Summarizing Data
• Graphical
– Histograms
• Numerical
– Descriptive Statistics
• Means
• Standard Deviations
• Excel Applications
© 2009 Institute of Industrial Engineers1-3-5
Six
Sig
ma
Bla
ck B
elt
We
ek
1S
ix S
igm
a B
lack
Be
lt W
ee
k 1
Six
Sig
ma
Bla
ck B
elt
We
ek
1 Histogram
• A histogram is a way of summarizing data that are measured on an interval scale (either discrete or continuous). It is often used in exploratory data analysis to illustrate the major features of the distribution of the data in a convenient form.
• It divides up the range of possible values in a data set into classes or groups.
• For each group, a rectangle is constructed with a base length equal to the range of values in that specific group, and an area proportional to the number of observations falling into that group. This means that the rectangles might be drawn of non-uniform height.
© 2009 Institute of Industrial Engineers1-3-6
Six
Sig
ma
Bla
ck B
elt
We
ek
1S
ix S
igm
a B
lack
Be
lt W
ee
k 1
Six
Sig
ma
Bla
ck B
elt
We
ek
1 Histograms Give an Indication of
• Central Location or Balance Point
– Compare with customer target
• Dispersion or Spread
– Compared with customer upper and lower
performance requirements
• Shape
© 2009 Institute of Industrial Engineers1-3-7
Six
Sig
ma
Bla
ck B
elt
We
ek
1S
ix S
igm
a B
lack
Be
lt W
ee
k 1
Six
Sig
ma
Bla
ck B
elt
We
ek
1
Histogram
0
2
4
6
8
10
12
14
1 2 3 4 5 6 7 8
Hours
# o
f O
bse
rva
tio
ns
© 2009 Institute of Industrial Engineers1-3-8
Six
Sig
ma
Bla
ck B
elt
We
ek
1S
ix S
igm
a B
lack
Be
lt W
ee
k 1
Six
Sig
ma
Bla
ck B
elt
We
ek
1
© 2009 Institute of Industrial Engineers1-3-9
Six
Sig
ma
Bla
ck B
elt
We
ek
1S
ix S
igm
a B
lack
Be
lt W
ee
k 1
Six
Sig
ma
Bla
ck B
elt
We
ek
1 Descriptive Statistics
Measures of central
tendency show the
locations of the data. Measures of dispersion
indicate how widely
distributed the data are.
Measures of shape indicate how
well the data fits the standard
normal and how skewed the data
is.
© 2009 Institute of Industrial Engineers1-3-10
Six
Sig
ma
Bla
ck B
elt
We
ek
1S
ix S
igm
a B
lack
Be
lt W
ee
k 1
Six
Sig
ma
Bla
ck B
elt
We
ek
1 Statistical Symbols
• Greek letters are used for population statistics.
• English letters are used for sample statistics.
© 2009 Institute of Industrial Engineers1-3-11
Six
Sig
ma
Bla
ck B
elt
We
ek
1S
ix S
igm
a B
lack
Be
lt W
ee
k 1
Six
Sig
ma
Bla
ck B
elt
We
ek
1 Arithmetic Mean
Sum of the individual
values in the sample
divided by the number of
values in the sample.
XX
n=∑
. symbol theusesmean population The µ
© 2009 Institute of Industrial Engineers1-3-12
Six
Sig
ma
Bla
ck B
elt
We
ek
1S
ix S
igm
a B
lack
Be
lt W
ee
k 1
Six
Sig
ma
Bla
ck B
elt
We
ek
1 Median
The median is another measure of central
tendency. It is the middle value of a sample with
an odd number of values and the average of the
two middle values in a sample with an even
number of values.
© 2009 Institute of Industrial Engineers1-3-13
Six
Sig
ma
Bla
ck B
elt
We
ek
1S
ix S
igm
a B
lack
Be
lt W
ee
k 1
Six
Sig
ma
Bla
ck B
elt
We
ek
1 Excel®
© 2009 Institute of Industrial Engineers1-3-14
Six
Sig
ma
Bla
ck B
elt
We
ek
1S
ix S
igm
a B
lack
Be
lt W
ee
k 1
Six
Sig
ma
Bla
ck B
elt
We
ek
1 Measures of Dispersion
The range is the difference between the largest
and the smallest value within a sample. The
symbol is R.
© 2009 Institute of Industrial Engineers1-3-15
Six
Sig
ma
Bla
ck B
elt
We
ek
1S
ix S
igm
a B
lack
Be
lt W
ee
k 1
Six
Sig
ma
Bla
ck B
elt
We
ek
1 Measures of Dispersion
The standard deviation is a mathematically
derived statistic that shows the average
variability, or dispersion, of the individual sample
values about the sample mean.
A population standard deviation uses the symbol,
σ, while a sample standard deviation uses s.
© 2009 Institute of Industrial Engineers1-3-16
Six
Sig
ma
Bla
ck B
elt
We
ek
1S
ix S
igm
a B
lack
Be
lt W
ee
k 1
Six
Sig
ma
Bla
ck B
elt
We
ek
1 Sample Standard Deviation
1
)( 2
−
−=∑
n
xxS
x
© 2009 Institute of Industrial Engineers1-3-17
Six
Sig
ma
Bla
ck B
elt
We
ek
1S
ix S
igm
a B
lack
Be
lt W
ee
k 1
Six
Sig
ma
Bla
ck B
elt
We
ek
1
© 2009 Institute of Industrial Engineers1-3-18
Six
Sig
ma
Bla
ck B
elt
We
ek
1S
ix S
igm
a B
lack
Be
lt W
ee
k 1
Six
Sig
ma
Bla
ck B
elt
We
ek
1 Measures of Shape
• Skewness is a measure of symmetry, or more precisely,
the lack of symmetry. A distribution, or data set, is
symmetric if it looks the same to the left and right of the
center point.
• Kurtosis is a measure of whether the data are peaked or
flat relative to a normal distribution. That is, data sets
with high kurtosis tend to have a distinct peak near the
mean, decline rather rapidly, and have heavy tails. Data
sets with low kurtosis tend to have a flat top near the
mean rather than a sharp peak. A uniform distribution
would be the extreme case.
© 2009 Institute of Industrial Engineers1-3-19
Six
Sig
ma
Bla
ck B
elt
We
ek
1S
ix S
igm
a B
lack
Be
lt W
ee
k 1
Six
Sig
ma
Bla
ck B
elt
We
ek
1 Skewness
3
x
n
1
3
i
1)s-(n
)x-(x
Skewness∑
=
Negative values for the skewness indicate data that
are skewed left and positive values for the
skewness indicate data that are skewed right.
© 2009 Institute of Industrial Engineers1-3-20
Six
Sig
ma
Bla
ck B
elt
We
ek
1S
ix S
igm
a B
lack
Be
lt W
ee
k 1
Six
Sig
ma
Bla
ck B
elt
We
ek
1 Kurtosis
4
x
n
1
4
i
1)s-(n
)x-(x
Kurtosis∑
=
The kurtosis for a standard normal distribution is
three. For this reason, excess kurtosis is defined as
so that the standard normal distribution has a
kurtosis of zero. Positive kurtosis indicates a
"peaked" distribution and negative kurtosis indicates
a "flat" distribution.
31)s-(n
)x-(x
4
x
n
1
4
i
−
∑
© 2009 Institute of Industrial Engineers1-3-21
Six
Sig
ma
Bla
ck B
elt
We
ek
1S
ix S
igm
a B
lack
Be
lt W
ee
k 1
Six
Sig
ma
Bla
ck B
elt
We
ek
1