Dr. Pham Huynh Tram Department of ISE Phtram@hcmiu - Edu.vn
Dr. Pham Huynh Tram Department of ISE Phtram@hcmiu - Edu.vn
Dr. Pham Huynh Tram Department of ISE Phtram@hcmiu - Edu.vn
\
|
=
=
=
o
2
o o =
( )
1
1
2
1
1
2
1
2
2
|
.
|
\
|
=
=
=
n
n
x
x
n
x x
s
n
i
n
i
n
i
2
s s=
Find the sample mean and sample variance for
the following series of data:
Value
21
12
34
22
17
18
43
28
56
34
12
Practice with Calculator !!
Skewness
Measure of asymmetry of a frequency distribution
Skewed to left
Symmetric or unskewed
Skewed to right
Kurtosis
Measure of flatness or peakedness of a frequency
distribution
Platykurtic (relatively flat)
Mesokurtic (normal)
Leptokurtic (relatively peaked)
Skewed to left
6 0 0 5 0 0 4 0 0 3 0 0 2 0 0 1 0 0
3 0
2 0
1 0
0
x
F
r
e
q
u
e
n
c
y
Mean < median < mode
Mean = median = mode
6 0 0 5 0 0 4 0 0 3 0 0 2 0 0 1 0 0
x
3 0
2 0
1 0
0
F
r
e
q
u
e
n
c
y
Symmetric
Mode < median < mean
6 0 0 5 0 0 4 0 0 3 0 0 2 0 0 1 0 0
x
3 0
2 0
1 0
0
F
r
e
q
u
e
n
c
y
Skewed to right
3 . 7 2 . 9 2 . 1 1 . 3 0 . 5 - 0 . 3 - 1 . 1 - 1 . 9 - 2 . 7 - 3 . 5
7 0 0
6 0 0
5 0 0
4 0 0
3 0 0
2 0 0
1 0 0
0
X
F
r
e
q
u
e
n
c
y
Platykurtic - flat distribution
4 3 2 1 0 - 1 - 2 - 3 - 4
5 0 0
4 0 0
3 0 0
2 0 0
1 0 0
0
X
F
r
e
q
u
e
n
c
y
Mesokurtic - not too flat and not too peaked
Leptokurtic - peaked distribution
1 0 0 - 1 0
2 0 0 0
1 0 0 0
0
Y
F
r
e
q
u
e
n
c
y
Normal distribution
Calculate probability
Skewed distribution
Unknown distribution
K = 1
K=2
K=3
6826 . 0 ) 1 1 ( = + < < o o X P
9544 . 0 ) 2 2 ( = + < < o o X P
9973 . 0 ) 3 3 ( = + < < o o X P
1
1
2
1
1
4
3
4
75%
1
1
3
1
1
9
8
9
89%
1
1
4
1
1
16
15
16
94%
2
2
2
= = =
= = =
= = =
At least of the elements of any distribution
lie within k standard deviations of the mean
|
.
|
\
|
2
1
1
k
At
least
Lie
within
Standard
deviations
of the mean
2
3
4
Control charts are constructed by drawing samples and
taking measurements of a process characteristics. Each set
of measurements is called a subgroup
Control charts help to
- identify and differentiate between common causes and
special causes of variation
- determine a processs capability
Process is stable if it only exhibits common cause variation
When a process is stable, continuous improvement helps to
bring the centerline of the process closer to a desired level
(nominal) by reducing the magnitude of common cause
variations
-Centerline: drawn at the average value of all the plotted data.
-Control Limits (UCL, LCL): set at a distance of 3 sigma above and 3
sigma below the centerline. They indicate variation from the centerline
* Difference between control limits and specification limits?
27
29
30
31
32
Rule 5: 8 or more successive values continually increase
or decrease
Rule 6: unusual small number of runs above and below
center line are present ( a sawtooth pattern)
Rule 7: 13 consecutive points fall in zone C
Over adjustment
Process should be adjusted not on the basis of time-to-
time observations, but on the basis of information
provided by a statistical control chart
Funnel experiment
Under adjustment
Lack of attention when the process is out of control and
no effort is made to provide neccesary regulation
*Also, becareful on false out-of control signal
Defect prevention: atribute chart
P chart, mp chart, c chart, u chart
Continuous improvement: variable control chart
X bar chart, R chart, MR chart, s chart