Documenti di Didattica
Documenti di Professioni
Documenti di Cultura
Indian Statistical
Institute
98 sampatrao Colony
BARODA 390 007
Factor
Measure
Report
Review
Total
Improve
Total
Guidelines for
scoring
1. Use the same 6
factors and the
time
scale as was used
while defining
ideal
quality value.
M
R
R
I
5 = Always
Performance of the listed factor is
measured
4 = Often
The performance measure is
reported
3 = Occasionally
The management
reviews the performance reports
2 = Rarely
Improvement actions
stem from the reviews
1 = Never
Factor
Measure
Report
Review
Total
Improve
Total
20
40
60
Belief Score
80
100
120
Cutting to the
Core
Behavior is a function of values
B = f(V)
Behavior
The way in which a person or group of people responds
Values
The complex of beliefs, ideals or standards which
characterizes a person or group of people
30%
Typical Company
Your Area?
The Need
If we dont know, we can
not act
The Role of
Questions
Questions lead and answers follow. The same question most often lead to
the same answers which invariably produce the same result. To change
the result means to change the question.
New
As
ability to survive
and prosper will increase, owing to the discovery of answers to
problems heretofore not known.
Insanity is doing the same thing over and over again but expecting different results Rita Mae Brown (Author)
Measurement
Question
Search
Knowledge
10
The Role of
Training
Undoubtedly the most
11
What is Quality
Quality means different things to different people. There is
no universally accepted definition.
However, there is a broad agreement on the following
Very difficult to define
Determined by customer
Multi dimensional
Dynamic
Needs to be TOTAL
13
Appropriateness of requirements
Customer
Satisfaction
Degree of conformance to
requirements
Cost of identifying and meeting the
requirements
14
Components of
Main
Quality
Quality of Design
Componen
Decides the level of customer
attraction
Related to market segmentation
based on product grade
t
Quality of
Design
Subcomponen
t
Product
Design
Process
Design
Rated efficiency
Process capability
Cycle time
Downtime for regulatory inspection
Process
Conformance
Process instability
Process failures
Late deliveries
Loss of efficiency/yield
Product
Conformance
Field failures
Factory scrap and rework
Deviation from target
Incorrect invoices
Quality of Conformance
Refers to the deficiencies
resulting from lack of control
Decides the level
customer dissatisfaction
of
Improving quality of
conformance always leads to
reduction of costs. It is in this
sense that Crosby says
quality is free
Quality of
Conformance
Examples of features
16
System Design
Parameter Design
Tolerance Design
Quality
Statistical Tools
Process Monitoring
and Adjustment
Quality of
Conformance Problem Solving
Product Disposal
17
Product
Design
in
AECL
This
Programm
e
System
Design
Limited*
Nil
Paramet
er
Design
-do-
The concept
of robustness
only
Toleranc
e Design
-do-
Nil
System
design
Limited**
Nil
The concept
of robustness
only
Illustration
18
with an
Process
Conforman
ce
Product
Conforman
ce
e in
AECL
Process
Monitorin
g and
Adjustme
nt
Very
High
Problem
Solving
Very
High
Product
Disposal
High
Field
This
Programm
e
Concepts,
disciplines
and simple
tools of
problem
solving
Bulk Sampling,
Acceptance Sampling,
Loss Function
Issues in bulk
sampling only
Quality
High with Statistics
Nil
Nil 19
Chapter 2:
Data
Data are facts or figures related to any characteristic of
an individual
Also called a variable
A m/c, an year, a casting, a dimension, a person
Date of
commissioning
Availability
(%)
No. of
outages
C:15
12/11/98
92.5
9
30
C:16
10/05/97
93.0
4
12/10/78
88.3
2
INDIVIDUALS
Average
duration of
non-stop
operation
(days)
Main
cause of
outage
Capacity
utilization
Forced
Planned
27
64
52
Leakag
e
High
47
28
52
52
Leakag
e
Mod.
124
58
261
164
Gen*
V. Low
* Generator stator / rotor problem
21
Types of Data/Variable
D a t a / V a r ia b le
N u m e r ic a l/ Q u a n t it a t iv e
C o n t in u o u s
D is c r e t e
C a t e g o r ic a l/ Q u a lit a t iv e
O r d in a l
N o m in a l
22
Variable Type
1. Date of commissioning
2. Availability (%)
3. Number of outages since
commissioning
4. Average duration of non-stop
operation (days)
5. Average loss per outage
(hours)
6. Main cause of outage
7. Capacity utilization
23
24
Data Gateway
DATA
COLLECTION
Problem/
Hypothesi
s
DATA ANALYSIS
Dat
a
Solutio
n/
Fact
25
Rank*
Wrong data
Misleading
information
Cooked data
Noisy Data
Potentially
misleading
information
High gauge
R&R
Old data
Partial information
Small sample
Hard data
Difficult to process
Censored
data
Redundant
Quality
with
Statistics
Useful but
adds
to
Multiple
626
Attribute
Data
Variable
Data
Very low
Low
Low
Moderate
Moderate
High
Moderate
High
High
Very High
General literature
Past data: In-house routine
Q.C records
27
VARIABLES
Var. 1 Var. 2 Var. 3
Population
.
Var. p
Ind. 1
Data
Data
Data
Ind. 2
Data
Data
Data
Data
Ind. 3
Data
Data
Data
Data
Ind. n
Data
Data
Data
Sample
Data
.
.
Measurement
.
Data
Recording
Quality with
Statistics
Editing, Storage,
28
Wron
g
Individua
l
Procedur
e
Inade
quat
e
Har
d
Gauge
Appraise
r
Others
Record
ing
Irrele
vant
Variables
Size
Measu
remen
t
Noisy
Format
Recorder
Editing, Storage,
Retrieval
Redun
dant
Issues
relate
d to
data
base
mgmt.
Quality
with Statistics
29
Individu
al
Sampl
e
Variabl
e
Samplin
g
Method
Size
Measureme
nt
Measuran
Gaug
d
e
Metho
Apprais
d
er
Poor
Data
Operat
Softwar
or
Hardwar
e
Forma e
Data base
Mgmt.
t
policy
Recordin
Editing, storage,
g
retrieval
Record
er
Qualit
y
Note: Due to limitations of space, only the main subcauses are shown in the CE diagram.
30
Operatio
n
done
Statu
Breakdow
s
Done long back n
Not
Resultsused
Measuremen
t
Bia
s
Malfunctionin
g
Inadvertent
error
Numbe
Appraiser
s
Reproducibili
ty
Unstabl
e
Not
traceable
Gauges
Different
makes
Many
Variable
least
count
Numbe
r
Operating
range
Beyond
limit
Capabilit
y
Low
repeatabilit
y Precision
Low least
count
Measuran
d
Inhomogeneou
s
Standard
procedure
Not
availabl
e
Type of
data
Unwante
d
Not
followed
Communicatio
n
Metho
d
Poor
Data
Qualit
y
31
The Planning
Questions
1) What do you want to
know?
2) How do you want to
see what it is that you
need to know?
3) What type of tool
will generate what it
is that you need to
see?
4) What type of data
is required of the
selected tool?
Illustration
Has X any effect on
Y?
X1 X2
X3 Y
.
. . .... . ...
..
.. .
Y
Histogra
m
X1 X2 X3
Y11 Y21
Y31
.
.
.
Y1n Y2p
Y3qinspection
Final
and production
log book
Scatter
diagram
X
X1
.
Xn
Y
Y1
.
Yn
Nowhereto be
collected
32
Clarity of purpose
Use of a structured approach
Commonly used data collection tools, that satisfies the two requirements
are
Check Sheet
Data Sheet
33
Month:
September
Sampling
interval: Every 3.5 demand
hours
Target: Min(420,
Data: Target - Y1
Y1) Class
bar
Check
Interval
<-54.99
-54.99 to
44.99
-44.99 to
34.99
Wasteful export
due to lack of
control
7
5
Export limit =
-10
-34.99 to
24.99
-24.99 to
14.99
Import limit =
+20
-14.99 to
04.99
-04.99 to
05.01
05.01 to
15.01
15.01 t0
Wasteful import
due to lack of
control
Defect rate = 27
%
8
12
6
16
342
35.0
30.0
25.0
20.0
15.0
10.0
5.0
0.0
1340
1237
1134
1031
928
825
722
619
516
413
310
207
104
35
Total
Process
failure
52
Process
deficienc
y
81
Early
slowdow
n
15
Late pick
up
34
Total
54
22
65
21
20
182
36
PF
30
15
PD
11
36 14 11
ES
LP Process
11 11
PF=
PD=
Process
failure
ES=
Early
deficiency slow
LP=
downLate pick
up
PF
29.
0
29.
5
PD
10
ES
10
30
15
7
LP 10
4
Total generation loss
(MWH)
C15 C16
D
E
30
15
Tota
l
PF
870
160
5
725
320
0
PD
55
18
360
70
55
558
ES
20
270
30
328
LP
110
44
150
105
409
with
238 Statistics
795 190
449
5
Tota
l
105
Quality
70
5
107.0 103.5
110.
0
37
Checks are made against the cause of a problem in the C-E diagram.
38
Var. 1
Common relevant
information
Var.
2
Var. p
Remar
k
Ind. 1
Ind. 2
Ind. n
Notes:
Important summary of
data
39
time
a
lity
wag
ons
m
date
m
time
t.
date
t.
time
.
hours
.
hours
son
Actual
unloadin
g time Hr.
01
01
19.45
Envi
ro
58
02
05.3
5
02
15.30
09.55
09.00
20
14
07.50
Du.
hill
58
15
16.4
5
16
00.20
07.35
23
S(19)
+I(4)
14.30
42
31
20.20
14.45
Purpose
? Estimation of demurrage
hours of demurrage
Control
hours
Important reasons cited are receipt in quick succession, successive
detentions and wet coal. These are beyond the control of the coal
handling section.
Inadequate
Quality
Data!with Statistics
40
Chapter 3:
Summarization of
Data
Hours
(MW)
10.00
13.30
14.00
17.30
18.00
21.30
22.00
01.30
02.00
05.30
06.00
09.30
10.00
13.30
14.00
17.30
Generation
102.8 105.2 103.2 104.0
105.0 105.0 104.0 104.0
103.2 104.2 102.0 103.6
105.2 106.0 105.0 103.0
104.2 105.8 105.4 104.8
106.0 104.0 104.2 103.8
103.4 104.4 104.4 104.2
104.8 102.8 103.6 104.8
104.0 104.0 104.0 104.0
103.0 104.8 102.8 104.0
104.0 103.4 106.0 104.4
What
are105.2
your
105.0
105.2
conclusions?
Quality with
105.2
105.2
103.8
103.2
104.8
104.4
104.8
104.4
104.4
103.4
104.4
Statistics
104.8
106.0
105.0
103.0
105.2
104.0
106.2
104.8
104.0
103.6
102.4
105.6
106.4
105.2
103.0
105.2
102.2
106.4
104.0
102.6
104.0
102.8
42
Frequency Distribution
- Analyzing a large data set on the same
variable
Generation data set (previous
The eighty observations
are grouped in eight classes of
slide)
equal length
Class Interval
Tally
Frequency
101.7 102.3
02
102.3 102.9
06
102.9 103.5
10
103.5 104.1
19
104.1 104.7
11
104.7 105.3
22
105.3 105.9
03
105.9 106.5
07
Total
80
43
Constructing Frequency
Distributions
- Variable Data
Data set
44
Constructing Frequency
Distributions (..contd.)
45
Constructing Frequency
Distributions (..Contd.)
Class limits
The minimum value of the generation data is 102.0 and the class
width has been determined as 0.6. So we can form the classes as
102.0 102.6, 102.7 103.3, 103.4 103.9, . . .
46
Constructing Frequency
Distributions (..Contd.)
47
Constructing Frequency
Distributions (..Contd.)
Tally marking (second column)
Start with the first observation. Find the class to which the observation
belongs. Put a tally against the class.
Classify all the remaining observations as above.
Tally marks are grouped in five, with the fifth tally crossed through the
previous four tallies. This provides a better visual display and helps in
counting the frequency of each class.
Note that all the above observations get classified as we go through
the observations only once. However, if we concentrate on a class and
then try to find out the number of observations in the class then we
have to go through the observations k times. This not only consumes
more time but also increases the chance of committing error.
Other columns
48
Constructing Frequency
Distributions
- Getting the class intervals right
Consider the same generation data example. Here w=0.2. Assume that
h = 0.657 is rounded to 0.7 (which is not an integer multiple of 0.2)
instead of 0.6. Thus the classes will be 101.9 102.6, 102.6 103.3, ..
Note that the number of observation units covered by each class are
not same. For example, the second class covers three units (102.8,
103.0 and 103.2) but the third class covers four units (103.4, 103.6,
103.8 and 104.0). As a result the frequency distribution is likely to
show many peaks.
49
!!
a
at
D
y
s
i
No
Class interval
Frequency
101.7 102.7
04
27
102.7 103.7
17
18
103.7 104.7
26
104.7 105.7
25
105.7 106.7
08
Total
80
15
5
15
Total
80
0s occur more frequently
at the cost of 6s. Does this
indicate
measurement
bias?
Quality
Histogram
Histogram is a graphical representation of a frequency distribution of
variable data.
The histogram of the generation data having five classes is shown below.
Frequenc
y
30
25
20
15
10
5
0
101.7
103.7
Pattern of variation: Slightly left
105.7
skewed
Generation in E station
(MW)
Specification limits: Should be shown wherever applicable.
Class mid-point: Marking the class mid-points may be helpful in
certain cases.
Open ended classes: Avoid adding too many classes at the ends
having zero or
Quality
withasStatistics
51
very
low
frequencies.
Shown
open
ended
bars
with
arbitrarily
reduced heights.
Construction of Histogram
- An exercise
Half-hourly record of power (MW) generated by station E during
29.9.2001
(10.00 hours) to 30.9.2001 (24.00 hours) gives us the following
data.29/9
6.4 6.4 6.8 6.0 5.2 4.8 6.4 4.4 5.2
(10 hrs.) 6.0
7.6 8.0 7.4 6.6 8.0 5.6 7.2 7.2 7.0
4.0
6.4 8.0 8.0 6.0 6.0 6.4 7.8 7.6 7.6
7.4
7.6 7.6 7.4 4.6 4.2 4.8 6.0 5.6 5.4
5.0
6.2 7.8 7.4 7.2 7.4 7.8 6.6 6.4 6.8
6.8
30/9
6.8 6.8 6.6 6.8 6.6 6.8 6.8 6.8 7.0
(24
hrs.)
7.0
Construct a histogram of the above data set. Compare with the
histogram 6.0 5.6 4.4 4.6 4.6 4.8 6.2 7.0 6.6
for the period
6.4
19.9.01
to 21.9.01
( previous slide) and offer your
Quality
with Statistics
52
comments.
Commonly Observed
Histogram Patterns
How
?
Single
positively
(long tail
right)
peak,
skewed
on the
Single
peak,
negatively skewed
(Long tail on the
left)
Many
characteristics
follow such patterns. We
have already seen that
generation
data
is
negatively skewed while
breakdown
data
is
Two peaks (bipositively
skewed.
modal)
?
w
However
such
shapes
Ho
may also indicate process
Quality with Statistics instability.
53
Frequency
Distribution of
Discrete
Data
Number of plant outages in each year since
commissioning
Statio
Period
Type of
n
outage
D
197879
To
200001
198586
To
200001
Forced
# of outages in a year
2, 3, 1, 0, 3, 2, 1, 0, 2, 2, 0, 2, 3, 0, 2, 1,
2, 1, 1, 0, 1, 0, 2
Planned 3, 5, 1, 4, 2, 5, 2, 1, 6, 3, 7, 7, 4, 7, 6, 5,
6, 4, 2, 2, 2, 6, 2
Forced
2, 2, 5, 3, 0, 0, 1, 0, 1, 0, 2, 1, 1, 0, 1, 4
Planned 15, 7, 8, 3, 7, 5, 2, 6, 3, 8, 7, 4, 5, 4, 3, 4
F
19881, frequency
1, 0, 0, 1, 1,
2, 0, 1, 0, 1,(for
6 each type
Ideally
we
should Forced
construct4,six
distributions
89
Planned However,
3, 11, 6, 12,
1, 2, 8, 2,of4,data
4, 6 we shall
of outage inTo
each station).
due4,to0,shortage
construct only
2000-two - one for forced outage and the other for planned
outage.
01
What can you say about the occurrence of two types of
Quality
with
Statistics
54
outages from the above
data
set?
1
6
1
2
8
Frequenc
y
Frequenc
y
1
6
1
2
8
Number of
outages
0 1 2
11,12,15
3 4
Number of
outages
8 9
55
Mean
May be used for ordinal data but not for nominal data
Sensitive to extreme values
Ordinal data: Category containing the (N+1)/2 case
Media
n
Mod
e
56
Interpretation of Mean
In a rising voltage test the alternating breakdown
voltage(kV) of 24 samples of an insulation arrangement were
found to be as follows:
210; 208; 208; 175; 182; 206; 190; 194; 198; 205; 212; 200;
205;
Dot
MEAN
=
[210
+
208
+
+
216
+
196]
/
202; 207; 210; 202; 201; 188; 205; 209; 201; 216; 196
Plo
24
t
= 201.25 kV
170
180
190
210
220
Mea
n for the distribution of the
Mean is the balance point (or fulcrum)
values
Jan
Feb
Mar
Oct
Nov
Dec
Total
1995
24
17
27
19
10
25
19
22
23
16
18
15
235
1996
22
10
22
18
16
21
21
20
21
18
18
18
225
1997
19
14
12
15
15
15
24
19
16
14
19
192
1998
14
14
12
20
19
23
10
16
13
15
17
19
192
1999
19
13
15
13
16
18
17
16
20
17
13
16
193
2000
12
14
15
22
12
13
13
134
Total
110
82
103
108
88
100
88
111
103
91
87
100
1171
58