CHAPTER 11

Statistical Quality Control

The most important word in the term “Statistical Quality Control” is quality. By
quality we mean an attribute of the product that determines it’s fitness for use.

Quality here means a level/standard, which, in tern, depends on four M’s besides
many other factors – Materials, Manpower, Machines and Management.
Quality control is a powerful productivity technique for effective diagnosis of lack of
quality (or conformity to settled standards) in any of the materials, processes,
machines or end products. It is essential that the end products possess the qualities
that the consumer expects of them, for the progress of industry depends on the
successful marketing of products. Quality control ensures this by insisting on quality
specifications all along the line from the arrival of materials through each of their
processing to the final delivery of goods.

Chance and assignable causes: Variation in the quality of manufactured product

in the repetitive process in industry is inherent and inevitable. These variations are
broadly classified as being due to two causes viz., i) Chance causes, and ii)
Assignable causes.

Statistical Quality Control (SQC) means planned and effective use of data for
studying causes of variations in quality either as between process, procedures,
materials, machines, etc., or over period of time.
The main purpose of Statistical Quality Control is to devise statistical techniques,
which would help us in separating the assignable causes from the chance causes,
thus enabling us to take intermediate remedial action whenever assignable causes
are present. A production process is said to be in a state of statistical control, if it
governed by chance causes alone, in the absence of assignable causes of variation.

Use of SQC:
1. The act of getting a process in statistical control involves the identification and
elimination of assignable causes of variation and possibly the inclusion of good
ones.
 121

2. It tells us when to leave a process alone and when to take action to correct
troubles, thus preventing frequent and unwarranted adjustments.
3. If testing is destructive a process in control gives confidence in the quality of
untested product, which is not the case otherwise.
4. It provides better quality assurance at lower cost.
5. SQC reduce waste of time and material to the absolute minimum by giving an
early warning about the occurrence of defects.

Process and Product Control:

The main objective in any production process is to control and maintain the quality
of the manufactured product so that it confirms to specified quality standards. In
other words, we want to ensure that the proportion of defective items in the
manufactured product is not too large. This is called ‘process control’ and achieved
through the technique of control charts pioneered by W. A. Shewhart.
On the other hand, by product control we mean controlling the quality of the
product by critical examination at strategic points and this is achieved through
‘Sampling inspection plans’ pioneered by Dodge and Roming. Product control aims
at guaranteeing a certain quality level to the consumer regardless of what quality
level being maintained by the producer. In other words, it attempts to ensure that
the product marketed by sales department does not contain a large number of
defective items.

Control Charts:
A typical control chart consists of the following three horizontal lines:
i) A central line (CL) to indicate the desired standard or the level of process.
ii) Upper Control Limit (UCL), and
iii) Lower Control Limit (LCL).

Control Charts for Variables:

These charts may be applied to any quality characteristic that is measurable.
a) and R Charts:

Steps for and R Charts:

i) Selection of samples or sub-groups
ii) Collection of and R for each sub-group
iii) Setting of control limits

Chapter 11
Statistical Quality Control
 122

iv) Construction of control chart for and R

v) Remarks on and R Charts
Control Limits for Chart:
Case – 1: When standards are given i.e., both µ and  are known. The 3-s control
limits are given by

Case – 2: When standards are not given i.e., both µ and  are unknown. The 3-s
control limits are given by

Control Limits for R Charts:

[ ]

Exercise:
1. Construct control charts for mean and the range for the following data on the basis of
fuses, samples of 5 being taken every hour. Comment on whether the production seems to
be under control.
42 42 19 36 42 51 60 18 15 69 64 61
65 45 24 54 51 74 60 20 30 109 90 78
75 68 80 69 57 75 72 27 39 113 93 94
78 72 81 77 59 78 95 42 62 118 109 109
87 90 81 84 78 132 138 60 84 153 112 136

Solution:
Sample Sample Sample
No. Total Average Range
1 42 65 75 78 87 347 69.4 45
2 42 45 68 72 90 317 63.4 48
3 19 24 80 81 81 285 57 62
4 36 54 69 77 84 320 64 48
5 42 51 57 59 78 287 57.4 36

Chapter 11
Statistical Quality Control
 123

6 51 74 75 78 132 410 82 81
7 60 60 72 95 138 425 85 78
8 18 20 27 42 60 167 33.4 42
9 15 30 39 62 84 230 46 69
10 69 109 113 118 153 562 112.4 84
11 64 90 93 109 112 468 93.6 48
12 61 78 94 109 136 478 95.6 75
Total 4296 859.2 716
Averag 71.6 59.67
e
Here = 859.2 ÷ 12 = 71.6 and = 716 ÷ 12 = 59.67
From the tables, for n = 5, we have A2 = 0.58 and D3 = 0 and D4 = 2.11
For Chart:
CL = = 71.60, UCL = + =71.6 + 0.58 × 59.67 = 106.21

LCL = - = 36.99
For R Chart:
CL = = 59.67, LCL = D3 = 0, UCL = D4 = 2.11 × 59.67 = 125.9

Chapter 11
Statistical Quality Control
 124

2. Track Bicycle Parts manufacturer precision ball bearings for wheel hubs, bottom
brackets, head sets, and pedals. Seth Adams is responsible for quality control at Track.
He has been checking the output of the 5-mm bearings used in front wheel hubs. For each
of the last 18 hours, he has sampled 5 bearings, with the following results:
Hou
r a) Construct control charts for mean
5.03 5.0 4.8 4.90 4.95 and the range to help Seth
1 6 6
4.97 4.9 5.0 4.78 4.88 determine whether the production
2 4 9 of 5-mm bearings is in control.
5.02 4.9 4.9 4.95 4.80
3 8 4 b) Should Seth conclude that the
4.92 4.9 4.9 4.92 4.96
4 3 0
process is in control?
5 5.01 4.9 4.9 5.06 5.01

Chapter 11
Statistical Quality Control
 125

9 3
5.00 4.9 5.1
6 5 0 4.85 4.91
4.94 4.9 5.0
7 1 5 5.07 4.88
5.00 4.9 5.0
8 8 5 4.96 4.97
4.99 5.0 4.9
9 1 3 5.10 4.98
5.03 4.9 4.9
10 6 2 5.01 4.93
5.02 4.8 5.0
11 8 0 4.98 5.09
5.09 5.0 5.1
12 1 3 4.89 5.02
4.90 4.9 4.9
13 3 7 4.98 5.12
5.04 4.9 5.1
14 6 5 5.04 5.02
5.09 4.9 5.0
15 0 4 5.19 5.03
5.10 5.0 5.0
16 1 4 5.05 5.02
4.97 5.1 5.1
17 0 3 4.92 5.04
5.01 4.9 5.0
18 9 6 5.04 5.12

Solution:
Sample
Ho Averag Sample
ur Total e Range

Chapter 11
Statistical Quality Control
 126

1 5.03 5.06 4.86 4.90 4.95 24.80 4.96 0.20

2 4.97 4.94 5.09 4.78 4.88 24.66 4.93 0.31
3 5.02 4.98 4.94 4.95 4.80 24.69 4.94 0.22
4 4.92 4.93 4.90 4.92 4.96 24.63 4.93 0.06
5 5.01 4.99 4.93 5.06 5.01 25.00 5.00 0.13
6 5.00 4.95 5.10 4.85 4.91 24.81 4.96 0.25
7 4.94 4.91 5.05 5.07 4.88 24.85 4.97 0.19
8 5.00 4.98 5.05 4.96 4.97 24.96 4.99 0.09
9 4.99 5.01 4.93 5.10 4.98 25.01 5.00 0.17
10 5.03 4.96 4.92 5.01 4.93 24.85 4.97 0.11
11 5.02 4.88 5.00 4.98 5.09 24.97 4.99 0.21
12 5.09 5.01 5.13 4.89 5.02 25.14 5.03 0.24
13 4.90 4.93 4.97 4.98 5.12 24.90 4.98 0.22
14 5.04 4.96 5.15 5.04 5.02 25.21 5.04 0.19
15 5.09 4.90 5.04 5.19 5.03 25.25 5.05 0.29
16 5.10 5.01 5.04 5.05 5.02 25.22 5.04 0.09
17 4.97 5.10 5.13 4.92 5.04 25.16 5.03 0.21
18 5.01 4.99 5.06 5.04 5.12 25.22 5.04 0.13
Total 449.33 89.87 3.31
Average 4.99 0.18

Here = 89.87 ÷ 18 = 4.99 and = 3.31 ÷ 1 = 0.18

From the tables, for n = 5, we have A2 = 0.58 and D3 = 0 and D4 = 2.11
For Chart:
CL = =4.99, UCL = + =4.99 + 0.58 × 0.18 = 5.0944

LCL = - = 4.8856
For R Chart:
CL = = 0.18, LCL = D3 = 0, UCL = D4 = 2.11 × 0.18 = 0.3798

Chapter 11
Statistical Quality Control
 127

Chapter 11
Statistical Quality Control
 128

Control Charts for Attributes:

There are two control charts for attributes:
i) Control chart for fraction defective (p-chart) or the number of defectives
(np or d chart).
ii) Control chart for number of defects per unit (c chart).

Control Limits for p- Chart:

Case – 1: When Standards are given:

Case – 2: When Standards are not given:

Where

Control Limits for d- Chart:

Case – 1: When Standards are given:

Case – 1: When Standards are not given:

Exercise:
1. The following are the figures of defectives in 22 lots each containing 2,000
rubber belts:
425, 430, 216, 341, 225, 322, 280, 306, 337, 305, 356,
402, 216, 264, 126, 409, 193, 326, 280, 389, 451, 420
Draw a control chart for fraction defective and comment on the state of
control of the process.

Solution:

Chapter 11
Statistical Quality Control
 129

p=
No. of No. of
Sample defectiv d÷ Sample defectiv p=
No. es 2000 No. es d ÷ 2000
1 425 0.2125 12 402 0.2010
2 430 0.2150 13 216 0.1080
3 216 0.1080 14 264 0.1320
4 341 0.1705 15 126 0.0630
5 225 0.1125 16 409 0.2050
6 322 0.1610 17 193 0.0970
7 280 0.1400 18 326 0.1630
8 306 0.1530 19 280 0.1400
9 337 0.1685 20 389 0.1950
10 305 0.1525 21 451 0.2260
11 356 0.1780 22 420 0.2100
Total = 3.5095
Average = 0.1595

Here

p = 0.1595, So 1 - p = 0.8505
UCL = 0.1841, CL = 0.1595, and LCL = 0.1349

Chapter 11
Statistical Quality Control
 130

2. Todd Olmstead is the Meals – on –wheels dispatcher of the Atlanta metropolitan area. He
wants meals delivered to clients within 30 minutes of living the kitchens. Meals with
longer delivery times tend to be too cold when they arrive. Each of his 10 volunteer
drivers is responsible for delivering 15 meals daily. Over the past month, Todd has
recorded the percentage of each day’s 150 meals that were delivered on-time:
Day 1 2 3 4 5 6 7 8
% on-time 89.33 81.33 95.33 88.67 96.00 86.68 98.00 84.00
Day 9 10 11 12 13 14 15 16
% on-time 90.67 80.67 88.00 86.67 96.67 85.33 78.67 89.33
Day 17 18 19 20 21 22 23 24
% on-time 89.33 78.67 94.00 94.00 99.33 95.33 94.67 92.67
Day 25 26 27 28 29 30
% on-time 81.33 89.33 99.33 90.67 92.00 88.00

a) Help Todd construct a p chart from these data.

b) How does your chart show that the attribute “fraction of meals delivered on-
time” is out of control?
Solution:
Day % on-time Proportion Day % on-time Proportion
1 89.33 0.8933 17 89.33 0.8933
2 81.33 0.8133 18 78.67 0.7867
3 95.33 0.9533 19 94.00 0.9400
4 88.67 0.8867 20 94.00 0.9400
5 96.00 0.9600 21 99.33 0.9933
6 86.67 0.8667 22 95.33 0.9533
7 98.00 0.9800 23 94.67 0.9467
8 84.00 0.8400 24 92.67 0.9267
9 90.67 0.9067 25 81.33 0.8133
10 80.67 0.8067 26 89.33 0.8933
11 88.00 0.8800 27 99.33 0.9933
12 86.67 0.8667 28 90.67 0.9067
13 96.67 0.9667 29 92.00 0.9200
14 85.33 0.8533 30 88.00 0.8800
15 78.67 0.7867 Total = 26.9400
16 89.33 0.8933
Here p = (26.94 ÷30) = 0.8980, So 1 - p = 0.1020

UCL = 0.9721, CL = 0.8980, LCL = 0.8239, = 0.2449

Chapter 11
Statistical Quality Control