Higher Engineering Mathematics

(Greg DeLong) #1
LINEAR CORRELATION 569

J

LetXbe the expenditure in thousands of pounds and
Ybe the days lost.


The coefficient of correlation,


r=


xy
√{(∑
x^2

)(∑
y^2

)}

wherex=(X−X) andy=(Y−Y),XandYbeing
the mean values ofXandYrespectively. Using a
tabular approach:


X Y x=(X−X) y=(Y−Y)

3.5 241 −6.57 69.9
5.0 318 −5.07 146.9
7.0 174 −3.07 2.9
10 110 −0.07 −61.1
12 147 1.93 −24.1
15 122 4.93 −49.1
18 86 7.93 −85.1


X= 70 .5, X=

70. 5
7

= 10. 07


Y=1198, Y=

1198
7

= 171. 1

xy x^2 y^2

−459.2 43.2 4886
−744.8 25.7 21580
−8.9 9.4 8
4.3 0 3733
−46.5 3.7 581
−242.1 24.3 2411
−674.8 62.9 7242

xy=− 2172


x^2 = 169. 2


y^2 = 40441

Thus


r=

− 2172

[169. 2 ×40441]

=− 0. 830

This shows that there isfairly good inverse corre-
lationbetween the expenditure on welfare and days
lost due to absenteeism.


Problem 3. The relationship between monthly
car sales and income from the sale of petrol for
a garage is as shown:

Cars sold 2 5 3 12 14 7 3 28 14 7 3 13
Income from
petrol sales
(£′000) 12 9 13 21 17 22 31 47 17 10 9 11

Determine the linear coefficient of correlation
between these quantities.

LetXrepresent the number of cars sold andYthe
income, in thousands of pounds, from petrol sales.
Using the tabular approach:

X Y x=(X−X) y=(Y−Y)

2 12 −7.25 −6.25
5 9 −4.25 −9.25
3 13 −6.25 −5.25
12 21 2.75 2.75
14 17 4.75 −1.25
7 22 −2.25 3.75
3 31 −6.25 12.75
28 47 18.75 28.75
14 17 4.75 −1.25
7 10 −2.25 −8.25
3 9 −6.25 −9.25
13 11 3.75 −7.25


X=111, X=

111
12

= 9. 25


Y=219, Y=

219
12

= 18. 25

xy x^2 y^2

45.3 52.6 39.1
39.3 18.1 85.6
32.8 39.1 27.6
7.6 7.6 7.6
−5.9 22.6 1.6
−8.4 5.1 14.1
−79.7 39.1 162.6
539.1 351.6 826.6
−5.9 22.6 1.6
18.6 5.1 68.1
57.8 39.1 85.6
−27.2 14.1 52.6

xy= 613. 4


x^2 = 616. 7


y^2 = 1372. 7
Free download pdf