II Semester B.

COM
Subject:
Quantitative Techniques for Business Analysis
Module – I
CORRELATION ANALYSIS
BY
[Link] G Angadi
Surana college(Autonomous)
 Module – I
CORRELATION ANALYSIS
Meaning
It refers to the technique used in measuring the closeness of degree of the
relationship between the quantitative variables. It is sometimes termed as “co-
variation”. The measure of correlation is called co-efficient of correlation.

Definition
According to A.M. Tuttle” An analysis of the relationship of two or more variable is
usually called correlation”.

According to Croxton and Cowden “ When the relationship is of a quantitative

nature, the appropriate statistical tool for discovering and measuring the relationship
and expressing it in a brief formula is known as Correlation”
Significance

[Link] helps in measuring the degree of relationship between two

quantitative variables
[Link] can be used to estimate the value of an unknown variable
with given value of another variable
[Link] helps in locating the critically important variables on which
others depend.
[Link] helps in the exact prediction.
 Types of correlation

Positive or Direct correlation

If values of variables are increasing or decreasing in the same direction, then such
correlation is referred to as Positive correlation
Negative or Inverse correlation
It refers to the change in the values of variables in opposite direction or
Correlation is said to be negative if an increase in the value of one variable is
accompanied by decrease in the value of another variable and vice-versa.
Linear Correlation
A correlation is referred to as linear correlation when the amount of change in one
variable tends to bear constant ratio to the change in the other variable.
Non-Linear correlation
A correlation is referred to as a non-linear correlation when the amount of
change in the values of one variable does not bear a constant ratio of the amount
of change in the other variable.
Simple correlation
If only two variables are chosen to study correlation between them, then such a
correlation is referred to a simple correlation.
Partial Correlation
If two variables are chosen to study the correlation between them but the effect
or other variable is kept constant, then such a correlation is referred to as partial
correlation.
Multiple correlations
If the relationship between more than three variables is considered
simultaneously for study, then such a correlation is referred to as multiple
correlations.
Uses

[Link] helps in measuring the relationship between the variables.

[Link] helps in analyzing the economic behavior such as salary and
inflation, price and demand etc.,
[Link] facilitates comparison and is a relative measure.
[Link] effect of correlation is to reduce the uncertainty in
prediction.
[Link] prediction based on correlation analysis will be more
reliable.
Method of Correlation:
[Link] diagram method.
[Link] Pearson’s coefficient of correlation
[Link] correlation
.
 Karl Pearson’s coefficient of Correlation

When Actual Mean method

∑𝐱𝐲
r= , where x = X – 𝑿, y = Y - Y
∑𝒙𝟐 ∑𝒚𝟐

When Assumed Mean method

𝑵𝜮𝒅𝒙𝒅𝒚− 𝜮𝒅𝒙 (𝜮𝒅𝒚)
r=
[𝒏𝜮𝒅𝒙𝟐 −(𝜮𝒅𝒙)𝟐 ][𝒏𝜮𝒅𝒚𝟐 −(𝜮𝒅𝒚)𝟐 ]
Assumptions
[Link] Pearson's correlation co-efficient is appropriate to calculate
when both variable x and y are measured on ratio scale.
[Link] exists a linear relationship between the variables
[Link] the variables are normally distributed.
[Link] is a cause and effect relationship between the forces
affecting the distribution.
Merits:
[Link] gives direction as well as degree of relationship
between the variables.
[Link] helps in estimating the value of the dependent variable
from the known value of independent variables if used
along with other information.
[Link] ranges from -1 and +1.
Limitations
[Link] assumption of linear relationship between the variables
may or may not always hold true.
[Link] requires more time to calculate the values of ‘r’ as
compared to other methods.
[Link] is affected by the extreme values of two variables.
[Link] requires careful interpretation as very often its value is
misinterpreted.
Interpretation of ‘r” Karl Pearson’s coefficient of correlation
[Link] r = +1 then, there exists Perfect positive correlation between
variables.
[Link] r = -1 then, there exists Perfect negative correlation between
variables
[Link] r = 0 then, there is no relationship between variables
[Link] r > 0.75 and < 0.99, then, there is high degree of
correlation.
[Link] r>0.25 and < 0.75 then, there is moderately correlation.
[Link] r < 0.25 then, there is low degree of relationship.
Probable Error
According to Horace Secrist “ the probable error of the correlation coefficient is
amount which if added to and subtracted from the average correlation coefficient,
produces amount within which the chances are even that a coefficient of correlation
from a series selected at random will fall.
Meaning
the probable error of coefficient of correlation is an amount which if added to and
subtracted from the values given two limits within which coefficient of correlation
obtained will fall, it is 0.6745 times of the standard error of r and it is computed as
1−𝒓𝟐 , 1−𝒓𝟐
Standard Error(SE) = 𝑛 Probable Error (PE) = 0.6745 𝑛

where r = coefficient of correlation, n= number of pairs of observation

Interpretation of probable error:
1. If r < 6 PE, then ‘r ‘ is not significant
2. If r > 6 PE, then, ‘r ‘ is significant
Uses of probable error:
[Link] is used to determine the limits within which the population
correlation coefficient may be expected to lie.
[Link] may be used to test whether sample correlation is significant
or not.
 Problems
1. Find the correlation coefficient under the Karl Pearson’s Method. and also find Probable Error.
X 10 20 30 40 50
Y 100 90 80 70 60 ∑X ∑Y
Mean( 𝑋 )= Mean(𝑌)=
𝑛 𝑛
Solution 𝑋=
150
𝑦=
400
5 5
𝑋 = 30 𝑦 = 80
Karl Pearson’s coefficient of Correlation
∑𝒙𝒚
r= , where x = X –𝑋, y = Y - 𝑦
∑𝒙𝟐 ∑𝒚𝟐

∑𝒙𝟐 = 1000 ∑𝒚𝟐 = 1000 ∑xy = -1000

−𝟏𝟎𝟎𝟎
r=
𝟏𝟎𝟎𝟎 𝐱 𝟏𝟎𝟎𝟎
−𝟏𝟎𝟎𝟎
r=
𝟏𝟎𝟎𝟎
r=-1
Conclusion:
The correlation between x and y is perfectly negative correlation
 1−𝒓𝟐
Probable Error (PE) = 0.6745( ), r = -1
𝒏
1− −𝟏 𝟐
Probable Error (PE) = 0.6745( )
𝟓
1−𝟏 = > -1 < 0
Probable Error (PE) = 0.6745( )
𝟓
Therefore,
Probable Error (PE) = 0.6745 (0)
Probable Error (PE) = 0 ‘r ‘ is not significant
Interpretation of probable error:
6PE = 6(0) = 0 and r = -1

Now, r < 6 PE
2. Find the coefficient of correlation between the following two variables and also find
Probable Error.
X 6 8 12 15 18 20 24 28 31
Y 10 12 15 15 18 25 22 26 28

Solution
 ∑X
Mean( 𝑋 )=
𝑛
Solution 162
𝑋=
9
𝑋 = 18
∑Y
Mean(𝑌)=
𝑛
171
𝑦=
9
𝑦 = 19
Karl Pearson’s coefficient of Correlation
∑𝒙𝒚
r= , where x = X –𝑋, y = Y - 𝑦
∑𝒙𝟐 ∑𝒚𝟐

∑𝒙𝟐 = 598 ∑𝒚𝟐 = 338 ∑xy = 431

𝟒𝟑𝟏
r=
𝟓𝟗𝟖 𝐱 𝟑𝟑𝟖
𝟒𝟑𝟏
r=
𝟐𝟎𝟐𝟏𝟐𝟒
𝟒𝟑𝟏
r=
𝟒𝟒𝟗.𝟓𝟖
r = 0.958
Conclusion:
The correlation between x and y is high degree positive correlation
 1−𝒓𝟐
Probable Error (PE) = 0.6745( ), r = 0.958
𝒏
)𝟐
1−(0.958
Probable Error (PE) = 0.6745( )
𝟗
1−𝟎.𝟗𝟏𝟕
Probable Error (PE) = 0.6745( ) r = 0.958
𝟗
0.083
Probable Error (PE) = 0.6745 ( ) Now, r > 6 PE
𝟑
Probable Error (PE) = 0.6745(0.0276)
= > 0.958 > 0.108
Probable Error (PE) = 0.018
Interpretation of probable error: Therefore,
6PE = 6(0.018)
‘r ‘ is significant
3. The following data relates to Percentage of Failures in examination find the
correlation coefficient. Also find Probable Error.
Age(year) 13 14 15 16 17 18 19 20 21
Percentage of Failures 39 40 43 34 36 39 48 47 52
Solution ∑X
Let us assume that X be the Age and Y be the Percentage of failures Mean(𝑋)=
𝑛
153
𝑋=
9
𝑋 = 17
∑Y
Mean(𝑌) =
𝑛
378
𝑦=
9
𝑦 = 42
Karl Pearson’s coefficient of Correlation
∑𝒙𝒚
r= , where x = X –𝑋, y = Y - 𝑦
∑𝒙𝟐 ∑𝒚𝟐

∑𝒙𝟐 = 60 ∑𝒚𝟐 = 284 ∑xy = 88

𝟖𝟖
r=
𝟔𝟎 𝐱 𝟐𝟖𝟒
𝟖𝟖
r=
𝟏𝟕𝟎𝟒𝟎
𝟖𝟖
r=
𝟏𝟑𝟎.𝟓𝟑𝟕𝟑
r = 0.67413 Conclusion:
The correlation between Age and Percentage of
Failures is moderately positive correlation
 1−𝒓𝟐
Probable Error (PE) = 0.6745( ), r = 0.67413
𝒏
1−(𝟎.𝟔𝟕𝟒𝟏𝟑)𝟐
Probable Error (PE) = 0.6745
𝟗
1−𝟎.𝟒𝟓𝟒𝟒𝟓
Probable Error (PE) = 0.6745( )
𝟗
0.54554 r = 0.67413
Probable Error (PE) = 0.6745 ( )
𝟑 Now, r < 6 PE
Probable Error (PE) = 0.6745(0.18184)
Probable Error (PE) = 0.12265 => 0.67413 < 0.73594
Interpretation of probable error:
Therefore,
6PE = 6(0.12265)
6PE = 0.73594 and ‘r ‘ is not significant
4. Compute Karl Pearson’s coefficient of correlation between per capita income
and per capita expenditure and also find Probable Error.
Per captia income 43 44 46 40 44 42 45 42 40 42 57 48
Per capita Expenditure 29 31 19 18 19 27 27 29 41 30 26 10

∑X ∑Y
Mean(𝑋)= Mean(𝑌) =
𝑛 𝑛
533 306
𝑋= 𝑦=
12 12
𝑋 = 44.416 𝑦 = 25.5
Solution 𝑋 = 44.416 𝑦 = 25.5
Let us assume that X be the Per capita Income and Y be the Per capita Expenditure

𝑨 𝑩
Karl Pearson’s coefficient of Correlation
𝑵𝜮𝒅𝒙𝒅𝒚− 𝜮𝒅𝒙 (𝜮𝒅𝒚)
r= , Where dx = X –𝐴, dy = Y- 𝐵,
[𝒏𝜮𝒅𝒙𝟐 −(𝜮𝒅𝒙)𝟐 ][𝒏𝜮𝒅𝒚𝟐 −(𝜮𝒅𝒚)𝟐 ]

Where A and B are assumed means of X and Y

∑dx = 29 ∑𝒅𝒙𝟐 = 303 ∑dy =-18 ∑𝒅𝒚𝟐 = 728 ∑(𝒅𝒙)(dy) = -165

𝟏𝟐 −𝟏𝟔𝟓 −(𝟐𝟗)(−𝟏𝟖)
r=
𝟏𝟐 𝟑𝟎𝟑 − 𝟐𝟗 𝟐 [𝟏𝟐 𝟕𝟐𝟖 − −𝟏𝟖 𝟐 ]
−𝟏,𝟗𝟖𝟎+𝟓𝟐𝟐
r=
𝟑,𝟔𝟑𝟔−𝟖𝟒𝟏 [𝟖,𝟕𝟑𝟔−𝟑𝟐𝟒]
 −𝟏,𝟒𝟓𝟖
r=
𝟐,𝟕𝟗𝟓 [𝟖,𝟒𝟏𝟐]
−𝟏𝟒𝟓𝟖
r=
𝟐,𝟑𝟓,𝟏𝟏,𝟓𝟒𝟎

−𝟏𝟒𝟓𝟖
r=
𝟒,𝟖𝟒𝟖.𝟖𝟔𝟗𝟗𝟕

r = - 𝟎. 𝟑𝟎𝟎𝟔𝟖𝟖𝟔
Conclusion:
The correlation between per Capita Income and per Captia
Expenditure is moderately negative correlation
 1−𝒓𝟐
Probable Error (PE) = 0.6745( ), r = -0.3006
𝒏
1− −𝟎.𝟑𝟎𝟎𝟔 𝟐
Probable Error (PE) = 0.6745( )
𝟏𝟐
1−𝟎.𝟎𝟗𝟎𝟑𝟔𝟎𝟑𝟔
Probable Error (PE) = 0.6745( )
𝟏𝟐
0.909639 r = -0.3006
Probable Error (PE) = 0.6745 ( )
𝟑.𝟒𝟔𝟒𝟏𝟎𝟏
Probable Error (PE) = 0.6745(0.2625903) Now, r < 6 PE
Probable Error (PE) = 0.177117 =>-0.3006< 1.0627
Interpretation of probable error:
6PE = 6(0.177117)
Therefore,
6PE = 1.0627033 and ‘r ‘ is not significant
5. From the following data find the correlation, probable error and comment on the
result. Marks in Statistics 25 43 27 35 54 61 37 45
Marks in Mathematics 35 47 20 37 63 54 28 40
Solution

Let us assume that X be the marks in Statistics and Y be the Marks in Mathematics

∑X ∑Y
Mean(𝑋)= Mean(𝑌) =
𝑛 𝑛

327 324
𝑋= 𝑦=
8 8
𝑋 = 40.875 𝑦 = 40.5
5. From the following data find the correlation, probable error and comment on the
result. Marks in statistics 25 43 27 35 54 61 37 45
Marks in Mathematics 35 47 20 37 63 54 28 40
Solution 𝑋 = 40.875 𝑦 = 40.5
Let us assume that X be the Age and Y be the Percentage of failures
x dx = X - 𝑨 𝒅𝒙𝟐 Y dy = Y - 𝑩 𝒅𝒚𝟐 (𝒅𝒙)(dy)
25 25-35 = -10 100 35 35-37 = - 2 4 (-10) x(-2) = 20
43 43-35 = 8 64 47 47-37 = 10 100 8 x 10 = 80
27 27-35 = -8 64 20 20-37 = -17 289 (-8) x (-17) = 136
35 𝑨 35-35 = 0 0 37 𝑩 37-37 = 0 0 0x0 = 0
54 54-35 = 19 361 63 63-37 = 26 676 19 x 26 = 494
61 61-35 = 26 676 54 54-37 = 17 289 26 x 17 = 442
37 37-35 = 2 4 28 28-37 = -9 81 2 x (-9) = - 18
45 45-35 = 10 100 40 40-37 = 3 9 10 x 3 = 30
∑X=327 ∑dx = 47 ∑𝒅𝒙𝟐 = 1369 ∑Y= 324 ∑dy = 28 ∑d𝒚𝟐 = 1448 ∑dxdy = 1184
Karl Pearson’s coefficient of Correlation
𝑵𝜮𝒅𝒙𝒅𝒚− 𝜮𝒅𝒙 (𝜮𝒅𝒚)
r= ,
[𝒏𝜮𝒅𝒙𝟐 −(𝜮𝒅𝒙)𝟐 ][𝒏𝜮𝒅𝒚𝟐 −(𝜮𝒅𝒚)𝟐 ]

Where dx = X –𝐴, y = Y- 𝐵 and A & B are assumed means of X & Y

∑dx = 47 ∑𝒅𝒙𝟐 = 1369 ∑dy = 28 ∑𝒅𝒚𝟐 = 1448 ∑(𝒅𝒙)(dy) = 1184
𝟖 𝟏𝟏𝟖𝟒 −(𝟒𝟕)(𝟐𝟖)
r=
𝟖 𝟏𝟑𝟔𝟗 − 𝟒𝟕 𝟐 [𝟖 𝟏𝟒𝟒𝟖 − 𝟐𝟖 𝟐 ]
𝟗,𝟒𝟕𝟐 −𝟏,𝟑𝟏𝟔
r=
𝟏𝟎,𝟗𝟓𝟐−𝟐,𝟐𝟎𝟗 [𝟏𝟏,𝟓𝟖𝟒−𝟕𝟖𝟒]
𝟖𝟏𝟓𝟔
r=
𝟖𝟕𝟒𝟑 [𝟏𝟎,𝟖𝟎𝟎]
 𝟖𝟏𝟓𝟔
r=
𝟖𝟕𝟒𝟑 [𝟏𝟎,𝟖𝟎𝟎]
𝟖𝟏𝟓𝟔
r=
𝟗,𝟒𝟒,𝟐𝟒,𝟒𝟎𝟎

𝟖𝟏𝟓𝟔
r=
𝟗𝟕𝟏𝟕.𝟐𝟐𝟏𝟖

r = 0.83933

Conclusion:
The correlation between per Capita Income and per Captia
Expenditure is high degree positive correlation
 1−𝒓𝟐
Probable Error (PE) = 0.6745( ), r = 0.83933
𝒏
1−(𝟎.𝟖𝟑𝟗𝟑𝟑)𝟐
Probable Error (PE) = 0.6745
𝟖
1−0.70447
Probable Error (PE) = 0.6745(
8
)
0.295525 r = 0.83933
Probable Error (PE) = 0.6745 ( )
2.8284
Probable Error (PE) = 0.6745(0.10448) Now, r > 6 PE
Probable Error (PE) = 0.070475 =>0.83933> 0.42285
Interpretation of probable error:
6PE = 6(0.070475) Therefore,
6PE = 0.42285 and ‘r ‘ is significant
6. From the following are the results of BBA Examination. Calculate coefficient of
correlation between age and percentage of success in an Examination.
Age 20-21 21-22 22-23 23-24 24-25 25-26
Candidates appeared 120 100 70 40 10 5
Success 72 55 35 18 4 1
Solution
Age(Mid-point)20.5 21.5 22.5 23.5 24.5 25.5
Percentage of 72/120 55/100 35/70 18/40 4/10 1/5
success 0.6x100 0.55x100 =0.5 x 100 =0.45 x100 =0.4 x100 0.2 x100
= 60% = 55% = 50% = 45% = 40% = 20%
Let us assume that X be the Age and Y be the Percentage of Success

X 20.5 21.5 22.5 23.5 24.5 25.5

Y 60 55 50 45 40 20
7. From the following data find out there is any relation between age and blindness.
Age 0-10 10-20 20-30 30-40 40-50 50-60 60-70 70-80
Blindness 55 35 43 40 36 22 18 15
Solution
Age 5 15 25 35 45 55 65 75
Blindness 55 35 43 40 36 22 18 15

Let us assume that X be the Age and Y be the Blindness

X 5 15 25 35 45 55 65 75
Y 55 35 43 40 36 22 18 15
8. Compute Karl Pearson’s coefficient of correlation between per capita income
and per capita expenditure and also find Probable Error.
Year 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009
Per capita income 249 251 248 252 258 269 271 272 280 275
Per capita expenditure 237 238 236 240 245 255 254 252 258 251
Solution
Per capita Income 249 251 248 252 258 269 271 272 280 275
Per capita 237 238 236 240 245 255 254 252 258 251
Expenditure

Let us assume that X be per capita income and Y be the per capita expenditure

X 249 251 248 252 258 269 271 272 280 275
Y 237 238 236 240 245 255 254 252 258 251
9. From the following data find out the correlation between age and Percentage of
reading habits of students.
age 15 16 17 18 19 20
No. of students 250 200 150 120 100 80
Regular Readers 200 150 90 48 30 12
Solution
Age 15 16 17 18 19 20
Percentage of 200/250 150/200 90/150 48/120 30/100 12/80
success 0.8x100 0.75x100 =0.6 x 100 =0.4 x100 =0.3 x100 0.15 x100
= 80% = 75% = 60% = 40% = 30% = 15%
Let us assume that X be the Age and Y be the percentage of Regular of Success

X 15 16 17 18 19 20
Y 80 75 60 40 30 15
10. Coefficient of correlation between two variables x and y is 0.8 their co-variance is 122.
The variance of x = 16, the number of values is 10. Find the value of σy.
Solution:
r = 0.8, Co-variance = Σxy = 122, Variance = 16, σx = 4. n = 10,
Σxy
Correlation coefficient (r) =
𝑛 σx σ𝑦
122
0.8 =
10 (4)(σy)
122
0.8 =
(40) σ𝑦
122
σ𝑦 =
(40 )(0.8)

122
σ𝑦 =
32

σ𝑦 = 3.8125
σ𝑦 = 4
11. If r = 0.98, n = 5 examine whether r is significant or not
12. If r = -1, n = 4 find whether r is significant or not. .
13. Find the probable error if r = 0.6 and n = 64
14. Find the probable error if r = 0.448 and n = 9
15. If σx = 11.2, σy = 36.9, Σxy = 270 , n = 8 find ‘r’.

Solution:

Σxy
Correlation coefficient (r) =
𝑛 σx σ𝑦 r = 0.081663
270
r=
8(11.2)(36.9)

270
r=
3306.24
16. From the following data compute coefficient of correlation between x and y if number of
values is 12 ,
(a) Square root of deviation from mean x = 115.96, y = 59.04
(b) The sum of the product of deviation of x and y from their respective mean is 53,956.
Solution:
The sum of the product of deviation of x and y from their respective
mean is 53956 = Co-variance = Σxy = 53956 , σx = 115.96. σy = 59.04 n = 12,
Σxy
Correlation coefficient (r) =
n σx σy
53956
r=
(12)(115.96)(59.04)
53956
r=
82155.3408
r = 0.65675584
17. Calculate correlation between x and y
Particulars No. of Pairs Variance
X 15 100
Y 15 144
Sum of product of deviations of x and y from their respective mean is 122.
Solution:
Variance (x) = 100
Standard Deviation(σx) = 𝑣𝑎𝑟𝑖𝑎𝑛𝑐𝑒 = 100 = 10
Variance (y) = 144
Standard Deviation(σy) = 𝑣𝑎𝑟𝑖𝑎𝑛𝑐𝑒 = 144 = 12 ,
n = 15, Σxy = 122
Σxy
Correlation coefficient (r) =
𝑛 σx σ𝑦
122
r=
15 (10)( 12)
122
r=
1800
r = 0.06777
 University Questions
2 – Marks

1. What is linear correlation?

2. What do you mean by correlation?
3. What is the meaning of Positive and Negative correlation
4. What is probable error
5. Mention the uses of correlation
6. State the assumptions of the Karl pearson’s coefficient of correlation
7. What is meant by perfect correlation?
8. Give the meaning of direct or positive correlation.
9. What is rank correlation?
10. Interpret when it is (a) – 0.25 (b) +0.95 (c) +1 (d) + 0.58.
11. If in a series r = 0.4 and N = 10 find the Probable error.
12. If in a series r = 0.6 and n = 10 find the Probable error.
13. If in a series r = 0.6 and n = 64 find the Probable error.
14. If in a series r = 0.8and n = 46 find the Probable error.
15. If in a series r = 0.9and n = 100 find the Probable error.
1. Calculate person’s coefficient of correlation from the following data using 44 and 26 as the origin of X and Y respectively.
X 43 44 46 40 44 42 45 42 38 40 42 57
Y 29 31 19 18 19 27 27 29 41 30 26 10
2. Calculate person’s coefficient of correlation from the following data using 44 and 26 as the origin of X and Y
respectively. Take 47 and 26 as assumed mean
Temperature 57 42 40 38 42 45 42 44 40
Germination time 10 26 30 41 29 27 27 19 18
3. Calculate Karl Person’s coefficient of correlation between heights and weights given below, taking 67 and 68 as
assumed mean respectively.
X 65 66 67 67 68 69 71 73
Y 67 68 64 68 72 70 69 70
4. Find the coefficient of correlation for the following data

X 10 14 18 22 26 30
f 18 12 24 6 30 36
5. Calculate Karl Pearson’s coefficient between Sales and advertising expenditure. Taking 17 as assumed mean and
comment on the correlation value.
Sales(in lakhs) 5 7 11 14 17 19 23 27 30
Advertising Expenditure (in 000s) 9 11 14 14 17 24 21 25 27
6. Find Karl Person’s coefficient of correlation from the following data. State whether ‘r’ is significant by using Probable
error.
Marks in Financial Accounting 45 70 65 30 90 40 50 75 85 60
Marks in Statistics 35 90 70 40 95 40 60 80 80 50
7. Find Karl Person’s coefficient of correlation between sales and advertising expenditure from the following data:
Sales(Rs. In lakhs) 65 66 67 68 69 70 71 72 73
Advertising Exp. Rs. In ‘000’ 66 67 64 67 71 69 70 68 70
8. Compute Karl Person’s coefficient of correlation from the following data and also calculate the Probable error.
Supply(quintals): 30 29 29 25 24 24 24 21 18 15
Price(Rs.) 11 12 13 14 15 16 15 17 18 20
9. From the following data on six cities, calculate the coefficient of correlation between density of population and death rate.
City A B C D E F
Density of population 200 500 400 700 600 300
Population(‘000’) 30 90 40 42 72 24
No. of deaths 300 1440 560 840 1224 312
10. From the following data of the marks obtained by 10 students in Accounts and Statistics. Calculate Pearson’s correlation.
Roll No 1 2 3 4 5 6 7 8 9 10
Marks in Accounts 20 25 60 45 80 28 55 65 30 75
Marks in Statistics 25 50 55 56 60 70 72 78 80 63
11. Following are the results of [Link] examination of a college. Calculate the Pearson’s coefficient of correlation between
the age and success of candidates.
Age (in years) 14 – 15 15 - 16 16 - 17 17 - 18 18- 19 19 – 20 20 - 21
No. of Candidates appeared 300 100 50 150 400 250 150
No. of Candidates passed 180 65 34 90 250 145 81

12. Following are the results of [Link] examination of a college. Calculate the Pearson’s coefficient of correlation between
the age and success of candidates.
Age (in years) 15 16 17 18 19 20
No. of Candidates appeared 400 540 680 720 800 600
No. of Candidates passed 300 324 340 360 360 240