Scribd
Upload
16 views17 pages

Correlation

Uploaded by

sharatkamath1002
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
16 views17 pages

Correlation

Uploaded by

sharatkamath1002
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
You are on page 1/ 17

CORRELATION

WHAT IS CORRELATION?
• It measures the degree and intensity of relation between two
variables.
• Correlation does not guarantee cause and effect relationship between
the two variables.
POSITIVE AND NEGATIVE
CORREALTION
• Positive – when the two variables move in the same direction
when their values change
• Negative – when the two variables move in the opposite direction
when their values change
POSITIVE CORRELATION NEGATIVE CORRELATION
VARIABLE 1 VARIABLE 2 VARIABLE 1 VARIABLE 2
0 20 0 40
5 40 5 35
10 55 10 30
25 70 25 25
30 85 30 20
45 95 45 15
LINEAR AND NON-LINEAR
CORRELATION

• Linear – when the changes in LINEAR CORRELATION NON-LINEAR CORRELATION


both variables follow a constant VARIABLE 1 VARIABLE 2 VARIABLE 1 VARIABLE 2
proportional change; the graph
2 5 2 3
between the two variables will
be a straight line 4 10 4 7
• Non – linear – when the changes 6 15 6 12
in both the variables does not 8 20 8 18
follow any constant proportional 10 25 10 25
changes, but occurs in a non- 12 30 12 35
linear way; the graph between
14 35 14 45
the two variables will not be a
straight line
SIMPLE AND MULTIPLE
CORREALTION
• Simple correlation is when only two variables are studied for their
degree of relationship between each other.
• Multiple correlation is when multiple independent variables and
their degree of relation with a single dependent variable is
studied.
DEGREES OF CORRELATON

1. PERFECT CORRELATION
i. Perfect positive – the correlation between the two variables when proportional
change between them is in the same direction. The correlation coefficient is +1.
ii. Perfect negative – the correlation between the two variables when
proportional change between them is in the opposite direction. The correlation
coefficient is -1.
2. ABSENCE OF CORRELATION – when there is no relation between the two variables. Change in one variable doesn’t affect
the other variable.
3. LIMITED DEGREE OF CORRELATION – in real life, correlation between two variables exists somewhere in between perfect
correlation and absence of correlation. It can of three levels –
i. HIGH – when the correlation between the two is very large. Correlation coefficient lies from +0.75 to +1
ii. MODERATE - when the correlation between the two is neither large nor small. Correlation coefficient lies from +0.25 to +0.75.
iii. LOW - when the correlation between the two is very small. Correlation coefficient lies from 0 to +0.25
MEASURMENT OF
CORRELATION
SCATTERED DIAGRAM

• By using the help


of a scatter plot,
which is the
distribution of data
of the two
variables on a
graph, the
correlation
between them can
be studied.
SCATTERED DIAGRAM – MERITS AND
DEMERITS

• MERITS
1. Simple
2. A glance at the diagram is enough
3. Indicates whether it is positive or negative
• DEMERITS
1. No precise measurement
2. Approximate idea only
3. Not a quantitative measure but only a qualitative measure
EXAMPLES
•1

HEIGHT 180 150 158 165 175 163 195 155 170

WEIGHT 65 54 55 65 60 54 63 50 70

• 2 – SHOW THE RELATION BETWEEN X AND Y THROUGH A SCATTERED


DIAGRAM
X 8 16 24 31 42 50
Y 70 58 50 32 26 12
KARL PEASRSON’S CORREALTION
COEFFICIENT

• According to Karl Pearson, the correlation between two variables can be quantitatively
calculated by using the below formula –

𝑟=
∑ 𝑥𝑦
𝑁 𝜎 𝑥𝜎 𝑦

r = coefficient of correlation

= Standard deviation of X
= Standard deviation of Y
N = Number of observations
MODIFIED KARL PEARSON’S
FORMULA

Here,
EXAMPLE

X 2 3 4 5 6 7 8
Y 4 7 8 9 10 14 18

Age of 21 22 28 32 35 36
Husband
Age of wife 18 20 25 30 31 32
X Y Dev x Dev y x2 y2 x*y X Y Dev x Dev y x2 y2 x*y
21 18 -8 -8 64 64 64
2 4 -3 -6 9 36 18
22 20 -7 -6 49 36 42
3 7 -2 -3 4 9 6
28 25 -1 -1 1 1 1
4 8 -1 -2 1 4 2
32 30 3 4 9 16 12
5 9 0 -1 0 1 0
6 10 1 0 1 0 0 35 31 6 5 36 25 30
7 14 2 4 4 16 8 36 32 7 6 49 36 42
8 18 3 8 9 64 24 174 156 0 0 208 178 191
35 70 0 0 28 130 58 Mean of
husband mean of
Mean of Mean of wife age
X Y age
5 10 29 26
KARL PEARSON’S COEFFICIENT –
SHORTCUT METHOD
• When the mean of the two variable is in fractions, assumed mean
method is used to calculate the correlation coefficient.
• In both the variables an assumed mean is selected, deviations are
calculated and using the deviations, “r” is calculated using the given
formula.
EXAM
PLE

You might also like