BIOSTATISTICS

LINEAR REGRESSION &

CORRELATION .

PRESENTER ; MICHAEL GILYA

FACILITATOR; PROF. SEMALI
Correlation
• Correlation; is a statistical tool that helps to measure
and analyze the degree of relationship between two
variables.

• Correlation analysis deals with the association

between two or more variables.

2
Correlation & Causation
Correlation denotes the interdependency among
the variables for correlating two phenomenon.

It is essential that the two phenomenon should

have cause-effect relationship,& if such relationship
does not exist then the two phenomenon can not
be correlated.

3
 Cont..
• If two variables vary in such a way that movement in
one are accompanied by movement in other, these
variables are called cause and effect relationship.

• Causation always implies correlation but correlation

does not necessarily implies causation.

4
Types of correlation

Type1
 A) POSITIVE CORRELATION

• The correlation is said to be positive correlation if

the values of two variables are changing with same
direction. E.g. Height & weight, water consumption
& temperature, study time & grades.
• Variable Y increases as x Increases and Vice versa is
true
5
Cont..
B) NEGATIVE CORRELATION

• The correlation is said to be negative correlation

when the values of variables change with opposite
direction .e.g. Price & quantity demanded, alcohol
consumption & driving ability.

 Variable Y increases as variable x decreases and

Vice versa is true
6
» TYPE 2;
 A) Simple correlation: only two variables are
studied.
 B) Multiple Correlation: three or more than
three variables are studied. Further
categorized into;
 Partial correlation: analysis recognizes
more than two variables but considers only
two variables keeping the other constant.
 Total correlation: is based on all the
relevant variables, which is normally not
feasible.
7
TYPE 3;
 A) Linear correlation: Correlation is said to be linear when the
amount of change in one variable tends to bear a constant
ratio to the amount of change in the other. The graph of the
variables having a linear relationship will form a straight line.
B) Non Linear correlation: The correlation would be non linear
if the amount of change in one variable does not bear a
constant ratio to the amount of change in the other variable.

8
 Pearson’s Linear Correlation Coefficient:

• Linear regression provides us with a straight line which

summarizes the relationship between two variables.

• However, it does not tell us how closely the data lie on a

straight line.

• The closeness with which the points lie along the

straight line is measured by the (Pearson's) correlation
coefficient 9
 Pearson’s Linear Correlation Coefficient

• It measures the strength of the linear association between two

quantitative variables

• Can be obtained by using the formula:

 ( x  x )( y  y )
r= 2 2
 ( x  x)  ( y  y )
Where:
i. r = Correlation coefficient
ii. Xi = Values of the x –variable in a sample
iii. x̄ = mean of the values of the x-variable
iv. yi = Values of the y – variable in a sample
10
v. ȳ = mean of the values of the y - variable
Characteristics of r
• It is a bivariate correlation coefficient summarizing the magnitude
and direction of the relationship between two variables.

• r> 0 means the variables are positively correlated, meaning that as x

increases, y tends to increase and the vice versa.

• r< 0 means variables are negatively correlated, as x increases, y tends

to decrease, while as x decrease , y tends to increase.

11
Cont..
• Ranges between -1 and +1
r=0 = No linear relationship ( uncorrelated)
r=1 = Perfect positive relationship
r= -1=Perfect negative relationship

12
1. Calculate the Correlation coefficient of age (Years) against the
body mass index of patients attended the clinic at a certain
department.
N AGE (YEARS) BMI (Kg/m2)
1 73 28
2 22 22
3 74 27
4 34 29
5 50 29
6 42 27
7 64 28
8 53 29
9 43 24
10 21 19
11 12 17
• Recall for, r

 ( x  x )( y  y )
2 2
 ( x  x)  ( y  y )
 X Y X - X̄ Y - Ȳ (X - X̄ )(Y –Ȳ ) (X- X̄ )2 (Y-Ȳ )2
73 28 73 – 44 = 29 28 – 25 = 3 87 841 9
22 22 22 - 44 = -22 22 – 25 = -3 66 484 9
74 27 74 – 44 = 30 27 – 25 = 2 60 900 4
34 29 34 – 44 = -10 29 – 25 = 4 -40 100 16
50 29 50 – 44 = 14 29 – 25 = 4 56 196 16
42 27 42 – 44 = -2 27 – 25 = 2 -4 4 4
64 28 64 – 44 = 20 28 – 25 = 3 60 400 9
53 29 53 – 44 = 9 29 – 25 = 4 36 81 16
43 24 43 – 44 = -1 24 – 25 = -1 1 1 1
21 19 21 – 44 = -23 19 – 25 = -6 138 529 36
12 17 12 – 44 = -32 17 – 25 = -8 256 1024 64
X̄ = 44 Ȳ = 25 Σ = 12 Σ=4 Σ = 716 Σ = 4564 Σ=184
r = 0.781

What does it mean?

How to use excel to find r ?
N AGE (YEARS) BMI (Kg/m2)
1 73 28
2 22 22
3 74 27
4 34 29
5 50 29
6 42 27
7 64 28
8 53 29
9 43 24
10 21 19
11 12 17
Rule of thumb for r
Correlation Strong Weak
Positive 0.7 to 1.0 0.3 to <0.7

Negative -1.0 to -0.7 -0.7< to -0.3

Little or No Correlation: -0.3 to 0.3

18
Degree of Correlations
a c
b

Strong +ve r Weak +ve r Strong -ve r

d e f

Weak - r Moderate –ve r No r

19
Coefficient of Determination
• Coefficient of Determination r2 is the square of the
Pearson’s correlation coefficient r.

• Represents the prediction percentage

20
• It denotes the percentage at which x can predict y.

• For example, r2 of 0.612 (= 61.2%) on a study of Age(x) and SBP (y)

will mean that:
• Age can predict SBP by only 61.2%, the remaining %
can only be predicted by other factors.

21
• In other words it will mean that only 61.2% of changes
in SBP (y) are due to changes in Age (x)

• Moreover we can say that, when you use Age( X) you

can only predict SBP (y) by only 61.2%.

22
Assumptions of Pearson’s Correlation
Coefficient

• There is linear relationship between two variables, i.e. when the two
variables are plotted on a scatter diagram, a straight line will be
formed by the points.

• Cause and effect relation exists between different forces operating on

the item of the two variable series.

23
Advantages of Pearson’s
Coefficient
• It summarizes in one value, the degree of correlation
& direction of correlation also.

24
THANK YOU

FOR YOUR ATTENTION!

25