GE 4

Mathematics in the
Modern World

ENGR. MARC FRANCIS M. LABATA, PH.D. Lecture 11

INSTRUCTOR
TOPIC:

STATISTICS – PART III

2
LINEAR CORRELATION
A correlation analysis tries to measure how two random variables are
strongly related using a correlation coefficient. This is only concerned
with the strength of the relationship and no causal effect is implied.
The sample correlation coefficient, denoted by (r) can be calculated as:

3
 LINEAR CORRELATION
The interpretation of the Sample Pearson Correlation Coefficient is
as follows:
1. The value of r ranges from -1 to +1. If r = ± 1, there is a perfect linear
relationship and all points lie in the straight line.
2. If r is close to +1, it indicates a high positive linear relationship between two
variables X and Y. If X increases, Y also increases.
3. If r is close to -1, it indicates a negative linear relationship between variables
X and Y. If X increases, Y decreases.
4. An r value near 0 means there is a lack of linearity between two variables or
no linear relationship between them. The relationship may not be linear.

4
LINEAR CORRELATION
Sample Pearson Correlation Coefficient

Value Interpretation
±1.00 Perfect Positive or Negative Correlation
±0.91 – ±0.99 Very High Positive or Negative Correlation
±0.71 – ±0.90 High Positive or Negative Correlation
±0.51 – ±0.70 Moderately Positive or Negative Correlation
±0.31 – ±0.50 Low Positive or Negative Correlation
±0.01 – ±0.30 Negligible Positive or Negative Correlation
0 No Correlation

5
LINEAR CORRELATION
Scatter Diagram – a graphical presentation of the independent
variable (x-axis) and dependent variable (y-axis). This is the easiest way
to determine if a relationship exists between the two variables.

6
LINEAR CORRELATION

• In Figure 3, the coefficient r becomes smaller as the distribution of points cluster less
closely around the line, and virtually zero when the distribution shows randomness.
• Figure 4 shows a neat curvilinear relationship between variables and can be verified
that its linear correlation coefficient will be low or near 0.

7
LINEAR CORRELATION

The Sample Coefficient of Determination (r2) determines the total

variation of variable Y that can be accounted for or explained by the
linear relationship with the values of variable X. This number is usually
expressed as a percentage.

For example, if r = 0.60, then r2 = (0.60)2 = 36%.

8
LINEAR CORRELATION

Exercise: Given the following quiz scores for 10 students in Science (x)
and Math (y), calculate the Pearson Correlation Coefficient.

x 20 15 18 15 20 25 19 8 15 14
y 6 12 9 18 15 15 16 7 10 24

9
LINEAR CORRELATION
Exercise:
x y xy x2 y2
20 6 120 400 36
25 12 300 625 144
10 2373 − (179)(132)
18 9 162 324 81 𝑟=
15 18 270 225 324
10 3445 − (179)! 10 2016 − (132)!
20 15 300 400 225
25 15 375 625 225 102
𝑟=
19 16 304 361 256 (2409)(2736)
8 7 56 64 49
15 10 150 225 100
𝒓 = 𝟎. 𝟎𝟒 ∴ Negligible Positive Correlation
14 24 336 196 576
179 132 2373 3445 2016

10
SIMPLE LINEAR REGRESSION

A regression analysis is a statistical method that utilizes the

relationship between two or more quantitative variables so one
variable, the dependent variable or response variable, can be
predicted with the knowledge of the values of another variable, the
independent variable or explanatory variable.

A mathematical equation used to predict the dependent variable is

called a regression equation.

11
SIMPLE LINEAR REGRESSION

Regression Equation y =a + bx
Where

α - intercept
β – slope of the regression line
x – independent variable

12
SIMPLE LINEAR REGRESSION
Assumptions in regression analysis:
• The values of the independent variable x may be fixed, that is the x
values must be selected by the researcher in advance. The x-value is
not a random variable.
• The values of x are measured without error.
• The dependent variable y, given different values of independent
variable x is normally distributed.
• The variances of the dependent variable y, given different values of
x are equal.

13
SIMPLE LINEAR REGRESSION
Estimation of Parameters

𝑛 ∑ 𝑥𝑦 − ∑ 𝑥 ∑ 𝑦
𝛽= !
𝑛∑𝑥 ! − (∑ 𝑥)

𝛼 = 𝑦, − 𝛽 𝑥̅

14
SIMPLE LINEAR REGRESSION
Exercise 𝑛 ∑ 𝑥𝑦 − ∑ 𝑥 ∑ 𝑦
𝛽= !
x y xy x2 y2 ∑ ! ∑
𝑛 𝑥 − ( 𝑥)
20 6 120 400 36
10 2373 − (179)(132)
25 12 300 625 144 𝛽=
10 3445 − (179)!
18 9 162 324 81
15 18 270 225 324 𝜷 = 𝟎. 𝟎𝟒
20 15 300 400 225
25 15 375 625 225
𝛼 = 𝑦< − 𝛽𝑥̅
19 16 304 361 256
8 7 56 64 49 132 179
15 10 150 225 100 𝛼= − (0.04)
10 10
14 24 336 196 576
179 132 2373 3445 2016 𝜶 = 𝟏𝟐. 𝟒𝟖

15
SIMPLE LINEAR REGRESSION
Exercise
x y xy x2 y2
20 6 120 400 36 𝒚 = 𝟎. 𝟎𝟒𝒙 + 𝟏𝟐. 𝟒𝟖
25 12 300 625 144
18 9 162 324 81
15 18 270 225 324
If x = 36, y = 13.92
20 15 300 400 225
25 15 375 625 225
19 16 304 361 256
8 7 56 64 49
15 10 150 225 100
If x = 48, y = 14.40
14 24 336 196 576
179 132 2373 3445 2016

16