Scribd
Upload
56 views

Linear Regression

Here are the steps to solve this problem: a) The scatter diagram is shown above with Sales (Y-values) on the vertical axis and Number of Contacts (X-values) on the horizontal axis. b) To find the regression equation: - Compute the needed summations and means: ∑X = 284, ∑X2 = 8,028, ∑XY = 4,692 ∑Y = 521, ∑Y2 = 37,484 X = 35.5, Y = 65.125 - Solve for a and b: b = [n∑XY - ∑X∑Y] / [n∑X2 - (

Uploaded by

Catherine Malabanan Dizon
Copyright
© © All Rights Reserved
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
56 views

Linear Regression

Here are the steps to solve this problem: a) The scatter diagram is shown above with Sales (Y-values) on the vertical axis and Number of Contacts (X-values) on the horizontal axis. b) To find the regression equation: - Compute the needed summations and means: ∑X = 284, ∑X2 = 8,028, ∑XY = 4,692 ∑Y = 521, ∑Y2 = 37,484 X = 35.5, Y = 65.125 - Solve for a and b: b = [n∑XY - ∑X∑Y] / [n∑X2 - (

Uploaded by

Catherine Malabanan Dizon
Copyright
© © All Rights Reserved
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
You are on page 1/ 20

SIMPLE LINEAR

REGRESSION
INTRODUCTION

Scientists, economists, psychologists, and


sociologists have always been concerned
with the problems of prediction.
The goal of studying regression is to be able
to predict behavior as accurately as possible
on the basis of established relationship
between one variable and another variable.
LINEAR REGRESSION

For example, it is possible to predict such


outcomes as:
Sales based on advertisement;
Brand as an index of sales;
Success in one job based on success in another
job;
Performance on a task related to income;
Wage or price increases based on past trends; etc.
LINEAR REGRESSION

When a relationship is suggested by a scatter


plot, the relationship is usually described
mathematically by finding an equation that
summarizes the way two variables are
related; such an equation is a mathematical
model.
A mathematical equation that is used to predict
values of one dependent variable from known
values of one or more independent variables
is called a regression equation.
LINEAR REGRESSION

Consider the problem of predicting values of a dependent


variable on the basis of a known measurement of an
independent variable. The regression equation is
expressed in the form
Y = a+ bX
where:
Y = dependent variable (predicted value for a given x value)
X = independent variable
(explanatory variable or predictor)
a = y-intercept
b = slope of the regression line
LINEAR REGRESSION

The value of a and b are calculated from the


formulas:
nXY  XY
b
nX 2  (X ) 2

a  Y  bX
TYPES OF RELATIONSHIPS

Linear relationships Curvilinear relationships


Y Y

X X

Y Y

X X
TYPES OF RELATIONSHIPS
Strong relationships Weak relationships
Y Y

X X

Y Y

X X
EXAMPLE:
Find the equation of the regression line of the following:
Hours Spent in Score in the
Student
Studying Exam
1 2 60
2 3 63
3 4 69
4 4 78
5 4 79
6 6 80
7 6 85
8 7 91
9 7 93
10 7 96
Total
50 794
SOLUTION:
The regression equation:
Compute the needed summations and means.
∑X = 50 ∑X2 = 280 ∑XY = 4163
∑Y = 794 = 5X = 79.4 Y
Solve for a and b.
b = [n∑XY – ∑X∑Y] / [n∑x2 –(∑x)2 ]
b = [10(4163) – 50(794)] / [10(280) – (50) 2]
b = 6.43
a  Y  bX
= 79.4 – 6.43(5)
a = 47.25
 Having calculated the values of a and b, the equation of
the regression line is
Y = a+ bX
Y = 6.43 x + 47.25
 The graph of the regression line and the scatter points are
shown below.
REGRESSION LINE

120
Y-Values
100

80

60

40

20

0
1 2 3 4 5 6 7 8
 Trend line is a line passing through the
series of points such that the total
vertical measurement of the points
below this line is more or less equal to
the total measurements of the points
above the line.
LINEAR REGRESSION
Example 2:
The table below shows the advertisement expense per month, expressed in
thousand pesos, and the net profit, expressed as a percentage of total
sales, of a random sample of seven stores:

Advertisement
Store Net Profit, Y
Expense, X
1 45 6.2

2 62 8.0

3 49 6.0

4 61 7.2

5 67 8.7

6 82 9.1

7 70 8.2
LINEAR REGRESSION
a) Construct the scatter diagram for the given
data.
b) Find the regression equation
Net Profit
10
9
8
7
6
5
4
3
2
1
0
40 45 50 55 60 65 70 75 80 85
SOLUTION:
b) The regression equation:
Compute the needed summations and means.
∑X = 436 ∑X2 = 28,104 ∑XY = 3411.3
∑Y = 53.4 ∑Y2 = 416.02
X= 62.29 Y = 7.63
Solve for a and b.
b = [n∑XY – ∑X∑Y] / [n∑x2 –(∑x)2 ]
b = [7(3411.3) – 436(53.4)] / [7(28,104) – (436) 2]
b = 0.09
a = Y – bX
a = 7.63 – 0.09(62.29) = 2.02
Thus, the regression equation is
Y = 2.02 + 0.09X.
LINEAR REGRESSION
Example 3:
The section head of 8 medical representatives believes that there is a
relationship between the number of contacts a medical representative
has and his sales. To prove his claim, he gathered the ff information from
his group and the results are tabulated below.

Sales (in
Medical Number of
thousand
Representative Contacts
pesos)
A 48 84
B 25 34
C 18 34
D 50 94
E 22 32
F 52 89
G 14 18
H 57 124
LINEAR REGRESSION
a) Construct the scatter diagram for the given
data.
b) Find the regression equation
Y-Values
140

120

100

80 Y-Values

60

40

20

0
10 15 20 25 30 35 40 45 50 55 60

You might also like