UNIT 13

REGRESSION ANALYSIS

Introduction

Regression Analysis is a technique used to develop the equation for a straight

line and make predictions. It is an equation that defines the relationship between two
variables.

The general form of linear regression equation is

Y^ = a + bx

Where

Y^ = read as y prime, is the predicted value of the Y variable for a selected

x value.

a is the Y-intercept. It is the estimated value of Y when x = 0. Another way

to put it is: a is the estimated value of Y where the regression line
crosses the Y axis when x = 0.

b = is the slope of the line, or the average change in y’ for each change of

one unit (either increase or decrease) in the independent variable

X.

X is any value of the independent variable that is selected.

The following formulas are needed to compute for a and b.

n ( ∑ XY )−(∑ X )(∑ Y )
Slope of the Regression Line: b =
N ( ∑ X 2 ) −( ∑ X ¿¿¿ 2 )

∑Y ∑X
Y-Axis Intercept a= -b
n n

Where:

X is the value of the independent variable

Y is the value of the dependent variable

n = the number of items in the sample

Example 1. The manager of a Furniture Company was studying the relationship
between sales and the amount spent on advertising. The sales information for the last
four months is shown below:

Month Advertising Sales Revenue

Expense (P Millions)
(P Millions)(X) (Y)
January 4 9
February 2 5
March 5 8
April 6 10
May 8 12
Total 25 44

(a) Determine the regression equation

(b) Interpret the values of a and b.
(c) Estimate sales when 4 million pesos is spent on advertising

The independent variable of the problem is the advertising expense (X)

and the dependent variable is the Sales revenue (Y).

Solution:

Step 1. Construct the table below to show the values of ∑X, ∑Y, ∑X 2, ∑XY

Month Advertising Sales

(X)Expense Revenue XY X2
(P Millions) (X) (P Millions)
(Y)
January 3 9 27 9
February 2 5 10 4
March 3 8 24 9
April 4 10 40 16
May 5 12 60 25
Total ∑X =16 ∑Y = 44 ∑XY = ∑X2= 63
161

Step 2. Solve for “b”, using the formula:

n ∑ XY −∑ X ∑Y 5 ( 161 ) −(16)( 44) 805−704 101

b= = = =
n ( ∑ X 2 ) −¿ ¿ 5 ( 63 )−¿ ¿ 315−256 59
 b = 1.71

Step 3. Solve for “a”, using the following formula:

∑Y ∑ X 44 16
a= -b = -1.71( ) = 8.8 – 5.472
n n 5 5

a = 3.328

Step 4. Regression equation is:

Y’ = a + bx  Y’ = 3.328 + 1.71x

Step 5. A = 3.328 is the y-intercept and b =1.71 is the slope of the

regression line.

Step 6. The sales when the advertising expense is 4 is:

Y’ = 3.328 + 1.71(4) = 10.168 is the estimated sales when advertising

expense is 4 million.

Example 2. A personnel specialist with a large accounting firm is

interested in determining the effect of seniority (the number of years in the
company) on hourly wages for secretaries. She selected at random 10
secretaries and compares their years with the company (X) and the hourly
wages (Y).

a. Calculate the regression slope and Y-intercept

b. Determine the regression equation
c. Predict the hourly wage of a randomly selected secretary who has
been with the company for 5 years.

Solution:

Step 1. Determine the values of ∑X, ∑Y, ∑XY, and ∑X2

Secretary X Y XY X2
A 0 12 0 0
B 2 13 26 4
C 3 14 42 9
D 6 16 96 36
E 5 15 75 25
F 3 14 42 9
G 4 13 52 16
H 1 12 12 1
I 1 15 15 1
J 2 15 30 4
 Total ∑x =27 ∑Y=139 ∑XY = 390 ∑X2 = 105

Step 2. Solve for “b”.

10 ( 390 )−(27)(139) 147

b= = = 0.46
10 ( 105 ) −(27)(27) 321

Step 3. Solve for “a”.

139 27
a= – 0.46( ) = 13.9 – 1.242 = 12.66
10 10

Step 4. Regression equation is

Y’ = 12.66 + 0.46x

Step 5. Regression slope is 0.46 and the Y-intercept is 12.66

Step 6. Determine the wage of the secretary who has been with the
company for 5 years.

Y’ = 12.66 + 0.46(5)  12.66 + 2.3

Y’ = 14.96 (the predicted wage of the secretary who has been with
the company for 5 years)

Example 3. The City Mall of the province sells fashion apparel for men and women plus a
broad range of home products. It services its customers by Mail. Listed below are the net
sales for the City Mall from 2000 through 2005. Draw a line chart depicting the net sales over
the time period and write a brief report.

Year(x) Net Sales (PhpMillions)(Y)

2000 (1) 506.8
2001(2) 522.2
2002(3) 574.6
2003(4) 580.7
2004(5) 568.5
2005(6) 581.9

x Y XY X2
1 506.8 506.8 1
2 522.2 2
3 574.6 9
4 580.7 16
5 568.5 25
6 581.9 36
Total
 nΣxy−( Σx)(Σy)
b=
nΣ x 2−¿ ¿
a= Σy
n
– b ( Σxn ); y’ = a + bx
Determine the sales in 2008?
Example 4. The following table shows the population, in thousands, of the Province for 10
year.
Year Population (Thousands) Year Population
(Thousands)
2000 152.3 2006 227.7
2001 165.4 2007 238.5
2002 180.7 2008 249.9
2003 194.3 2009 263.0
2004 205.1 2010 282.5
2005 218.0
∑Y ∑X n ∑ XY −∑ X ∑Y
a= -b ; b=
n n n ( ∑ X 2 ) −¿ ¿

Y’ = a + bx

Activity 13

Regression Analysis

1. A communication researcher wanted to measure the effect of television

viewing on aggressive behavior. He questioned a random sample of 14
children as to how many hors of television they watch daily (X) and
then, as a measure of aggression, observed the number of
schoolmates they physically attacked (shoved, pushed, or hit) on the
playground during a 15-minute recess (Y). The following results were
obtained:

X Y
0 0
6 3
2 2
4 3
4 4
1 1
1 0
2 3
5 3
5 2
4 3
0 1
2 3
6 4
a. Draw a scatter plot of the data
b. Calculate the regression slope and y-intercept
c. Draw the regression line on the scatter plot
d. Predict the number of schoolmates attacked by a child who watches
television 3 hours daily
2. An educational researcher was interested in the effect of academic
performance in high school on academic performance in college. She
consulted the school records of 12 college graduates, all of whom had
attended the same high school, to determine their high school
cumulative grade average (X) and their cumulative grade average in
college (Y). The following results were obtained:

X (High School) Y (College)

3.3 2.7
2.9 2.5
2.5 1.9
4.0 3.3
2.8 2.7
2.5 2.2
3.7 3.1
3.8 4.0
3.5 2.9
3.7 2.0
2.6 3.1
4.0 3.2

a) Draw a scatter plot of the data

b) Calculate the regression slope and Y-intercept
c) Draw the regression line on the scatter plot
d) Determine the regression equation
e) Predict the college grade average of a student who attains a 3.0 grade
in high school.

3. The Manager of Legazpi Mall believes that there is a relationship

between the number of client contacts and the amount of sales. To
document his assertion, He gathered the following sample information.
The X column indicates the number of client contacts for the month of
October 2020, and the Y column shows the amount of sales (in
thousands of pesos) of the same month.
 No. of Sales No. of contacts Sales
Contacts (P thousands) (P thousands
x y X Y
14 24 23 30
12 14 48 90
20 28 50 85
16 30 55 120
46 80 50 110

a. Calculate the regression slope and Y-intercept

b. Determine the regression equation
c. Determine the estimated sales if 40 contacts are made.