Scribd
Upload
39 views4 pages

ManSci Notes - Regression Analysis

The document discusses simple linear regression analysis. It introduces regression as a technique to predict the value of one variable based on another. An example is provided of a store manager analyzing how TV advertising expenditures affect monthly sales. A regression equation is calculated using the historical data points, yielding an equation where monthly sales = 1.02 * TV expenditures + 19.49. This equation is then used to predict monthly sales levels corresponding to TV expenditure amounts from $0 to $19,000.

Uploaded by

dmangigin
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
39 views4 pages

ManSci Notes - Regression Analysis

The document discusses simple linear regression analysis. It introduces regression as a technique to predict the value of one variable based on another. An example is provided of a store manager analyzing how TV advertising expenditures affect monthly sales. A regression equation is calculated using the historical data points, yielding an equation where monthly sales = 1.02 * TV expenditures + 19.49. This equation is then used to predict monthly sales levels corresponding to TV expenditure amounts from $0 to $19,000.

Uploaded by

dmangigin
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 4

Philippine School of Business Administration

826 R. PAPA STREET, SAMPALOC MANILA

REGRESSION ANALYSIS:
● It is the relationship between variables to be able to predict the value of one based on
the other.
● It is a statistical technique use to find relationships between variables for the purpose of
predicting future values.
For this regression analysis will be introduced with the following assumptions:
1. Historical Data of two or more variables are determined.
2. The historical data are long enough in the past.
This chapter will introduce three models
1. Simple Regression
SIMPLE REGRESSION:
A linear regression is simple if there is only one independent variable.
For this section, simple linear regression will be presented with the following condition:
1. There is only one independent variable.
2. There is a linear relationship between the independent and dependent variables.
EXAMPLE: BENCH GLORIETTA
Jefferson, the Store Manager of BENCH GLORIETTA branch, wants to determine the
effect of TV advertising to the branch sales per month. He was able to monitor the TV and
expenditure and the sales per month. This year, the TV ad expenditure and sales for the month
of January is $8,000 and $24,000 respectively, February is $5,000 and $25,000, March is
$13,000 and $28,000, April is $9,000 and $31,000, May is $6,000 and $27,000, June is $16,000
and $39,000, July is $10,000 and $26,000, August is $15,000 and $37,000, September is $11,000
and $29,000, October is $14,000 and $32,000, November is $12,000 and $35,000, and
December is $7,000, and $30,000 respectively. The figures are summarized in a table below:
What is the monthly sales forecast if there are no TV ad expenditures? What if it is
$1,000? Jefferson also wants to determine the sales forecast for every $1,000increase in TV ad
expenditure up to $19,000.

Dominic Q. Taday
Philippine School of Business Administration
826 R. PAPA STREET, SAMPALOC MANILA

STEP 1: Plot Data from the table to a regression chart, and draw a Trend Line to see for a
relationship between variables

STEP 2: Determine the Coefficients of the REGRESSION EQUATION with the help table:
FORMULA:

^
Trend Line: 𝑦 = 𝑎𝑥 + 𝑏

Dominic Q. Taday
Philippine School of Business Administration
826 R. PAPA STREET, SAMPALOC MANILA

𝑛∑𝑥𝑦−(∑𝑥)(∑𝑦)
Where: 𝑎= and 𝑏 = 𝑦 − 𝑎𝑥
2 2
𝑛∑𝑥 −(∑𝑥)

n = 12 𝑥 = 10.5 𝑦 = 30.25 ∑x^2 = 1,466


∑x = 126 ∑y = 363 ∑xy = 3,958 (∑x)^2 = 15,876

12(3958)−(126)(363) 1758
𝑎= 12(1466)−15876
𝑎= 1716
𝑎 = 1. 02

𝑏 = 30. 25 − (1. 02)(10. 5) = 19. 49

^
Trend Line: 𝑦 = 1. 02𝑥 + 19. 49

STEP 2: Using the Trend Line Equation, predict the monthly sales when TV Ad is between 0
and $19,000 at $1,000 interval.
^
Trend Line: 𝑦 = 1. 02𝑥 + 19. 49
19.49 = 19.49 + 1.02(0)
20.52 = 19.49 + 1.02(1)
21.54 = 19.49 + 1.02(2)
…

Dominic Q. Taday
Philippine School of Business Administration
826 R. PAPA STREET, SAMPALOC MANILA

38.96 + 19.49 + 1.02(19)

Thus the predicted monthly sales are shown above.

REFERENCE: Quantitative Decision Model


by: Edwin J Loma

Dominic Q. Taday

You might also like