Scribd
Upload
6 views5 pages

Forcasting Exercises Page 28 Half Done

The document outlines sales data for a company and provides calculations for four-month moving averages, exponential smoothing forecasts, and a regression model relating sales to advertising expenditure. It includes detailed calculations for moving averages, exponential smoothing with a smoothing constant, and the derivation of a regression equation. The final regression equation established is Y = 6.89 + 0.00664X, where Y represents sales and X represents advertising expenditure.

Uploaded by

Daniel Solomon
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
6 views5 pages

Forcasting Exercises Page 28 Half Done

The document outlines sales data for a company and provides calculations for four-month moving averages, exponential smoothing forecasts, and a regression model relating sales to advertising expenditure. It includes detailed calculations for moving averages, exponential smoothing with a smoothing constant, and the derivation of a regression equation. The final regression equation established is Y = 6.89 + 0.00664X, where Y represents sales and X represents advertising expenditure.

Uploaded by

Daniel Solomon
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
You are on page 1/ 5

Question 1

a) The table below shows the sales data for the company.
Required: Calculate the four-month moving averages for the data.
Sales Data Recap
Month Sales
Jan 1200
Feb 1280
Mar 1310
Apr 1270
May 1190
Jun 1290
Jul 1410
Aug 1360
Sep 1430
Oct 1280
Nov 1410
Dec 1390
Calculations
1. January–April:
1200+1280+ 1310+1270 5060
Moving Average= = =1265
4 4
2. February–May:
1280+1310+ 1270+1190 5050
Moving Average= = =1262.5
4 4
3. March–June:
1310+1270+ 1190+1290 5060
Moving Average= = =1265
4 4
4. April–July:
1270+1190+1290+1410 5160
Moving Average= = =1290
4 4
5. May–August:
1190+1290+1410+1360 5250
Moving Average= = =1312.5
4 4
6. June–September:
1290+1410+ 1360+1430 5490
Moving Average= = =1372.5
4 4
7. July–October:
1410+1360+ 1430+1280 5480
Moving Average= = =1370
4 4
8. August–November:
1360+1430+ 1280+1410 5480
Moving Average= = =1370
4 4
9. September–December:
1430+1280+ 1410+1390 5510
Moving Average= = =1377.5
4 4

Question 2
To solve this, we will use exponential smoothing with the following
formula:
F t=α × At −1 + ( 1 −α ) × Ft −1

Where:
 F t = forecast for the current period

 At −1 = actual sales for the previous period

 F t −1 = forecast for the previous period

 α = smoothing constant (0.2 in this case)

We’ll start with January’s sales (1200) as the initial forecast, and apply
exponential smoothing to calculate the forecast for February onward.
Given:
 Smoothing constant (α ) = 0.2

 January sales = 1200

Forecast Calculations:
a) January:
Since January is the first month, the forecast is the same as the actual sales
value:
F Jan=1200 (given)

b) February:
Using the sales of January as the “actual” value, and the forecast for January
is 1200:
F Feb =0.2× A Jan + 0.8× F Jan=0.2 ×1200+ 0.8× 1200=1200

Question 3
1. The Regression Model
We assume a linear relationship between Sales and Advertising Expenditure
given by:
Y =a+b X
Where:
 Y is the dependent variable (Sales in N’m).

 X is the independent variable (Advertising Expenditure in ’000).

 a is the intercept.

 b is the slope.

2. Data
The observed data are summarized in the table below. (Note that all
products and squares are recalculated correctly.)

Ob Sales Advertising Expenditure


2
s. (N’m) (’000) X Y X ×Y X
1 8.5 210 210 8.5 210 ×8.5=1785 2102=44100
2 9.2 250 250 9.2 250 × 9.2=2300 2502=62500
3 7.9 290 290 7.9 290 ×7.9=2291 2902=84100
4 8.6 330 330 8.6 330 ×8.6=2838 3302=108900
5 9.4 370 370 9.4 370 ×9.4=3478 3702=136900
6 10.1 410 410 10. 410 × 10.1=4141410 2=168100
1
3. Preliminary Calculations
Sums and Count
$$ \begin{aligned} \sum X &= 210 + 250 + 290 + 330 + 370 + 410 =
1860,\$$
1mm] Y &= 8.5 + 9.2 + 7.9 + 8.6 + 9.4 + 10.1 = 53.7,$$1mm] (XY) &=
1785 + 2300 + 2291 + 2838 + 3478 + 4141 = 16833,$$1mm] (X^2) &=
44100 + 62500 + 84100 + 108900 + 136900 + 168100 = 604600,$$1mm]
n &= 6. \end{aligned}$$

4. Formulas for the Regression Coefficients


Slope (b )
n ∑( X Y )− (∑ X ) (∑Y )
b=
n ∑ ( X 2 ) − (∑ X )
2

Intercept (a )
∑Y − b∑ X
a=
n

5. Calculation of the Slope


Substitute the values into the slope formula:
6 ×16833 −1860 ×53.7
b ¿ 2
6 × 604600− ( 1860 )
1116
¿ ¿
168000
¿ ¿

6. Calculation of the Intercept


Substitute the computed slope into the intercept formula:
53.7− 0.00664 × 1860
a ¿
6
41.343
¿ ¿
6
¿ ¿
7. The Final Regression Equation
The best-fit regression equation is:
Y =6.89+0.00664 X .

You might also like