Professional Documents
Culture Documents
WHAT IS FORECASTING?
It is the process of estimation in unknown situations.
Prediction is similar, but in a more general term.
Trend Consumer
Projections Market Survey
MOVING AVERAGES
Moving Average is a series of arithmetic means
Used if little or no trend
Used often for smoothing
Provides overall impression of data over
time
Formula:
Period Supply
1 35
2 50 Compute for a
four-month
3 65
weighted
4 55 moving average
5 70 using the data
given.
6 75
EX. 2 FOUR-MONTH AVERAGE FORECAST
Period Supply Weights Applied
Forecast Period
4 Last month
1 35 3 2-Months ago
2 50 2 3-Months ago
3 65 1 4-Months ago
10 Sum of Weights
4 55
5 70 [(55 x 4) + (65 x 3) + (50 x 2) + 35] / 10 = 55
Last Period’s
New forecast = 142 + 0.20 ( 153 – 142)
Forecast = 142
= 142 + 0.20 ( 11 )
units
= 142 + 2.2
Last Period’s
= 144. 2 ≈ 144 Cars
Actual Demand
Therefore, the demand forecast for the = 153 units
Mitsubishi “Montero” in March is 144 cars.
α = 0.20
Use exponential smoothing to compute for a series of
forecast
Period Demand
1 20
2 35
a. α = 0.20;
3 46
b. α = 0.50 and
4 40
c. plot the
5 50 actual data
6 55 and both sets
7 45 on a single
8 graph
α = 0.20
Period Actual Forecast Error
Demand
1 20 - Formulas:
Forecast error tells us
2 35 20 15
how wellNew
the forecast
methods = areLast
3 46 23 23 performed against
period’s forecast +
themselves using past
4 40 27.60 13.60 α (Last
data.
period’s
actual demand – Last
5 50 30.08 19.92 period’s forecast)
6 55 34.06 20.94 Forecast Error =
7 45 38.25 6.75 Actual Demand -
Forecast
8 39.60
α = 0.50
Period Actual Forecast Error
Demand
1 20 - Formulas:
50
40
DEMAND
30 Actual Demand
α = 0.20
20 α = 0.50
10
0
1 2 3 4 5 6 7 8
PERIOD
REGRESSION ANALYSIS
It is a statistical technique used to develop
a mathematical equation showing how
variables are related. It is a forecasting
procedure that uses the least squares
approach or more independent variables
to develop a forecasting method.
REGRESSION ANALYSIS
Formula: The dependent variable Ŷ is the item
we are trying to forecast, while the
Ŷ = a + bX
Where: independent variable (X) is an item
Ŷ = value of dependent variable
that might have a causal effect on the
a = Y-axis intercept dependent variable.
b = slope of the regression line
X = independent variable
n(∑XY) – (∑X)(∑Y)
b =
n(∑X²) – (∑X)²
Where: X = mean of X Ȳ = mean of Y
n = number of observations, or years
Maxus Sales Corporation is in the business of
selling laptops. They realized the advantages of
forecasting very early in their business. They also
realized that in order to perform effective forecast,
they need to keep track of their current and past sales
numbers.
Currently, they are in the process of forecasting
their sales numbers of each quarter of the coming year.
In order to do this, they have pulled up their sales
numbers for the last 8 quarters. These numbers are as
follows:
X Y
Quarter Sales
1 600
2 1550
3 1500
4 1500 n = 8 quarters
5 2400
6 3100
7 2600
8 2900
Find the X² and XY of each row.
Quarter Sales
X² XY n = 8 quarters
X Y
1 600 1 600
2 1550 4 3,100
3 1500 9 4,500
4 1500 16 6,000
5 2400 25 12,000
6 3100 36 18,600
7 2600 49 18,200
8 2900 64 23,200
∑X ∑Y ∑X² ∑XY
Find the summation of each column.
Quarter Sales
X² XY n = 8 quarters
X Y
1 600 1 600
2 1550 4 3,100
3 1500 9 4,500
4 1500 16 6,000
5 2400 25 12,000
6 3100 36 18,600
7 2600 49 18,200
8 2900 64 23,200
∑X∑X
= 36 ∑Y =∑Y 16,150 ∑X²∑X²= 204 ∑XY =
∑XY
86,200
Use the given data and formula to compute for
the mean of X and Y( and Ȳ).
Given:
∑X = 36 ∑Y = 16,150 ∑X² = 204 ∑XY = 86,200
n = 8 quarters
Formula:
36 16,150
Ȳ = ∑X
X = X =
8 𝐧
8
∑Y
Ȳ =
X = 4.5 Ȳ = 2,018.75 𝐧
Use the given data and formula to compute for
the b(slope of the regression line).
Given:
∑X = 36 ∑Y = 16,150 ∑X² = 204 ∑XY = 86,200
a = 569.66
Form the estimated regression equation.
Given:
n(∑XY) – (∑X)(∑Y)
b= a = Ȳ – bX
n(∑X²) – (∑X)²
8(86,200) – (36)(16,150)
a = 2,018.75 – (322.02)(4.5)
b =
8(204) – (36) ²
Formula:
b= 322.02 a = 569.66
Ŷ = a + bX
15 8
17 9 n = 5 stores
21 13
18 10
19 11
Find the X² and XY of each row.
Sales Profit
X² XY
X Y
15 8 225 120
17 9 289 153
21 13 441 273
18 10 324 180
19 11 361 209
∑X ∑Y ∑X² ∑XY
n = 5 stores
Find the summation of each column.
Sales Profit
X² XY
X Y
15 8 225 120
17 9 289 153
21 13 441 273
18 10 324 180
19 11 361 209
∑X∑X
= 90 ∑Y∑Y
= 51 ∑X² ∑X²
= 1,640 ∑XY∑XY
= 935
n = 5 stores
Use the given data and formula to compute for
the mean of X and Y( and Ȳ).
Given:
∑X = 90 ∑Y = 51 ∑X² = 1,640 ∑XY = 935
n = 5 stores
51 Formula:
90
X = Ȳ = ∑X
5 5 X =
𝐧
∑Y
X = 18 Ȳ = 10.20 Ȳ =
𝐧
Use the given data and formula to compute for
the b(slope of the regression line).
Given:
∑X = 90 ∑Y = 51 ∑X² = 1,640 ∑XY = 935
n = 5 stores X = 18 Ȳ = 10.20
a = -5.10
Form the estimated regression equation.
Given:
n(∑XY) – (∑X)(∑Y)
b= a = Ȳ – bX
n(∑X²) – (∑X)²
5(935) – (90)(51)
b = a = 10.20 – (0.85)(18)
5(1,640) – (90) ²
Formula:
b= 0.85 a = -5.10
Ŷ = a + bX
Profit Ŷ==-5.10
-5.10++0.85(Sales)
0.85X
Predict profit for a store assuming
sales of ₱30 million.