CH 4

MANAGERIAL ECONOMICS
CHAPTER FOUR
DEMAND AND DEMAND FORECASTING
By: Teklebirhan A. (Asst. Prof)
E-mail: [email protected]
1 AAU , 2024
4.1. Introduction
2
Business enterprise needs to know the demand for its product.

 Any business organization must know current demand for its
product in order to avoid underproduction or over production.
The current demand should be known for determining pricing
and promotion policies so that it is able to secure optimum sales
or maximum profit.
4.2. Demand Analysis and Forecasting
3
Unless and until knowing the demand for a product how can we
think of producing that product.
Therefore, demand analysis is something which is necessary for
the production function to happen.
Demand analysis helps in analyzing the various types of demand
which enables the manager to arrive at reasonable estimates of
demand for product of his company.
Managers not only assess the current demand but he has to take
into account the future demand also.
4.3. Demand Forecasting
4
Demand Forecasting refers to an estimate of future demand for

the product.
It is an objective assessment of the future course of demand.
Forecasting enables the manager to minimize the element of
future risk and uncertainty.
Accurate demand forecasting is essential for a firm
 to enable it to produce the required quantities at the right time
 to arrange well in advance for the various factors of production.
Therefore, forecasting helps the firm to assess the probable
demand for its products and plan its production accordingly.
4.4. Methods of Forecasting
5
4.4.1. Qualitative Forecasting
In some situation, forecasts rely solely on judgment and opinion to
make forecasts.
 If management must have a forecast quickly; there may not be
enough time to gather and analyze quantitative data.
 At other times, especially when political and economic
conditions are changing, available data may be obsolete and
more up to date information might not yet be available.
 Short term forecasting depends heavily on the qualitative
method.
Cont…..
6
Qualitative forecasting relies on one or more individuals to

generate forecasts without using mathematical models.
It is subjective in nature.
Some of the common qualitative methods of forecasting are:
1) Opinion Survey method/Sales- Force –Composite method/
collective opinion method.
 The company asks its salesmen to submit estimate for future sales
in their respective territories.
 This method is more useful and appropriate because the salesmen
are more knowledgeable about their territory.
Cont…..
7
2) Expert Opinion: Apart from salesmen and consumers,

distributors or outside experts may also be used for forecast.
3) Delphi Method: a panel is selected to give suggestions to solve
the problems in hand.
 Both internal & external experts can be the members of the panel.
 Panel members are kept apart from each other and express their
views in an anonymous manner. Here is an attempt to arrive at a
consensus in an uncertain area by questioning a group of experts
repeatedly until the responses appear to converge along a single
line.
Cont…..
8
4) Consumer Interview Method/Opinion Survey

Method/Direct Interview Method
 The most direct method of estimating the demand for a product in
the short-run is to interview the consumers and ask them what
quantity of a product they would be planning to buy at alternative
prices over a given period of time.
 This method is ideal and it gives firsthand information, but it is
costly and difficult to conduct.
4.4.2. Quantitative Forecasting Method
9
Quantitative forecasting method use mathematical models to

represent relationship among relevant variables based on
historical data or known relationship.
These consist of statistical or mathematical techniques which are
used to forecast the demand for a product in the long- period.
In opposite to qualitative approach, quantitative models are
objective in their very nature.
A) Trend projection method
10
This is also known as time series analysis.

 A firm that has been existence for long period will have
accumulated considerable data on sales pertaining to different
time periods. – the data is time series data.
Such data can be analyzed in order to establish the nature of
trends in sales over a period so that possible trend in future can be
inferred. The past trend is projected in order to interpret the
future trend.
A trend line can be fitted through a series of statistical techniques
such as the method of least square
Cont…..
11
The focus of time-series analysis is to identify the components of

change in the data
 A trend is a long-term increase or decrease in the variable.
 The seasonal component represents changes that occur at
regular intervals.
 Cyclical patterns is a sustained periods of high values followed
by low values.
 The remaining variation in a variable that does not follow any
discernable pattern is due to random fluctuations.
Cont…..
12
Changes in the variable due to random factors are not predictable.

The larger the random component of a time series, the less
accurate the forecasts based on those data.
ILLUSTRATION:
Suppose a manufacturer of transistors in Addis Ababa decides to
forecast the sales of his products during the next year by trend
projection method. He collects data on his sales for the past five
years as follows;
Cont…
Year
= = ,
1989 50 1 -12 -2 24 4 and
1990 60 2 -2 -1 2 1
= =
1991 55 3 -7 0 0 0
1992 70 4 8 1 8 1
1993 75 5 13 2 26 4
Sum 310 15 0 0 60 10
∑( − )( − ) ∑
= == = =
∑( − ) ∑
= − ∴ = − ( )=
Therefore, the fitted regression equation (i.e., OLS regression line) is:
= +
By: Teklebirhan A. 13
Cont…..
14
Using the equation, we can find out trend values for the previous
years and estimate the sales for 1994.
Y 1989 = 44 + 6 x (1) = 44 + 6 = 50
Y 1990 = 44 + 6 x (2) = 44 +12 = 56
Y 1991 = 44 + 6 x (3) = 44 + 18 =62
Y 1992 = 44 + 6 x (4) = 44 + 24 = 68
Y 1993 = 44 + 6 x (5) = 44 + 30 = 74
Y 1994 = 44 + 6 x (6) = 44 + 36 = 80
Thus, forecast sales for 1994 would be 80 thousand based on trend
projection equation.
B) Averaging Methods
15
These methods utilize historical data for calculating average of the

past demand.
This average is then used as a forecast.
Different ways of calculating an average for short range forecast
include the following given below;
i) Simple average method: in this method an average of past data
in which the demands of all previous periods are equally weighted,
is calculated.
Cont…..
16
Simple average =
Example: Demand of an item in a firm has been 180, 160, 170 and
190 items in each of the last four quarters. Forecast the demand of
this item for the current quarter based on simple average method?
Solution: Forecast for current quarter based on simple average
would be;
700
= =
4
Cont…..
17
ii) Simple moving average: it is a simple arithmetic average of a set

of observed values, from the present time period to a certain time
period in the past and then using that average as the forecast for
the immediate future.
 In this method number of past periods to be used in the
calculation are first decided and held constant. In this method
also, equal weight age is given to all the periods.
 To keep the number of periods constant, some old data are
discarded while new (present) values are added.
Cont…..
18
‘ ’
S =
Example: Demand for generating sets of a particular size in the

past six months, in a firm was as follows;
January 300
February 350
March 400
April 400
May 450
June 500
Forecast the demand for July, based on (i) 6 months moving

average (ii) 4 moving month’s average and (iii) 3 months moving
average?
Cont…..
19
300 + 350 + 400 + 400 + 450 + 500

6 months = = 400
6
400 + 400 + 450 + 500

4 months = = 437. 5
4
400 + 450 + 500

3 months = = 450
3
Cont…..
20
iii) Weighted moving average: This method incorporates some

weights of old demand. Greater weight is given to the more
recent data.
Weighted ‘n’ period moving average forecast for the period (t +1) =
sum of demand times a weighted factor over desired periods in the
moving average.
Example: From the monthly data given below, compute a
weighted three months moving average for July, where the weights
are 0.5 for the latest month, 0.3 weights and 0.2 for the other
months respectively.
Cont…..
21
Solution:
A three-month weighted moving average forecast for July;
= ( ) + ( ) + ( )
= (0.5 500) + (0.3 450) + (0.2 400)
= 250 + 135 + 80
=
C) Exponential Smoothing
22
The forecast can be based on the old calculated forecast and the
new data.
The weight given to latest actual demand is called a smoothing
constant and is represented by the Greek letter alpha (α).
It is always expressed as a decimal from 0 to 1.
 In general, the formula for calculating the new forecast is:
= ( )( ) + ( − )( )
Cont…..
23
Example: The old forecast for May was 220, and the actual
demand for May was 190. If alpha is 0.15, calculate the forecast for
June. If June demand turns out to be 218, calculate the forecast for
July.
Solutions:
= ( . )( ) + ( − . )( ) = .
= ( . )( ) + ( . )( . ) = .
Cont…..
24
As an alternate formula you can use the previous forecast plus a
percentage of the difference between that forecast and the actual
value of the series at that point.
Cont…..
25

CH 4

Uploaded by

Copyright:

Available Formats

CH 4

Uploaded by

Document Information

Original Description:

Original Title

Copyright

Available Formats

Share this document

Share or Embed Document

Sharing Options

Did you find this document useful?

Is this content inappropriate?

Copyright:

Available Formats

CH 4

Uploaded by

Copyright:

Available Formats

MANAGERIAL ECONOMICS

By: Teklebirhan A. (Asst. Prof)

Business enterprise needs to know the demand for its product.

Demand Forecasting refers to an estimate of future demand for

 Short term forecasting depends heavily on the qualitative

Qualitative forecasting relies on one or more individuals to

2) Expert Opinion: Apart from salesmen and consumers,

4) Consumer Interview Method/Opinion Survey

Quantitative forecasting method use mathematical models to

This is also known as time series analysis.

The focus of time-series analysis is to identify the components of

Changes in the variable due to random factors are not predictable.

These methods utilize historical data for calculating average of the

ii) Simple moving average: it is a simple arithmetic average of a set

Example: Demand for generating sets of a particular size in the

Forecast the demand for July, based on (i) 6 months moving

300 + 350 + 400 + 400 + 450 + 500

400 + 400 + 450 + 500

400 + 450 + 500

iii) Weighted moving average: This method incorporates some

You might also like