Chapter four

4. Demand and demand forecasting

4.1 Definition of Market Demand

The market demand of any product is the sum of individual demands for the product at a given
market price in a given time period. Note that the individual demand for the product per unit of
time at a given price is the quantity demanded by an individual.
A horizontal summation of individual demand schedule gives rise to the market demand
schedule. For example, assume three consumers, X, Y, and Z of a given commodity, say
commodity A. Let the individual demands by the consumers, X, Y, and Z be represented as in
table 4.1 below, the market demand schedule, that is, the aggregate of individual demands by the
three consumers at different prices, as indicated, is shown by the last column of the table.

4.2 Types of Demand

The types of demand encountered in business decisions are outlined below.
4.2.1. Individual and Market Demand.
The quantity of a commodity an individual is willing and able to purchase at a particular price,
during a specific time period, given his/her money income, his/her taste, and prices of other
commodities, such as substitutes and complements, is referred to as the individual demand for
the commodity. As illustrated in table above, the total quantity which all the consumers of the
commodity are willing and able to purchase at a given price per time unit, given their money
incomes, their tastes, and prices of other commodities, is referred to as the market demand for
the commodity.

Demand and Demand Forecasting Page 1

4.2.2. Demand for firm’s and Industry’s Product.
The quantity of a firm’s product that can be sold at a given price over time is known as the
demand for the firm’s product. The sum of demand for the products of all firms in the industry is
referred to as the market demand or industry demand for the product.
4.2.3 Autonomous and Derived Demand.
An autonomous demand or direct demand for a commodity is one that arises on its own out of a
natural desire to consume or possess a commodity. This type of demand is independent of the
demand for other commodities. Autonomous demand may also arise due to demonstration effect
of a rise in income, increase in population, and advertisement of new products.
The demand for a commodity which arises from the demand for other commodities, called
‘parent products’ is called derived demand. Demand for land, fertilizers and agricultural tools, is
a derived demand because these commodities are demanded due to demand for food. In addition,
demand for bricks, cement, and the like are derived demand from the demand for house and
other types of buildings. In general, demand for producer goods or industrial inputs are a derived
demand.
4.2.4. Short-term and Long-term Demand.
Short-term demand refers to the demand for goods over a short period. The type of goods
involved in the short-term demand are most fashion consumer goods, goods used seasonally,
inferior substitutes for superior goods during scarcities. Short term demand depends mainly on
the commodity price, price of their substitutes, current disposable income of the consumers, the
consumers’ ability to adjust their consumption pattern, and their susceptibility to advertisement
of new products.
The long-term demand refers to the demand which exists over a long period of time. Changes in
long-term demand occur only after a long period. Most generic goods have long-term demand.
The long-term demand depends on the long-term income trends, availability of better substitutes,
sales promotion, consumer credit facility, and the like.
4.3 Determinants of Market Demand
There are several factors affecting market demand for a product, the most important are:
1. Price of the product or the own price (Po). This is the most important determinant of demand
for a product. The own price of a product and the quantity demanded of it are inversely-related.

Demand and Demand Forecasting Page 2

2. Price of the related goods, such as substitutes and complements (Ps and Pc)
When two goods are substitutes for each other, the change in price of one affects the demand for
the other in the same direction. If goods X and Y are substitute goods, then an increase in the
price of X will give rise to an increase in the demand for Y. Note that changes in the price of
related goods cause shifts in the demand for the goods. Changes in demand are illustrated
graphically as rightward shifts (for increase) and leftward shifts (for decrease) in the demand for
the products. As shown below, An increase in the price of good X will shift the demand for good
Y to the right and shift that of good X to the left.
Figure 4.2.1 Shifts in Demand Px Py
px py

X Y

Symbolically, Dx = f(Py); ΔDx/ΔPy > 0

Dy = f(Px); ΔDy/ΔPx > 0
When two goods are complements for each other, one complements the use of another. Petrol
and car a complement goods. If an increase in the price of one good causes a decrease in demand
for the other, the goods are said to be complements. Thus if the demand function for a car (Dc) in
relation to petrol price (Pp) is specified by:
Dc f(Pp), ΔDc/ΔPp < 0.
3. Consumer’s Income This is the major determinant of demand for any product since the
purchasing power of the consumer is determined by the disposable income. Managers need to
know that income-demand relationship is of a more varied nature than those between demand
and its other determinants.
The relationships between demands for commodity X, for example, and the consumer’s income,
say Y, keeping other factors constant, can be expressed by a demand function:
Dx = f(Y), and ΔDx/ΔY > 0.
4. Consumers’ Tastes and Preferences Consumers’ tastes and preferences play important role in
the determination of the demand for a product. Tastes and preferences generally depend on life
style, social customs, religious values attached to a commodity, habit of the people, age and sex

Demand and Demand Forecasting Page 3

of the consumers, and the like. Changes in these factors tend to change consumers’ tastes and
preferences.
5. Advertisement Expenditures. Advertisement costs are incurred while attempting to promote
sales. It helps in increasing product demands in at least four ways:
(a) By informing the potential consumers about the product’s availability;
(b) By showing the product’s superiority over the rival product;
(c) By influencing consumer’s choice against the rival product; and,
(d) By setting new fashions and changing tastes. The impact of these causes upward shifts in the
demand for the product. All things being equal, as expenditure on advertisement increases, it is
expected that volume of sales will increase.
The relationship between sales (S) and advertisement outlays (AD) can be expressed by the
function: S = f(AD), and ΔS/ΔAD > 0. This relationship is indicated in figure below:
Figure 4.2.2 Advertisement and Sales

6. Consumers’ Expectations. The consumers’ expectations about the future product prices,
income, and supply position of goods play significant role in the determination of demand for
goods and services in the short run. A rational consumer who expects a high rise in the price of a
nonperishable commodity would buy more of it at the high current price with a view to avoiding
the pinch of the high price rise in the future. On the contrary, if a rational consumer expects a fall
in the price of goods he/she purchases, he/she would postpone the purchase of such goods with a
view to taking advantage of lower prices in the future. This is especially the case for nonessential
goods. This behaviour tends to reduce the current demand for goods whose prices are expected to
decrease in the future.

Demand and Demand Forecasting Page 4

An expected increase in income would similarly increase current demand for goods and services.
For instance, a corporate announcement of bonuses or upward revision of salary scales would
induce increases in current demand for goods and services.
7. Demonstration Effect. Whenever new commodities or models of commodities are introduced
in the market, many households buy them not because of their genuine need for them but
because their neighbours have purchased them. This type of purchase arises out of such feelings
jealousy, competition, and equality in the peer group, social inferiority, and the desire to raise
once social status. Purchases based on these factors are the result of what economists refer to as
‘demonstration effect’ or the ‘Band-Wagon effect’. These effects have positive impacts on
commodity demand.
On the contrary, when a commodity becomes a thing of common use, some rich people decrease
their consumption of such goods. This behaviour is referred to in economics as the ‘snob effect’.
This has negative impact on the demand for the commodity concerned.
4.3 The Demand functions
The various types of demand functions relevant to our discussions include:
1. The Linear Demand function;
2. The non-linear demand function; and,
3. The multivariate or dynamic demand function.
Each of these demand functions has specific roles to play in decision making involving the
demand for a firm’s product.
1 Linear Demand function
A demand function is said to be linear when its graph results in a straight line. The general form
of a linear demand function is presented in equation below:
Dx = a - bPx (4.3.1)
Where a = the demand intercept or the quantity demanded at a zero price, b= the slope of the
demand function or the rate at which quantity demanded of product X changes with respect to
the price (Px). This slope is defined by ΔDx/ΔPx
The graphical form of this demand function is illustrated in figure below.
Price
px Dx = a - bPx

Quantity (Dx)

Demand and Demand Forecasting Page 5

The price function can easily be obtained from the demand function (equation 4.1.1) in the
following way:

Dx = a – bPx
bPx = a – Dx
Px = a – Dx = a – 1Dx (4.3.2)
b b b

2 Nonlinear Demand Function

A demand function is said to be nonlinear or curvilinear when the slope of the demand function,
ΔP/ΔD, changes along the demand curve. A nonlinear demand function yields a demand curve
unlike the demand line yielded by a linear demand function as in figure 4.3.1 above. A nonlinear
demand function is of the form of a power function as given in equation (4.3.3) below.
Dx = aPx -b (4.3.3)
You should note that the exponent of the Price variable P x, that is, -b, in the nonlinear demand
function (equation (4.3.3) is referred to as the price-elasticity of demand. The nonlinear demand
function can be sketched as in figure 4.3.1 below
Figure 4.3.1: Nonlinear Demand Function

3 Multi-Variate or Dynamic Demand Function

The demand functions discussed above are classified as single-variable demand functions, and,
as such, referred to as short-term demand functions. In the long run, neither the individual nor
the market demand for a given product is determined by anyone of its determinants alone,

Demand and Demand Forecasting Page 6

because other determinants do not remain constant. The long run demand for a product depends
on the composite impact of all its determinants operating simultaneously. It follows that in order
to estimate the long-term demand for a product, all the relevant determinants must be taken into
account.
The long-run demand functions describe the relationship between a demand for a product (the
dependent variable) and its determinants (the independent variables). Demand functions of this
type are referred to as multi-variate or dynamic demand functions.
Consider the demand for product X, (D x), which depends on such variables as its own price (P x),
consumer’s income (Y), price of its substitutes (P s), price of the complementary goods (P c),
consumer’s taste (T), and advertisement expenditure (A), the functional form can be written as:
Dx = f(Px, Y, Ps, Pc, T, A) (4.3.4)
If the relationship between the demand (D x) and the quantifiable independent variables, P x, Y, Ps,
Pc, and A, is of a linear form, then the estimable form of the demand function is formulated as:
Dx = a + bPx + cY + dPs + ePc + gA (4.3.5)
Where ‘a’ is a constant and parameters b, c, d, e. and g are the coefficients of relationship
between the demand for product X (Dx) and the respective independent variables.
4.4 ELASTICITY OF DEMAND
4.4 .1 Own –Price Elasticity of Demand
The own-price elasticity of demand is generally defined as the degree of responsiveness of
demand for a commodity to changes in its own price. More precisely, it is the percentage change
in quantity demanded as a result of one percent change in the price of the commodity. The
working definition is as follows:
ep = Percentage change in quantity demanded (Q)
Percentage change in price (P)
where ep stands for own-price elasticity.
From this definition, a general formula for the calculation of the coefficient of own-price
elasticity is derived as follows: ep = ΔQ ÷ ΔP = ΔQ x P = ΔQ x P
Q P QΔP ΔP Q
Where Q = original quantity demand, P = original price, ΔQ = change in quantity demanded
(new quantity – original quantity), ΔP = change in price (new price – original price).

Demand and Demand Forecasting Page 7

Note that since the term, ΔQ/ΔP is the slope of the demand function, a minus sign (-) is generally
inserted in the formula before the fraction with a view to making the elasticity coefficient a non-
negative value.
The own-price elasticity can be measured between two points on a demand curve (for arc
elasticity) or on a point (for point elasticity).
4.4.1.1 Arc Elasticity
An arc elasticity measures the elasticity of demand between any two finite points on a given
demand line or curve. Measure of elasticity between points A and B in figure below, for
example, is referred to as arc elasticity. Movement from point A to B indicates a fall in the
commodity price from say, N10/unit to N8/unit, so that ΔP = N(10 – 8) = N2. The decrease in
price is assumed to cause an increase in quantity demanded from say, 50 to 60 units, so that ΔQ
= 50 – 60 = -10 units. The elasticity from A to B can be computed by substituting these values
into the elasticity formula to get:
ep = -ΔQ/ΔP . Po/Qo (Po = original price; Qo = original quantity)
= -10/2 x 10/50 = -1 (the case of unitary elasticity)
The elasticity of 1 (unitary elasticity) implies that 1 percent decrease in price of the commodity
results in 1 percent increase in quantity demanded
Figure 4.4.1.1: Arc Elasticity for a Linear Demand Function

Px
30
20
10 A
8 B
5
0 10 20 30 40 50 60 70 Qx
4.4.1.2 Point Elasticity

Demand and Demand Forecasting Page 8

Point elasticity is the elasticity of demand at a finite point on a demand line or a demand curve.
For example, at the point C or D on the linear demand line, MN, of figure 4.4.1.2 you will
calculate the point elasticity. This is not the same as the arc elasticity between points C and D.
Figure 4.4.1.2: Point Elasticity for a Linear Demand Function

A movement from point D towards C would imply change in Price (ΔP) becoming smaller and
smaller, such that point C is almost approached. At this point, the change in price is
infinitesimally small. The measurement of elasticity for an infinitesimally small change in price
is same as measurement of elasticity at a point. Point elasticity I measured by the following
formula:
Point elasticity (ep) = (P/Q)(dQ/dP)
The derivative, dQ/dP, is reciprocal of the slope of the demand line or demand curve, that is,
1/dP/dQ.
4.4.2: Cross-Elasticity of Demand
The cross-elasticity (or cross-price elasticity) can be defined as the degree of responsiveness of
demand for a commodity to the changes in price of its substitutes and complementary goods. The
formula for measuring the cross-elasticity of demand for a commodity, X, can be written as:
Ex,i = Percentage change in quantity demanded of X (Qx)
Percentage change in the price of i (Pi)
= Pi. ΔQx
Qx ΔPi
Where i refers to either substitutes to commodity X or its complementary goods.

Demand and Demand Forecasting Page 9

The cross-elasticity of demand can be used to identify substitute and complementary goods for a
given commodity. If the cross-price elasticity between two goods is positive, the two goods may
be considered as substitutes to one another. The greater the cross price elasticity coefficient, the
closer the substitute. Similarly, if the cross-price elasticity is negative, the two goods may be
considered as complements. The higher the negative cross-elasticity coefficient, the higher the
degree of complementarily.
The concept of cross-elasticity is important in pricing decisions. If the cross-elasticity in
response to the price of substitutes is greater than 1, it would not be advisable to increase the
price. Reducing the price, instead may prove beneficial. If the price of the complementary good
is rising, it would be beneficial to reduce the price of the commodity.
4.5 DEMAND FORECASTING
4.5.1 Demand Forecasting Techniques
There are many techniques employed in demand forecasting, but of most important in our
discussions are the Survey and Statistical methods.
4.5.1.1 The Survey Techniques
Survey techniques are used where the purpose is to make short-run demand forecasts. This
technique uses consumer surveys to collect information about their intentions and future
purchase plans. It involves:
(i) Survey of potential consumers to elicit information on their intentions and plans;
(ii) Opinion polling of experts, that is, opinion survey of market experts and sales
representatives;
The methods used in conducting the survey of consumers and experts include:
i. Consumer Survey Techniques - The rationale for forecasting based on surveys of economic

intentions is that many economic decisions are made well in advance of actual expenditures.

For example, businesses usually plan to add to plant and equipment long before expenditures

are actually incurred. Consumers’ decisions to purchase houses, automobiles, TV sets,

washing machines, furniture, vacations, education, and other major consumption items are

made months or years in advance of actual purchases. Similarly, government agencies prepare

budgets and anticipate expenditures a year or more in advance. Surveys of economic

Demand and Demand Forecasting Page 10

 intentions, thus, can reveal and can be used to forecast future purchases of capital equipment,

inventory changes, and major consumer expenditures.

ii. Experts opinion-The most basic form of qualitative analysis forecasting is personal insight, in

which an informed individual uses personal or company experience as a basis for developing

future expectations. Although this approach is subjective, the reasoned judgment of informed

individuals often provides valuable insight. When the informed opinion of several individuals

is relied on, the approach is called forecasting through panel consensus. The panel consensus

method assumes that several experts can arrive at forecasts that are superior to those that

individuals generate.

Direct interaction among experts can help ensure that resulting forecasts embody all available

objective and subjective information. Although the panel consensus method often results in

forecasts that embody the collective wisdom of consulted experts, it can be unfavorably

affected by the forceful personality of one or a few key individuals. A related approach, the

Delphi method, has been developed to counter this disadvantage. In the Delphi method,

members of a panel of experts individually receive a series of questions relating to the

underlying forecasting problem. Responses are analyzed by an independent party, who then

tries to elicit a consensus opinion by providing feedback to panel members in a manner that

prevents direct identification of individual positions. This method helps limit the steamroller

or bandwagon problems of the basic panel consensus approach.

iii.Test marketing or controlled experimentation

Firms resort to test marketing while launching a new product or likely to change the design or

model of the existing products. This is also known as controlled experimentation method as

the product is likely to be launched in a segmented market to identity its demand potential.

Demand and Demand Forecasting Page 11

 The essential prerequisites of test marketing are that the product price, its design, quality,

level of advertisement and sales promotion campaign should be equal in promotion to that of

what the firm is likely to incur had it been released in the national market. Test marketing

should be continued until the repurchase cycle commences. The geographical, economic,

sociological and even the demographic features of the test marketing region should represent

all the features of the national market.

Test marketing can be under taken in a single market or different markets with different

features of the product. Test marketing will no doubt be useful method as it ventilates the

consumer preferences and facilitates the model or design changes if necessary but at the same

time, it is an expensive proposition. The forecasted sales in the test marketing area should not

be taken on their face values.

iv.End-use or input-output method

The end-use method applies for forecasting the demand for intermediate products. These are

products used in the manufacture of some other final goods. The demand for the final product

is an indicator of the demand for intermediate product, subject to the availability of the input

output coefficients. Once the demand for the final goods estimated, the demand for the

intermediate product can be easily arrived at using the input-output coefficients. The major

problem of using this method is that one product is an intermediate product for producing not

one commodity but several other commodities as in the case of iron and steel. In such cases,

the input-output coefficient in all the uses and the estimated demand for all those products

should be available, failing which the demand forecasts become useless.

4.5.1.2 Statistical Techniques

The statistical techniques of demand forecasting use historical (or time-series), and cross section
data for estimating long-term demand for a product.
1. The Econometric Techniques.

Demand and Demand Forecasting Page 12

The Econometric techniques include: (i) Regression method; and, (ii) Simultaneous Equation
method.

A. The Regression Method.

Regression analysis is found to be the most popular method of demand estimation and/or
forecasting. It combines economic theory and statistical techniques of estimation. The economic
theory specifies the determinants of demand and the nature of the relationship between the
demand for a product and its determinants. It helps in ascertaining the general form of demand
function. Statistical techniques on the other hand are employed in estimating the values of the
parameters in the estimated equation.
In regression models, the quantity to be forecast in the demand function is the dependent
variable, and the determinants of demand are the independent or explanatory variables.
In specifying the demand functions for various commodities, the forecaster may come across
many commodities whose demand depends, at large, on a single independent variable. For
instance, suppose the demand for sugar in a given geographical area is found to depend largely
on the population, then the demand function for sugar will be referred to as a single-variable
demand function. But if it is found that demand functions for fruits and vegetables depend on a
number of variables such as, their own-prices, substitutes, household income, population, and the
like, then such demand functions are referred to as multi-variable demand functions. The single
regression equation is used for single-variable demand functions, while the multi-variable
equation is used for multivariable demand functions. The single-variable and multi-variable
regressions are outlined below.
The Simple or Bivariate Regression Technique
As mentioned earlier, in a simple regression technique, a single independent variable is used in
estimating the statistical value of the dependent variable or the variable to be forecast. This
technique is similar to trend fitting, though, in trend fitting, the independent variable is time, t,
while in the case of simple regression, and the chosen independent variable is the single most
important determinant of demand.
Suppose we want to forecast the demand for sugar, for example, for particular periods on the
basis of some past data, we would estimate the regression equation of the form:
Y = a + bX ( 4.5.1)

Demand and Demand Forecasting Page 13

where Y represents the quantity of sugar to be demanded; and, X represents the single variable,
population, and a and b are constants.
The parameters a and b can be estimated, using the past data, by solving the following
corresponding linear questions for a and b:
ΣYi = na + bΣXi (4.5.2)
ΣXiYi = aΣXi + bXi2 (4.5.3)
The procedures for calculating the terms in equations (4.5.2) and (4.5.3) can be illustrated by the
following example. Consider the following hypothetical past data on the demand for sugar for
the years 2000 to 2006:
Table 4.5.1 Demand for Sugar
Year Population Quantity of sugar demanded (millions) (000’s)
2000 10 40
2001 12 50
2002 15 60
2003 20 70
2004 25 80
2005 30 90
2006 40 100
Using this hypothetical data, we can calculate the terms as shown in table 3.1.2 below:

Table 4.5.2 Calculation of Terms of the Linear Equations in Simple Regression

Demand and Demand Forecasting Page 14

Substituting the related values from table 4.5.2 into equations (4.5.2) and (4.5.3), we get:
490 = 7a + 152b (4.5.4)
12000 = 152a + 3994b (4.5.5)

 Solving simultaneously for a and b in the above equations, we obtain:

 a = 27.44; b = 1.96. substituting these values into the regression equation the estimated
regression equation becomes:
Y = 27.44 + 1.96X
Suppose the population for the year 2008 is projected to be 100 million then the demand for
sugar, according to our example, would be estimated using the regression equation as:
Y = 27.44 + 1.96(100) = 27.44 + 1960 = 223,440 units.
The Multi-Variate Regression Technique
The technique is used in cases where the demand for a commodity is determined to be a function
of many independent variables, or where the explanatory variables are greater than one.
The procedure of multiple regression analysis involves the following steps:
 Step One: Specification of the independent or explanatory variables,
 Step Two: Collection of time-series data on the independent variable.
 Step Three: Specification of the Regression Equation.
The final step is to employ the necessary statistical technique in estimating the parameters of the
regression equation.
Some common forms of multi-variate demand functions are as follows:
1. The Linear Function. The linear demand function is where the relationship between the
demand and its determinants is formulated by a straight line. The most common type of this
equation is of the form:
Qx = α – bPx + cY + dPs + JA
where Qx = quantity demanded of commodity X; Px = unit price of commodity X; Y =
consumer’s income; Ps = price of substitute good; A = advertisement expenditure; α is a constant
(or the demand intercept), and b, c, d, and j are the parameters (or regression coefficients)
expressing the relationship between demand and Px, Y, Ps, and A, respectively.
2. The Power Function.
The power form of the demand function is given by:
 Qx = αPx bYcPs dAj

Demand and Demand Forecasting Page 15

The algebraic form of multiplicative demand function can be transformed into a log linear form
for simplicity in estimation as follows:
Log Qx = log α – b log Px + c log Y + d log Ps + j log A

B. The Simultaneous Equations Method

 This method of demand forecasting involves the estimation of several simultaneous
equations.
The following example illustrates the simultaneous equation method. A simple macroeconomic
model is given below:
Yt = Ct + It + Gt + Xt
 where, Yt = Gross National Product (GNP)
Ct = Total consumption expenditure
It = Gross Private Investment
Gt = Government expenditure
Xt = Net Export (X – M), where X represents Export, and M, Import.
Subscript t represents a given time unit.

Demand and Demand Forecasting Page 16