Unit – 2

Demand forecasting
 Demand forecasting
 Demand forecasting is estimating future demand for the product.
 Methods of demand forecasting
I. Opinion polling / Survey method
 It is one of the most common and direct methods of forecasting
demand in the short term.
 In this method, an organization conducts surveys with
consumers/dealers to determine the future demand for their
products.
1. Opinion survey method
 It is known as sales-force-composite method or collective opinion method.
 Forecasting is done by getting the opinion of salesmen.
Advantages
 It is simple.
 It requires minimum statistical work.
 It is economical (less costly).
Disadvantages
 Highly subjective (more personal opinion)
2. Expert opinion
 Opinion from dealers or distributors
 E.g. Automobile companies
Advantages
 Quick and cheap forecasts
 Useful for new products
Disadvantage
 Subjective
3. Consumers’ interview method
 Direct interview with the consumers (about their
preferences)
Advantage
 First hand information
Disadvantage
 Costly and difficult
Consumers interview is done in 3 ways:
i. Complete enumeration method
 All the consumers are interviewed.
 Advantage
o First hand information
 Disadvantage
o Costly and difficult
ii. Sample survey method
 A sample of consumers are selected for the interview
 It is easy, less costly and highly useful.
iii. End-use method
 Demand for textile machinery = f(expansion of textile industry)
II. Statistical methods
 It is used for long-run forecasting.
 Statistical and mathematical techniques are used to forecast
demand.
 This method relies on past data.
1. Trend projection method
 It is concerned with the movement of variables through time.
 It requires long time – series data.
Year Sales (in 000s)

2011 53

2012 49

2013 61

2014 42

2015 59
 This method is based on the assumption that the factors liable for
the past trends in the variables shall continue to play their role in
future in the same manner and to the same extent.
 Eg: Set of factors affecting sales will affect sales in future.
 Trend projection method includes 3 techniques based on time-series
data. These are:
(a) Graphical method
(b) Fitting trend equation or least square method
(c) Box-Jenkins method
(a) Graphical method
  It is the most simple statistical method in which the annual sales
data are plotted on a graph, and a line is drawn through these
plotted points. 
 Under this method, it is assumed that future sales will assume the
same trend as followed by the past sales records.
 Although the graphical method is simple and inexpensive, it is not
considered to be reliable.
(b) Fitting trend equation or least square method
 The least square method is a technique in which the trend-line is
fitted in the time-series using the statistical data to determine the
trend of demand.
 The form of trend equation that can be fitted to the time-series
data can be determined by plotting the sales data.
The most common types of trend equations are:
• Linear Trend: When the time-series data reveals a rising or a linear trend in
sales, the following straight line equation is fitted:
y=a+bx
Where ‘y’ is sales; ‘a’ is intercept / constant, ‘b’ is slope or it shows the
impact of the independent variable on dependent variable, ‘x’ is time or
years, ‘y’ is dependent variable and ‘x’ is independent variable.
• Exponential Trend: It is used when the data reveal that the total sales have
increased over the past years either at an increasing rate or at a constant
rate.
(c) Box-Jenkins method
 It is used for short-term predictions and projections.
 Box-Jenkins method is used when the time-series data reveal
monthly or seasonal variations that reappear with some degree of
regularity.
2. Barometric technique
 In this method, estimation of time-series is done through certain
indicators to predict the future.
 There are 3 types of indicators: They are:
(a) Leading indicators
(b) Coincident indicators
(c) Lagging indicators
(a) Leading indicators
 Leading indicators are statistics that precedes economic events.
 An event that has already happened is used to predict the future
event.
 The already happened event would act as a leading indicator.
 Eg: Fresh orders for consumer goods, capital goods etc. 
(b) Coincident indicators
 It is an indicator that changes simultaneously with general economic
conditions and therefore reflects the current status of the economy.
 Coincident indicator provides information on the current state of the
economy.
 It does not show which way the economy is heading, but where it is at
present.
 Eg: Personal income is a coincident indicator of economic health.
(c) Lagging indicators
 These indicators can only be known after the event.
 Lagging indicators confirm long-term trends, but they do not
predict them.
 Eg: Unemployment rate
 Econometric methods of demand forecasting
 The econometric  methods make use of statistical tools and
economic theories in combination to estimate the economic
variables.
 The econometric model can either be a single-equation regression
model or a system of simultaneous equations.
 The econometric methods are:
(i) Regression method
(ii) Simultaneous equation model
(i) Regression
 Regression analysis is about how one variable affects another.
 It focuses on the relationship between a dependent variable and one or more
independent variables (or 'predictors').
 It is a statistical approach to forecast change in a dependent variable due to
change in one or more independent variables.
 It shows the extent of relationship between variables; i.e., how the value of
the dependent variable changes when one of the independent variable is
varied, while other independent variables are fixed.
 Eg: D=f(P); extent of relation i.e., 98% or 39%
 In the above equation, there is only 1 independent variable ie., P
 If D=f(P,Y,PR, W) – There are several independent variables i.e.,
P,Y,PR,W etc.
 Identifying the functional relationship with 1 independent variable is
simple regression; and with several independent variables is known
as multiple regression.
(ii) Simultaneous equation method
 Simultaneous equation is a set of equations where a variable
appears as independent and dependent variable.
 Eg: D=f(P) ------- (1)
P=f(D) ------- (2)
 Supply
 Supply means the commodity offered for sale at a price (by retailers
and wholesalers) during some given period; say a month or week or
3 months or 6 months, etc.
 ↑Price ↑Supply (Direct relation)
 Factors determining supply
1. Number of firms or sellers
2. State of technology
3. Cost of production
4. Prices of related goods
5. Price expectations
6. Natural factors
7. Labour trouble
8. Change in government policy
 Law of supply
 The law of supply states that, “Other things being constant, the
price of a commodity has a direct influence on the quantity
supplied. As the price of a commodity rises, its supply is extended;
as the price falls, its supply is contracted”.
Supply=f(Price) ; ↑Price↑Supply ; ↓Price↓Supply
 There is a direct relation between price and supply.
 Other factors are assumed to be constant.
Supply schedule
 Market price determination
 Market price is determined at a point where demand and supply are
equal.
 Market price is determined by the aggregate demand and aggregate
supply.
 The equilibrium price is determined where D=S.
Market price determination
 At equilibrium price, both the buyers and sellers
are satisfied (because D=S).
o If price is higher than the equilibrium price;
S>D (↑P; sellers bring down the prices to
dispose the excess stock. Ultimately, the
price reaches the equilibrium).
o If price is less than the equilibrium price;
D>S (↓P; buyers bid up the prices to get the
product. When buyers bid up the price, the
price reaches the equilibrium).
 Consumer’s Surplus
 In the words of Marshall, “The excess of the price which he would be
willing to pay rather than go without the thing, over that which he
actually does pay, is the economic measure of the surplus satisfaction.
It may be called “consumer’s surplus”.
 The price which a consumer pays for a commodity is always less than
what he is willing to pay for it, so that the satisfaction which he gets
from its purchase is more than the price paid for it and thus he derives
a surplus satisfaction which Marshall calls Consumer’s Surplus.
 Examples: Match box, salt, newspapers, postcard
 To illustrate, let us suppose that a consumer is willing to buy 1 orange if its
price were Re 1, 2 oranges if the price were 75 paise, 3 oranges at 50 paise and
4 oranges if it were 25 paise. Suppose the market price is 25 paise per orange.
At this price, the consumer will buy 4 oranges and enjoy a surplus of Rs 1.50
(.75 + .50 + .25).
 The consumer’s surplus can also be defined as the difference between what a
consumer is willing to pay for a commodity and what he actually does pay for
it. Our hypothetical consumer is prepared to pay Rs. 2.50 (= 1.00+.75+.50+ .25)
for four oranges but actually pays Re 1, and therefore derives a surplus of Rs.
1.50 (Rs 2.50-1.00).
 Consumer’s surplus is represented diagrammatically
where DD1 is the demand curve for the commodity. If
OP is the price, OQ units of the commodity are
purchased and the price paid is OP x OQ = area
OQRP. But the total amount of money he is prepared
to pay (total utility) for OQ units are OQRD.
 Therefore, CS = OQRD — OQRP = DRP. If the price of
the commodity falls to OP1 the consumer’s surplus
increases to DR1P1 and conversely a rise in price
would diminish it. In other words, consumer’s
surplus is the area between the demand curve (DD1)
and the price line (PR or P1R1) and is equal to the
triangle that is formed under the demand curve.
 Criticism of Consumer’s Surplus
 Utility is not measurable.
 A consumer does not pay more than the actual price.
 Not possible to know the prices consumer is willing to pay.
Thank You