Demand Estimation

Meaning of demand estimation / forecasting

Demand estimation means forecasting is the method or technique of estimating its demand in the future.
According to Evan J. Douglas “Demand forecasting will be taken to mean the process of finding the
values for demand in future time periods.”
Objectives /Purposes / Role / Contribution / Importance of demand estimation or forecasting
The main purposes or objectives of demand forecasting are as follows:
1. To make appropriate production policy
If a firm is able to do demand forecasting effectively, then it can decide easily how much to
produce to avoid the situations of over production or under production.
2. To make proper management of inventories
When a firm is able to do demand forecasting, then it can adjust its inventories levels (maximum
level, minimum level, re-order level, buffer stock etc.) easily. It reduces carrying or holding cost
and increases the efficiency.
3. To make appropriate sales policy
Once demand is estimated, then firm is able to observe the change in demand structure and
competition in the market over a period of time. On the basis of this, the firm can formulate a
suitable sales policy to tackle with the changing demand structure and competition.
4. To estimate financial requirements
Sales/turonver is the biggest source of revenue for any firm. If a firm can estimate the demand for
its product, then it can estimate its sales also. After estimating sales, the firm can calculate how
much finance or money is required from other sources like bank loans, debentures etc.
5. Arranging manpower
We know that labour is required to produce goods and services. If demand estimation can help in
deciding how much to produce, then accordingly we can decide how much manpower is required.
It will keep the labour cost at its optimum level.
6. Planning for new opportunities.
Today’s world is dynamic. If a firm finds that the demand structure has changed or competition
has evolved significantly over a long period of time, then it can think about new opportunities or
product lines/projects. If the changes are found to be favourable, then it can think about the
expansion of the product line etc.
Techniques/Methods of demand estimation/forecasting
There two categories of the techniques of demand estimation which are as follows:
1. Opinion Poll Technique
2. Statistical Technique

Opinion Poll Technique

It includes the following techniques:

a. Consumer Survey Technique

Under this technique, the agents of the firm approach to the consumers personally and seek the
information regarding their views about the product concerned, how much quantity they are
going to buy at a particular price in a given period of time and so on. In this regard, sample
survey or census can be made.
b. Collective Opinion Technique / Sales Force Opinion Method
Under this technique, the opinions of the salesmen are sought about what they think what
quantity the consumers are going to buy at a particular price in a given period of price. Salesmen
are the most suitable persons in this regard because they are in close contact to the consumers and
they understand the expectations/mood of their consumers well.
c. Expert Opinion Technique / Delphi Technique
Under this technique, the opinions of the experts are sought. In “Delphi Technique” two or more
panels of experts are created and the estimations of various panels are exchanged among the
panels without disclosing the identities of the panels. One panel may agree or disagree to the
opinion of the other panels. In case one panel, say, A disagrees to the estimations of another panel
say, B, the estimations are brought back to panel B either to revise the estimation or to seek the
reasons of disagreement. The process of exchanging the estimations are generally repeated 3 or 4
times but it may be continued unless some sort of unanimity is arrived at.
Statistical Techniques
Under statistical technique the tools of statistics are used. The main tools are as follows:

1. Time Series Analysis

A time series a table that shows the values of a variable like sales, production, etc. at different
points of time. If we have a time series, then we are able to estimate the value of the concerned
variable at the desired point of time using the following methods:

a. Graphical method
Under this method, the actual values of the variable under study are plotted on a graph paper
and a straight line, known as trend line, is drawn using free hand technique or semi
average method. The trend line may be upward sloping as well as downward sloping. This is
the simplest technique.

b. Least Square method

Least square method is a scientific method of fitting or drawing a trend line. If X and Y are
two variables such that Y is dependent on X, a trend line is defined as follows:

Y =a+bX
To calculate the values of a & b we use the following two equations:

a=
∑Y
N
And

b=
∑ XY
∑ X2

Example:
Below are given the figures of sales of a sugar:
Years 2002 2003 2004 2005 2006 2007 2008
Sales 80 90 92 83 94 99 92
You are required to calculate the following
i. A trend line.
ii. Estimate the sales of 2010

Solution
i.

Year Sales (Y) X X2 XY

2002 80 -3 9 -240
2003 90 -2 4 -180
2004 92 -1 1 -92
2005 83 0 0 0
2006 94 1 1 94
2007 99 2 4 198
2008 92 3 9 276

∑ Y =¿ ¿63 ∑ X=¿ ¿0 ∑ X =¿28 2

∑ XY =¿ ¿56
0

Let the trend line is

Y =a+bX
and to calculate the values of a & b we use the following two equations:

a=
∑ Y = 630 =90
N 7
And

b=
∑ XY = 56 =2
∑ X 2 28

On putting the values of a and b into the trend line, we get the following trend line

Y =90+2 X
 ii.
For the year 2010 the value of X should be 5, therefore putting X = 5 the above trend line
Y =90+2 ×5=100

Thus, in 2010 the estimated sale is 100.

Important Note: Dear students please do this example carefully

because this type of question has been asked in the examination.
You should not take risk of leaving this example.

c. Moving average method

Under this method, the average value for a number of years is taken and this average is taken
as the normal or trend value for the unit of time falling at the middle of the period covered.
The formula for 3 year moving average would be

a+b+ c b +c +d c+ d +e d+ e+ f
, , , ∧so on
3 3 3 3

The formula for 5 year moving average would be

a+b+ c+ d +e b +c +d +e +f c +d + e+ f + g d+ e+ f + g+h
, , , ∧so on
5 5 5 3

2. Regression Analysis
If X and Y are two variables such that Y is dependent variable (quantity demanded) and X is an
independent variable (price of the good or income of the consumer etc.), then in regression
analysis, a line which is known as regression line of Y on X is defined as follows:
σY
Y −Y =r ( X−X )
σX
Where Y = Arithmetic mean of Y ; X= Arithmetic meanof X
r =Coefficient of correlation between X∧Y
 σ Y=Standard deviationof Y
σ X=Standard deviation of Y
Similarly, if X and Y are two variables such that Y is independent variable and X is dependent
variable, then in regression analysis gives a line known as regression line of X on Y which is
defined as follows:
σX
X −X =r ( Y −Y )
σY

3. Barometric Technique
Barometric technique is based upon the assumption that an economic indicator can give some
idea about the change in a variable.

Examples are
a. If we find that automobile registrations are increasing day by day, then this is an indicator
or barometer that the demand for cars or motor bikes etc.are increasing.
b. If we find that the number of construction contracts sanctioned by government has
increased, then this an indicator or barometer that the demand for the material cement,
bricks, sand etc. is going to increase.