8/8/2019 Demand Fore Casting
1/15
DEMAND FORECASTING
8/8/2019 Demand Fore Casting
2/15
Superior method of demand estimation
Scientific method (based on dependent & independent
variable)
Estimates are more reliableEstimation involves small cost
STATISTICAL METHODS
8/8/2019 Demand Fore Casting
3/15
Following 3 techniques:-
1. trend projection method
2.
3.
8/8/2019 Demand Fore Casting
4/15
TREND PROJECTION METHOD
It is used under the assumption that the factors
responsible for the past trends in the variable to be
projected will continue to play their past in future in the
same manner & to the same extent .
8/8/2019 Demand Fore Casting
5/15
Following three techniques:-
1. Graphical method
2. Fitting trend equation / least square method
3. Box-jenkins method
8/8/2019 Demand Fore Casting
6/15
(b) Fitting trend Equation -
Extension of graphical method
Using statistical techniques
following types:-
(a) linear trend(b) exponential trend
(c) box-junkins method
8/8/2019 Demand Fore Casting
7/15
Linear trend
When a line seriesdata reveals a rising trend in sales
then a straight line trend equation of the following form
is fitted:-
s=a+bT
S= annual sales
T = time (years) a&b = constant
8/8/2019 Demand Fore Casting
8/15
Exponential trend
When sales have increased over the past years at a
increasing rate or at a costant percentage rate , then trend
equation used is :-
Y = ae^bT Y is sales , T is time
Limitations:- 1.assumptions that past trend will
follow again
2.cannot be used for short termestimates.
8/8/2019 Demand Fore Casting
9/15
Box-jenkins method
1. Used only for short term predictions
2. Only for monthly or seasonal variations recurring
with some degree of regularity
example:- sale of greeting cards in december last week
8/8/2019 Demand Fore Casting
10/15
ECONOMETRIC METHODS
In this method, statistical tools are combined with the
economic theories to estimate economic variables and to
forecast the intended economic variables.
The forecasts made through econometric methods are
much more reliable than those made through any other
method.
This method can be described briefly by two basicmethods
1. Regression method
2. Simultaneous equation method
8/8/2019 Demand Fore Casting
11/15
Regression methods
Regression analysis is the most popular method of
demand estimation. This method combines economic
theory and statistical techniques of estimation.
I
n this demand function, the quantity to be forecasted is adependent variable and the variables that effect or
determine the demand are called independent or
explanatory variables.
Example: the demand of tunics depend on the socialculture and the seasonal changes. Here, the demand of
tunics is dependent variable and social culture and
seasonal changes are independent variables.
8/8/2019 Demand Fore Casting
12/15
REGRESSION METHOD
SINGLE ORBIVARIATEREGRESSION TECHNIQUE
MULTI-VARIATEREGRESSION TECHNIQUE
8/8/2019 Demand Fore Casting
13/15
Single or bivariate regression technique:
In single regression technique only one variable is
taken in consideration for the forecasting. And in bivariate
regression technique only two variable are taken inconsideration.
Multi variate regression technique:
The multi variate regression equation is used where
demand for a commodity is deemed to be the function ofmany variables or in cases in which the number of
explanatory variables is greater than one.
8/8/2019 Demand Fore Casting
14/15
Simultaneous Equations Model
Simultaneous equations model is a complete and
systematic approach to forecasting. This technique uses
mathematical and statistical tools.
Simultaneous equation model allows the forecaster to
take into account the simultaneous interaction between
dependent and independent variables.
The variables included are:
1. Endogenous variables
2. Exogenous variables
8/8/2019 Demand Fore Casting
15/15
Thank You
ADITYA UPADHYAY
LATIKA KATAYALP SHIVRAM
SHAH TWINKLE