DEMAND ESTIMATION
AND
FORECASTING
Prepared by Dr. G. Makuyana
+263 782 314 111
grkmakuyana@gmail.com
1. The business environment is
uncertain, volatile, dynamic and
WHY risky.
FORECA 2. Better decision can be taken if
uncertainty can be eliminated or
ST reduced.
DEMAN
D? Demand forecast, predicting
the future demand for firm’s
product, is one of the ways to
reduce uncertainty.
Some of the business decision-making aided by
a good demand forecast are:
Determining the optimal level of output
WHY Planning and scheduling of production,
FORECA distribution & transportation
ST Acquiring inputs (raw material, labour,
capital)
DEMAN
D? Determining cost and pricing strategy
Decisions on expansion and exit strategies
for the product
Meeting customer order dates and
customer satisfaction
1. quantify the links or relationship between
the level of demand and the variables which
In are determinants to it and is generally used in
Demand designing pricing strategy of the firm.
estimating 2. analyse the impact of future change in price
manager on the quantity demanded.
attempts In demand estimation data is collected for
to: short period usually a year or less and
analysed in relation to various variables to
know the impact of each variables mainly the
price on the demand behaviour of the
customers.
extrapolate the most likely future demand of a product so
that he/she can make necessary arrangement for the various
factor of production i.e labour, raw material, machines,
money etc.
Demand forecasting tells the expected level of demand at
some future date on the basis of past and present information.
It helped in production planning, new product development,
capacity enhancement or new schemes etc.
In Demand forecasting managers attempt to:
Direct Methods of
Demand Estimation
Consumer interviews
range from stopping
shoppers to speak with
them to administering
detailed questionnaires
Direct Methods of
Demand Estimation
Potential problems with consumer
interviews:
1. Selection of a representative sample,
which is a sample (usually random)
having characteristics that accurately
reflect the population as a whole;
2. Response bias, which is the difference
between responses given by an individual
to a hypothetical question and the action
the individual takes when the situation
actually occurs.
Empirical Demand
Functions
Demand equations
derived from actual
market data.
Useful in making pricing
& production decisions
Simple linear regression
assumes one-way
causation
Simple Inappropriate
competitive markets
for
regression Price and output are
analysis simultaneously
determined in competitive
markets
Advanced regression
techniques are available
for estimating demand in
competitive markets
Empirical Demand Functions
In linear form, an empirical demand function can
be specified as
𝑄=𝑎+𝑏𝑃+𝑐𝑀 +𝑑 𝑃 𝑅
where Q is quantity demanded, P is the price of the good or service,
M is consumer income, & PR is the price of some related good R
Empirical Demand Functions
𝑄=𝑎+𝑏𝑃+𝑐𝑀 +𝑑 𝑃 𝑅
In linear form
b = Q/P
c = Q/M
d = Q/PR
Expected signs of coefficients
b is expected to be negative
c is positive for normal goods; negative for inferior goods
d is positive for substitutes; negative for complements
Empirical Demand Functions
𝑄=𝑎+𝑏𝑃+𝑐𝑀 +𝑑 𝑃 𝑅
•
Estimated elasticities of demand are computed as
^ ^ 𝑃
• 𝐸= 𝑏
𝑄
^ 𝑀
• 𝐸 𝑀 =𝑐^
𝑄
^ 𝑃𝑅
^
• 𝐸 𝑋𝑅= 𝑑
𝑄
Nonlinear Empirical Demand Specification
When demand is specified in log-linear form, the
demand function can be written as
𝑏 𝑐 𝑑
𝑄=𝑎 𝑃 𝑀 𝑃
𝑅
• To estimate a log-linear demand function, covert
to logarithms
ln 𝑄=ln 𝑎+𝑏 ln 𝑃+𝑐 ln 𝑀+𝑑 ln 𝑃 𝑅
• In this form, elasticities are constant
^𝐸=𝑏^ 𝐸^ 𝑀 =𝑐^ ^𝐸 𝑋𝑅 =𝑑^
To estimate demand function for a price-
setting firm:
Demand Step 1: Specify price-setting firm’s
demand function
for a Price-
Setter Step 2: Collect data for the variables in
the firm’s demand function
Step 3: Estimate firm’s demand using
ordinary least-squares regression (OLS)
Time-Series Forecasts
A time-series model shows how a time-ordered
sequence of observations on a variable is
generated
Simplest form is linear trend forecasting
Sales in each time period (Qt ) are assumed to be linearly
related to time (t)
bt
Linear Trend Forecasting
• Use regression analysis to estimate
values of a and b
^ 𝑡 =𝑎^ + 𝑏^ 𝑡
𝑄
• If b > 0, sales are increasing over time
• If b < 0, sales are decreasing over time
• If b = 0, sales are constant over time
• Statistical significance of a trend is
determined by testing 𝑏 ^ or by examining
the p-value for 𝑏 ^
A Linear Trend Forecast
Q
Estimated trend line
𝑄^ 2009
12
𝑄^ 2004
7
Sales
t
2006
2004
2005
2007
1997
1999
2000
1998
2001
2002
2003
2012
Linear Trend Estimation
7-
18
Forecasting Sales for Terminator Pest Control
Seasonal (or Cyclical) Variation
Can bias the estimation of parameters in linear
trend forecasting
To account for such variation, dummy variables are
added to the trend equation
Shift trend line up or down depending on the particular
seasonal pattern
Significance of seasonal behaviour determined by using t-
test or p-value for the estimated coefficient on the dummy
variable
Sales with Seasonal Variation
2004 2005 2006 2007
Quarterly Sales Data
7-
22
The further into the future a
forecast is made, the wider is the
confidence interval or region of
Some uncertainty
Final Model misspecification, either by
excluding an important variable or
Warnings by using an inappropriate
functional form, reduces reliability
of the forecast
Forecasts are incapable of
predicting sharp changes that
occur because of structural
changes in the market
