An attempt is made to quantify the relationship between the
demand for a product and the determinant variables, such as price, price of related goods, national income, advertising etc.
Widespread application: A computer dealer would like to know the implications of reduction in excise duties, lower prices and rising GNP on the demand for PCs.
An electronics manufacturer might be interested in estimating changing proportion of demand for domestic and imported electronic items when the import policy of the government is liberalized.
Methods of Demand Estimation 1.Regression analysis-Most useful and used method .
2.Marketing Research Approach a)Consumer Survey and Observational Research-Former useful but could be biased and expensive.Latter could raise questions about privacy.(Scanners and People meters) b)Consumer Clinics-Useful but sample maybe too small and situation too artificial. c)Market Experiments-Either same market over different time periods or different markets with similar socioeconomic features.Can be conducted on a larger scale and more realistic.However, maybe over a short period or on a limited scale due to cost considerations.Further bias may get in due to extraneous conditions,danger from competitors and permanent loss of customers due to price rise experimentation. Meaning:It refers to the anticipation or expectation about the future course of the market demand for a product.
Nevertheless,it is not a speculative exercise into the unknown.It is based on on the statistical data about past behavior and empirical relationships.
The aim is to reduce the risk or uncertainty that the firm faces in its short-term operational decision-making and in planning for its long-term growth.
This begins with a macro-forecast of the general level of economic activity for the economy as a whole or gross national product.These macro-forecasts are used as Inputs for their micro-forecasts of the industrys and firms demand and sales. Demand Forecasting It is very essential for all aspects of decision-making. Production Planning,Sales Forecasting,Control of Business,Inventory Control, Growth and Long-term Investment Programmes,Stability .
Short-term forecasting-Relates to a period not exceeding a year.Important for evolving a sales policy,a price policy, a purchase policy fixation of sales targets and for short-term financial-planning.
Long-term forecasting-Vital for strategy formulation, manpower planning and long-term financial planning. Significance of Demand Forecasting I)QUALITATIVE FORECASTS: Often used to make short-term forecasts when quantitative data is not available or for supplementing it. Also useful during product introduction. 1.Survey Techniques Have proved very useful in conjunction with other tools but a growing number of consumers are refusing to participate in market-research surveys because of the time involved, the loss of privacy, and the pressure from salespeople operating under the guise of market research. This leads to increasing difficulties in obtaining representative samples and to a trend towards the greater use of observational research. This may include the complete enumeration method, the sample survey method and the end use method.
Different Techniques of Demand Forecasting 2.Opinion Polls: While the results of published surveys of expenditure plans of businesses, consumers and governments are useful, the firm usually needs specific forecasts of its own sales by polling experts within and outside the firm. There are several such polling techniques: a)Executive polling: The firm can poll its top management from its sales, production, finance and personnel departments on their views on the sales outlook for the firm during the next quarter or year. While these personal insights are to a large extent subjective, by averaging the opinions of the experts who are most knowledgeable about the firm and its products, the firm hopes to arrive at a better forecast than would be provided by these experts individually. Outside market experts could also be polled. Different Techniques of Demand Forecasting To avoid a bandwagon effect the Delphi method can be used. Here, experts are polled separately, and then feedback is provided without identifying the expert responsible for a particular opinion. The hope is that through this feedback procedure the experts can arrive at some consensus forecast. b)Sales force polling: This is a forecast of the firms sales in each region and for each product line; it is based on the opinion of the firms sales force in the field. These are the people closest to the market, and their opinion of future sales can provide valuable information to the firms top management. c)Consumer intentions polling 3.Soliciting a Foreign Perspective: Here councils are formed of distinguished foreign dignitaries and business people. This input becomes a valuable tool to get a global perspective and plan longer-term domestic and foreign strategies. Different Techniques of Demand Forecasting 2). TIME SERIES ANALYSIS:this attempts to forecast future vales of the time series by examining past observations of the data.The assumption is that the time series will continue to move as in the past. For this reason, this analysis is often called nave forecasting.
Reasons for fluctuations in Time-Series data: 1. Secular trend refers to a long-run increase or decrease in the data series.(Example sales may show a rising trend over years because of population etc). 2.Cyclical fluctuations are the major expansions and contractions in most economic time series that seem to recur every several years. 3.Seasonal variation refers to the regularly recurring fluctuation in economic activity during each year because of weather and social customs. 4.Irregular or random influences may result from wars,strikes etc Different Techniques of Demand Forecasting The simplest form of time-series analysis is projecting the past trend by fitting a straight line to the data either visually or, more precisely, by regression analysis. Time-series cannot forecast turning points until they have occurred and it does not examine the underlying forces. Hence it is most useful in conjunction with other forecasting methods.
3) SMOOTHING TECHNIQUES :These predict values of a time series on the basis of some average of its past values only. These are useful when the time series exhibit little trend or seasonal variations but a great deal of random variation which are then smoothed. Two specific smoothing techniques are given under: Moving Averages and Exponential Smoothing :Here the forecasted value is equal to the average value of the time- series in a number of previous periods. The latter is used more frequently as it includes a weighted average. Different Techniques of Demand Forecasting 4)BAROMETRIC METHODS: One way to forecast or anticipate short-term changes in economic activity or turning points in business cycles is to use the index of economic indicators. The three basic indicators used here are classified as given: 1)Leading indicators: These move up or down ahead of some other series. For example, an increase in building permits can be used to forecast an increase in housing construction. 2)Coincidental indicators: These move up or down with simultaneously with the level of economic activity. For example, the rate of unemployment. 3)Lagging indicators: These follow a change after some time-lag. Example, outstanding loans.
Different Techniques of Demand Forecasting Different Techniques of Demand Forecasting In order to smooth out random variations and provide more reliable forecasts with fewer wrong signals than individual indicators we may use what is termed as the composite index.This is a weighted average of the individual indicators in each group, with the indicators that do a better job of forecasting given bigger weights. Another way of solving this problem would be through the diffusion index.This gives the percentage of rising indicators. Though the above is a reasonably good tool to predict turning points, however at times a leading variable may not be available.The variability in lead time may also be considerable.Also this provides only a qualitative forecast.Thus it must be used in conjunction with other methods.
Different Techniques of Demand Forecasting 5)ECONOMETRIC MODELS:These combine statistical tools with economic theories to forecast economic events.They seek to identify and measure the relative importance of the various determinants of demand or other economic variables to be forecasted.
An econometric model may be a single-equation regression model or it may consist of a system of simultaneous equations.
Finally the applicability and usefulness of a method depends on the purpose of forecasting and availability of reliable and relevant data.Ultimately the analysts own judgment also holds great importance.