Forecasting

One of the crucial aspects in which managerial economics differs from pure economic theory lies in the treatment of risk and uncertainty. Traditional economic theory assumes a riskfree world of certainty; but the real world business is full of all sorts of risk and uncertainty. A manager cannot, therefore, afford to ignore risk and uncertainty. The element of risk is associated with future which is indefinite and uncertain. To cope with future risk and uncertainty, the manager needs to predict the future event. The likely future event has to be given form and content in terms of projected course of variables, i.e. forecasting. Thus, business forecasting is an essential ingredient of corporate planning. Such forecasting enables the manager to minimize the element of risk and uncertainty. Demand forecasting is a specific type of business forecasting. Concepts of Forecasting: The manager can conceptualize the future in definite terms. If he is concerned with future event- its order, intensity and duration, he can predict the future. If he is concerned with the course of future variables- like demand, price or profit, he can project the future. Thus prediction and projection-both have reference to future; in fact, one supplements the other. Suppose, it is predicted that there will be inflation (event). To establish the nature of this event, one needs to consider the projected course of general price index (variable). Exactly in the same way, the predicted event of business recession has to be established with reference to the projected course of variables like sales, inventory etc. Projection is of two types ± forward and backward. It is a forward projection of data variables, which is named forecasting. By contrast, the backward projection of data may be named µback casting¶, a tool used by the new economic historians. For practical managers concerned with futurology, what is relevant is forecasting, the forward projection of data, which supports the production of an event. Thus, if a marketing manager fears demand recession, he must establish its basis in terms of trends in sales data; he can estimate such trends through extrapolation of his available sales data. This trend estimation is an exercise in forecasting. Need for Demand Forecasting Business managers, depending upon their functional area, need various forecasts. They need to forecast demand, supply, price, profit, costs and returns from investments. The question may arise: Why have we chosen demand forecasting as a model? What is the use of demand forecasting?

It is comparatively easy to forecast the immediate future than to forecast the distant future. More over the time duration also depends upon the nature of the product for which demand forecasting is to be made. Time duration may be set for demand forecasting depending upon how frequent the fluctuations in demand are. The purposes are. Sales constitute the primary source of revenue for the corporate unit and reduction for sales gives rise to most of the costs incurred by the firm. In fast developing economy the duration may go up to 5 or 10 years.term forecasting: The concept of demand forecasting is more relevant to the long-run that the short-run. Fluctuations of a larger magnitude may take place in the distant future. Appropriate scheduling of production to avoid problems of over production and under. y . The forecasting demand helps a firm to arrange for the supplies of the necessary inputs without any wastage of materials and time and also helps a firm to diversify its output to stabilize its income overtime. while for another plant duration may extend to 6 months or one year.production. (1) The purpose of the Short term forecasting: It is difficult to define short run for a firm because its duration may differ according to the nature of the commodity. y Assessing long term financial needs. expansion and modernization of an existing unit. while in stagnant economy it may go up to 20 years.The significance of demand or sales forecasting in the context of business policy decisions can hardly be overemphasized. short. Demand forecasting is essential for a firm because it must plan its output to meet the forecasted demand according to the quantities demanded and the time at which these are demanded. Planning for a new project. y y y Proper management of inventories Evolving suitable price strategy to maintain consistent sales Formulating a suitable sales strategy in accordance with the changing pattern of demand and extent of competition among the firms. It takes time to raise financial resources. The purpose of demand forecasting differs according to the type of forecasting.term forecasting can be undertaken by affirm for the following purpose. For a highly sophisticated automatic plant 3 months time may be considered as short run. y (2) The purpose of long. y Forecasting financial requirements for the short period. diversification and technological up gradation.

The demand for intermediate goods like basic chemicals is derived from the final demand for finished goods like detergents. It has to go through a number of steps. final or intermediate demand.y Arranging suitable manpower. 2) Nature of product: The next important consideration is the nature of product for which you are attempting a demand forecast. price expectation etc. Promoting sales through advertising or price competition is much less important in the case of intermediate goods compared to final goods. conditional or non-conditional etc. your next task is to locate clearly the determinants of demand for the product. While forecasting the demand for basic chemicals. related income. The time taken for such adjustment varies from product to product. If there are storage facilities. adaptation of demand will be spread over a longer duration of time. Such considerations are categorically listed below: 1) Nature of forecast: To begin with. you have to choose the type of forecasts: short-run or long-run. Time factor is a crucial determinant in demand forecasting. active or passive. You have to examine carefully whether the product is consumer goods or producer goods. price and income. Steps in Demand Forecasting Demand or sales forecasting is a scientific exercise. then buyers can adjust their demand according to availability. it is important to consider socio- . Here skilful demand forecasting is needed to avoid waste. Depending on the nature of product and nature of forecasts. At each step. A couple of examples may illustrate the importance of this factor. 3) Determinants of demand: Once you have identified the nature of product for which you are to build a forecast. Perishable commodities such as fresh vegetables and fruits can be sold over a limited period of time. different determinants will assume different degree of importance in different demand functions. It can help a firm to arrange for specialized labour force and personnel. The elasticity of demand for intermediate goods depends on their relative importance in the price of the final product. y Evolving a suitable strategy for changing pattern of consumption. Depending upon its use. own income-disposable and discretionary. Whereas in case of expensive equipment which is worn out and replaced after a long period of time. you have been exposed to a number of price-income factors or determinants-own price. advertisement. perishable or durable. related price. Goods of daily necessities that are bought more frequently will lead to quicker adjustments. you have to make critical considerations. In the preceding unit. new demand or replacement demand type etc. you should be clear about the uses of forecast datahow it is related to forward planning and corporate planning by the firm. In addition. it becomes essential to analyze the nature of demand for detergents.

In an analysis of statistical demand function. which affect demand over long-run. because there is some regularly with regard to their occurrence. sociological and psychological factors affecting demand. Much of the accuracy and relevance of the forecast data depends accuracy required. which are a little more certain compared to cyclical factors. for it is a very critical choice. statistical or otherwise. You will find that different techniques may be appropriate for forecasting demand for different products depending upon their nature. While forecasting you cannot neglect these factors. 4) Analysis of factors &determinants: Identifying the determinants alone would not do. complexity of the relationship postulated in the demand function. others quite complex and difficult. The size of population. demand which is being predicted. the sex-composition-all these exercise influence on demand in. social status. This stating is needed to avoid/reduce the margin of error and thereby improve its validity for practical decision-making purpose. and (d) random factors which create disturbance because they are erratic in nature. In some cases. Such factors are particularly important for long-run active forecasts. specially demographic. Subsequently you will be exposed briefly to some of these methods and their uses. If more babies are born. You have to choose a particular technique from among various techniques of demand forecasting. it is customary to classify the explanatory factors into (a) trend factors. 6) Testing accuracy: This is the final step in demand forecasting. their operation and effects are not very orderly. more will be the demand for toys. (b) cyclical factors whose effects on demand are periodic in nature. Some of them are simple and inexpensive. Without considering these factors. trend factors are important. more will be the demand for furniture. demonstration effect etc. the location of household unit. it may be possible to use more than one technique. . However. reference period of the forecast. long-run demand forecasting is not possible. varying degrees. An analysis of factors is specially important depending upon whether it is the aggregate demand in the economy or the industry¶s demand or the company¶s demand or the consumers. but for a short-run demand forecast. for a long-run demand forecast. the choice of technique has to be logical and appropriate. (c) seasonal factors. There are various methods for testing statistical accuracy in a given forecast. you will be exposed to all such techniques. if more youngsters marry. their analysis is also important for demand forecasting. In the same way buyers¶ psychology-his need. ego. cyclical and seasonal factors are important. size of cost budget for the forecast etc. available time for forecasting exercise.psychological determinants. more will be the demand for sticks. 5) Choice of techniques: This is a very important step. Subsequently. the age-composition. if more old people survive. Also. ±also effect demand.

Techniques of Demand Forecasting Broadly speaking. thus generates ³reasoned opinion´ in place of ³unstructured opinion´. 3) Consumers Survey. In this set of methods. The first method is usually found suitable for short-term forecasting. the forecaster undertakes a complete survey of all consumers whose demand he intends to forecast. Sometimes this method is also called the µhunch method¶ but it replaces analysis by opinions and it can thus turn out to be highly subjective in nature. Moreover if the data are wrongly recorded. the forecaster selects a few consuming units out of the relevant population and then collects data on their . but this is still a poor proxy for market behavior of economic variables. This may lead to a narrowing down of the divergent views (of the experts) expressed earlier. the experts on the particular product whose demand is under study are requested to give their µopinion¶ or µfeel¶ about the product. Once this information is collected. we may undertake the following exercise. Both these methods rely on varying degrees of judgment. If the number of such experts is large and their experience-based reactions are different. These experts. 1) Experts Opinion Poll: In this method. the sales forecasts are obtained by simply adding the probable demands of all consumers. dealing in the same or similar product. 4) Consumer Survey-Sample Survey Method: Under this method.Complete Enumeration Method: Under this. Here is an attempt to arrive at a consensus in an uncertain area by questioning a group of experts repeatedly until the responses appear to converge along a single line. He simply records the data and aggregates. Simple Survey Method: For forecasting the demand for existing product. it is not feasible where a large number of consumers are involved. Such feedback may result in an expert revising his earlier opinion. there are two approaches to demand forecasting. this method will be totally useless. then an average-simple or weighted ±is found to lead to unique forecasts. are able to predict the likely sales of a given product in future periods under different conditions based on their experience. The principle merit of this method is that the forecaster does not introduce any bias or value judgment of his own. But it is a very tedious and cumbersome process. 2) Reasoned Opinion-Delphi Technique: This is a variant of the opinion poll method. followed by the Greeks earlier. the latter for long-term forecasting. such survey methods are often employed. The Delphi Techniques.one is to obtain information about the likely purchase behavior of the buyer through collecting expert¶s opinion or by conducting interviews with consumers. There are specific techniques which fall under each of these broad methods. the other is to use past experience as a guide through a set of statistical techniques. The participants are supplied with responses to previous questions (including seasonings from others in the group by a coordinator or a leader or operator of some sort).

The movement of AY is similar to that of ST. this method is less tedious and less costly. The demands for final consumption and exports net of imports are estimated through some other forecasting method. If the sample is properly chosen. The total demand of sample units is finally blown up to generate the total demand forecast. one can predict the direction of movement of tractors¶ sale (ST) for the next year. it only needs the time series data. As such. and its demand for intermediate use is estimated through a survey of its user industries. you may be quite familiar with some the statistical tools and techniques. it is an appropriate method for long-run forecasts. Thus agricultural income (AY) may be used as a barometer (a leading indicator) to help the short-term forecast for the sale of tractors. but the choice of sample is very critical. (2) Barometric Techniques or Lead-Lag indicators method: This consists in discovering a set of series of some variables which exhibit a close association in their movement over a period or time. but the movement in ST takes place after a year¶s time lag compared to the movement in AY. it shows the movement of agricultural income (AY series) and the sale of tractors (ST series). Complex Statistical Methods: We shall now move from simple to complex set of methods of demand forecasting. the moving average method or exponentially weighted moving average method is used to smoothen the series. but inappropriate for short-run forecasts. otherwise there may be sampling error. the sales of a product are projected through a survey of its end-users. and subject to less data error. . For example. Compared to the former survey. The only limitation in this method is that it assumes that the past is repeated in future. In that case. A product is used for final consumption or as an intermediate product in the production of other goods in the domestic market. the time series data on the under forecast are used to fit a trend line or curve either graphically or through statistical method of Least Squares. The trend method outlined above often yields a dependable forecast. (1) Time series analysis or trend method: Under this method. or it may be exported as well as imported. Also. The trend line is worked out by fitting a trend equation to time series data with the aid of an estimation method. as a part of quantitative methods for business decisions. then it will yield dependable results. Thus if one knows the direction of the movement in agriculture income (AY). Such methods are taken usually from statistics. Sometimes the time series analysis may not reveal a significant trend of any kind. The advantage in this method is that it does not require the formal knowledge of economic theory and the market.probable demands for the product during the forecast period. The sampling error can decrease with every increase in sample size 5) End-user Method of Consumers Survey: Under this method. The trend equation could take either a linear or any kind of non-linear form.

We are on the realm of multiple regression and multiple correlation. Lastly. In other . Some of the limitations of this method may be noted however. The analysis can be carried with varying degrees of complexity. Finally. besides generating demand forecast. this barometric method has been used in some of the developed countries for predicting business cycles situation. b2. The relationship may be expressed in the form of a demand function. Econometrics. We shall concentrate simply on the use of these econometric techniques in forecasting.). The reflect the direction as well as proportion of change in demand for x as a result of a change in any of its explanatory variables. advertisement etc. statistical analysis and mathematical functions to determine the relationship between a dependent variable (say. it explains why the demand is what it is. you must have covered those statistical techniques as a part of quantitative methods. b2< 0 suggest that DX and PX are inversely related. Through our estimation we may find out the best-fitted lag period on the past data. 3) Correlation and Regression: These involve the use of econometric methods to determine the nature and degree of association between/among a set of variables. For example. Also.Generally. b4 > 0 suggest that x and y are substitutes. but only the direction of change. For example. if you know the future values of explanatory variables like own price (PX). some countries construct what are known as µdiffusion indices¶ by combining the movement of a number of leading series in the economy so that turning points in business activity could be discovered well in advance. lagging or coincident indicators of the variable for which a demand forecast is being attempted. Here we shall not get into the methods of finding out µcorrelation coefficient¶ or µregression equation¶. sales) and one or more independent variables (like price. income. The principle advantage of this method is that it is prescriptive as well descriptive. is the use of economic theory. The form of the equation may be: DX = a + b1 A + b2PX + b3Py You know that the regression coefficients b1. income (B) and advertisement (A). b3 and b4 are the components of relevant elasticity of demand. Similarly. but the same may not be true for the future. it may not be always possible to find out the leading. the lead period itself may change overtime. b3 > 0 suggest that x is a normal commodity with commodity with positive income-effect. you may forecast the expected sales (DX). Given the estimated value of and bi. based on past data can be used for forecasting. Such relationships. we shall not go into the question of economic theory. the better is the fit. The closer it is to unity. you may recall. you may also recall that the statistics R2 (Co-efficient of determination) gives the measure of goodness of fit. as we have seen earlier. and that way you get a more reliable forecast. That is. The leading indicator method does not tell you anything about the magnitude of the change that can be expected in the lagging series. For this purpose. related price (Py). b1 is a component of price elasticity of demand.

In this method of forecasting. (4) Simultaneous Equations Method: Here is a very sophisticated method of forecasting. The only precaution you need to take is that data analysis should be based on the logic of economic theory. It is also known as the µcomplete system approach¶ or µeconometric model building¶. this technique has got both explanatory and predictive value. endogenous and exogenous variables affecting the variable under forecast. The method is indeed very complicated. The principle advantage in this method is that the forecaster needs to estimate the future values of only the exogenous variables unlike the regression method where he has to predict the future values of all. . our focus is limited to micro elements only. However. this method is normally used in macro-level forecasting for the economy as a whole. such econometric models have limitations. Presently we do not intend to get into the details of this method because it is a subject by itself. this method can be used easily to derive meaningful forecasts. as corporate managers. However. we have made reference to such econometric models. when package programmes are available. In your earlier units.words. The values of exogenous variables are easier to predict than those of the endogenous variables. The regression method is neither mechanistic like the trend method nor subjective like the opinion poll method. similar to that of regression method. Moreover. in the days of computer. in this course. should know the basic elements in such an approach. you may use not only time-series data but also cross section data. Of course. you.

Sign up to vote on this title
UsefulNot useful