Lesson 12 DEMAND FORECASTING                                Learning outcomesAfter studying this unit, you should be able ...
the backward projection of data may be named ‘back casting’, a tool used by thenew economic historians. For practical mana...
Thus, if a marketing manager fears demand recession, he mustestablish its basis in terms of trends in sales data; he can e...
Nature of forecast: To begin with, you should be clear about the uses offorecast data- how it is related to forward planni...
4) Analysis of factors &determinants: Identifying the determinants alone wouldnot do, their analysis is also important for...
For forecasting the demand for existing product, such survey methods are oftenemployed. In this set of methods, we may und...
6) End-use Method of Consumers’ Survey : Under this method, the sales of aproduct are projected through a survey of its en...
business activity could be discovered well in advance. Some of the limitations of thismethod may be noted however. The lea...
precaution you need to take is that data analysis should be based on the logic ofeconomic theory. Simultaneous Equations M...
Unitary ealstic                            %∆Q=%∆PRelatively elastic                                                      ...
Elasticity                                                       Assumptione = own price or direct priceelasticity of dema...
and forecasting. What is the significance of demand forecasting?
Distinguish between the following types of forecasts:    1) Economic and Non-economic forecasts    2) Micro and Macro fore...
.............................................................................................................................
Adhikary, M. (1987) Managerial Economics, Khosla Publishing House: N. Delhi(Ch. VIII).Gupta, G.S. (1974) ‘Forecasting Tech...
or, log eD = loge a + b loge TThis double-log trend assumes a constant elasticity = b every period.POINTS TO PONDER       ...
Slide 3                                                                          __________________________________       ...
Slide 3                                                                          __________________________________       ...
Slide 3                                                                          __________________________________       ...
Upcoming SlideShare
Loading in …5
×

Deman forcasting

3,257 views

Published on

0 Comments
1 Like
Statistics
Notes
  • Be the first to comment

No Downloads
Views
Total views
3,257
On SlideShare
0
From Embeds
0
Number of Embeds
1
Actions
Shares
0
Downloads
84
Comments
0
Likes
1
Embeds 0
No embeds

No notes for slide

Deman forcasting

  1. 1. Lesson 12 DEMAND FORECASTING Learning outcomesAfter studying this unit, you should be able to: define ‘forecasting’ in contrast to ‘projection’ and ‘ prediction’ distinguish between various types of forecasts describe the techniques of demand forecasting discuss the uses and abuses of each techniqueIntroduction One of the crucial aspects in which managerial economics differs frompure economic theory lies in the treatment of risk and uncertainty. Traditionaleconomic theory assumes a risk-free world of certainty; but the real worldbusiness 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 futurewhich is indefinite and uncertain. To cope with future risk and uncertainty, themanager needs to predict the future event. The likely future event has to be givenform and content in terms of projected course of variables, i.e. forecasting. Thus,business forecasting is an essential ingredient of corporate planning. Suchforecasting 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 isconcerned with future event- its order, intensity and duration, he can predict thefuture. If he is concerned with the course of future variables- like demand, price orprofit, he can project the future. Thus prediction and projection-both havereference to future; in fact, one supplements the other. Suppose, it is predicted thatthere will be inflation (event). To establish the nature of this event, one needsto consider the projected course of general price index (variable). Exactly in thesame way, the predicted event of business recession has to be established withreference to the projected course of variables like sales, inventory etc. Projection is of two types – forward and backward. It is a forwardprojection of data variables, which is named forecasting. By contrast,
  2. 2. the backward projection of data may be named ‘back casting’, a tool used by thenew economic historians. For practical managers concerned with futurology,what is relevant is forecasting, the forward projection of data, whichsupports the prediction of an event.
  3. 3. Thus, if a marketing manager fears demand recession, he mustestablish its basis in terms of trends in sales data; he can estimate such trendsthrough extrapolation of his available sales data. This trend estimation isan exercise in forecasting. NEED FOR DEMAND FORECASTING Business managers, depending upon their functional area, need variousforecasts. They need to forecast demand, supply, price, profit, costs, investment,and what have you. In this unit, we are concerned with only demand forecasting.The reason is, the concepts and techniques of demand forecastingdiscussed here can be applied anywhere. The question may arise: Why have we chosen demand forecasting as amodel? What is the use of demand forecasting? The significance of demand or sales forecasting in the context ofbusiness policy decisions can hardly be overemphasized. Sales constitute theprimary source of revenue for the corporate unit and reduction for sales givesrise to most of the costs incurred by the fir. Thus sales forecasts are needed forproduction planning, inventory planning, profit planning and so on .Production itself requires the support of men, materials, machines, money andfinance, which will have to be arranged. Thus, manpower planning,replacement or new investment planning, working capital management andfinancial planning—all depend on sales forecasts. Thus demand forecasting iscrucial for corporate planning. The survival and growth of a corporate unit has to beplanned, and for this sales forecasting is the most crucial activity. There is nochoice between forecasting and no-forecasting. The choice exists only withregard to concepts and techniques of forecasting that we employ. It must benoted that the purpose of forecasting in general is not to provide an exact futuredata with perfect precision, the purpose is just to bring out the range ofpossibilities concerning the future under a given set of assumptions. In otherwords, it is not the ‘actual future’ but the ‘likely future’ that we build up throughforecasts. Such forecasts do not eliminate, but only help you to reduce thedegree of risk and uncertainties of the future. Forecasting is a step towards thatkind of ‘gursstimation’; it is some sort of an approximation to reality. If thelikely state comes close to the actual state, it means that the forecast isdependable. If you do not meaningless. A sales forecast is meant to guidebusiness policy decision. Without forecasting, forward planning by a corporateunit will be directionless.STEPS IN DEMAND FORECASTINGDemand or sales forecasting is a scientific exercise. It has to go through a number ofsteps. At each step, you have to make critical considerations. Such considerations arecategorically listed below:
  4. 4. Nature of forecast: To begin with, you should be clear about the uses offorecast data- how it is related to forward planning and corporate planning by thefirm. Depending upon its use, you have to choose the type of forecasts: short-run or long-run, active or passive, conditional or non-conditional etc.1) Nature of product: The next important consideration is the nature of productfor which you are attempting a demand forecast. You have to examine carefullywhether the product is consumer goods or producer goods, perishable ordurable, final or intermediate demand, new demand or replacement demand typeetc. A couple of examples may illustrate the importance of this factor. Thedemand for intermediate goods like basic chemicals is derived from thefinal demand for finished goods like detergents. While forecasting thedemand for basic chemicals, it becomes essential to analyse the nature ofdemand for detergents. Promoting sales through advertising or pricecompetition is much less important in the case of intermediate goodscompared to final goods. The elasticity of demand for intermediate goodsdepends on their relative importance in the price of the final product. Time factor is a crucial determinant in demand forecasting.Perishable commodities such as fresh vegetables and fruits can be soldover a limited period of time. Here skilful demand forecasting is needed toavoid waste. If there are storage facilities, then buyers can adjust theirdemand according to availability, price and income. The time taken forsuch adjustment varies from product to product. Goods of daily necessitiesthat are bought more frequently will lead to quicker adjustments. Whereas incase of expensive equipment which is worn out and replaced after a long periodof time, adaptation of demand will be spread over a longer duration of time.3) Determinants of demand: Once you have identified the nature of product forwhich you are to build a forecast, your next task is to locate clearly thedeterminants of demand for the product. Depending on the nature of product andnature of forecasts, different determinants will assume different degreeof importance in different demand functions. In the preceding unit, you havebeen exposed to a number of price-income factors or determinants-own price,related price, own income-disposable and discretionary, related income,advertisement, price expectation etc. In addition, it is important to considersocio-psychological determinants, specially demographic, sociological andpsychological factors affecting demand. Without considering thesefactors, long-run demand forecasting is not possible. Such factors are particularly important for long-run activeforecasts. The size of population, the age-composition, the location of householdunit, the sex-composition-all these exercise influence on demand in. varyingdegrees. If more babies are born, more will be the demand for toys; ifmore youngsters marry, more will be the demand for furniture; if more oldpeople survive, more will be the demand for sticks. In the same way buyers’psychology-his need, social status, ego, demonstration effect etc. –alsoeffect demand. While forecasting, you cannot neglect these factors.
  5. 5. 4) Analysis of factors &determinants: Identifying the determinants alone wouldnot do, their analysis is also important for demand forecasting. In an analysis ofstatistical demand function, it is customary to classify the explanatory factors into(a) trend factors, which affect demand over long-run, (b) cyclical factors whoseeffects on demand are periodic in nature, (c) seasonal factors, which are a littlemore certain compared to cyclical factors, because there is some regularly withregard to their occurrence, and (d) random factors which createdisturbance because they are erratic in nature; their operation and effectsare not very orderly.An analysis of factors is specially important depending upon whether it isthe aggregate demand in the economy or the industry’s demand or thecompany’s demand or the consumers; demand which is being predicted. Also,for a long-run demand forecast, trend factors are important; but for ashort-run demand forecast, cyclical and seasonal factors are important.5) Choice of techniques: This is a very important step. You have to choose aparticular technique from among various techniques of demand forecasting.Subsequently, you will be exposed to all such techniques, statistical or otherwise.You will find that different techniques may be appropriate for forecasting demand fordifferent products depending upon their nature. In some cases, it may bepossible to use more than one technique. However, the choice of technique has tobe logical and appropriate; for it is a very critical choice. Much of the accuracy andrelevance of the forecast data depends accuracy required, reference period of theforecast, complexity of the relationship postulated in the demand function, availabletime for forecasting exercise, size of cost budget for the forecast etc.6) Testing accuracy : This is the final step in demand forecasting. Thereare various methods for testing statistical accuracy in a given forecast. Some ofthem are simple and inexpensive, others quite complex and difficult. Thisstating is needed to avoid/reduce the margin of error and thereby improveits validity for practical decision-making purpose. Subsequently you will beexposed briefly to some of these methods and their uses.TECHNIQUES OF DEMAND FORECASTINGBroadly speaking, there are two approaches to demand forecasting- one is toobtain information about the likely purchase behavior of the buyer throughcollecting expert’s opinion or by conducting interviews with consumers, the other isto use past experience as a guide through a set of statistical techniques. Both thesemethods rely on varying degrees of judgment. The first method is usually foundsuitable for short-term forecasting, the latter for long-term forecasting. Thereare specific techniques which fall under each of these broad methods.We shall now taker up each one of these techniques under broadcategory of methods suggested above.SIMPLE SURVEY METHODS
  6. 6. For forecasting the demand for existing product, such survey methods are oftenemployed. In this set of methods, we may undertake the followingexercise.1) Experts’ Opinion Poll : In this method, the experts on the particular productwhose demand is under study are requested to give their ‘opinion’ or ‘feel’ aboutthe product. These experts, dealing in the same or similar product, areable to predict the likely sales of a given product in future periods underdifferent conditions based on their experience. If the number of such experts islarge and their experience-based reactions are different, then anaverage-simple or weighted –is found to lead to unique forecasts.Sometimes this method is also called the ‘hunch method’ but it replacesanalysis by opinions and it can thus turn out to be highly subjective in nature.2) Reasoned Opinion-Delphi Technique : This is a variant of the opinion pollmethod. Here is an attempt to arrive at a consensus in an uncertain area byquestioning a group of experts repeatedly until the responses appear to convergealong a single line. The participants are supplied with responses to previousquestions (including seasonings from others in the group by a coordinator ora leader or operator of some sort). Such feedback may result in an expert revisinghis earlier opinion. This may lead to a narrowing down of the divergent views (of theexperts) expressed earlier. The Delphi Techniques, followed by the Greeksearlier, thus generates “reasoned opinion” in place of “unstructured opinion”; but thisis still a poor proxy for market behaviour of economic variables.3) Consumers’ Survey- Complete Enumeration Method : Under this, theforecaster undertakes a complete survey of all consumers whose demand heintends to forecast, Once this information is collected, the sales forecasts areobtained by simply adding the probable demands of all consumers. For example,if there are N consumers, each Ndemanding D then the total demand forecast is ∑ D i i = 1The principle merit of this method is that the forecaster does not introduce anybias or value judgment of his own. He simply records the data and aggregates.But it is a very tedious and cumbersome process; it is not feasible where a largenumber of consumers are involved.Moreover if the data are wrongly recorded, this method will be totally useless.4)Consumer Survey-Sample Survey Method : Under this method,the forecaster selects a few consuming units out of the relevant population andthen collects data on their probable demands for the product during theforecast period. The total demand of sample units is finally blown up to generatethe total demand forecast. Can you give me any example?Compared to the former survey, this method is less tedious and less costly, and subject toless data error; but the choice of sample is very critical. If the sample is properly chosen,then it will yield dependable results; otherwise there may be sampling error. Thesampling error can decrease with every increase in sample size.
  7. 7. 6) End-use Method of Consumers’ Survey : Under this method, the sales of aproduct are projected through a survey of its end-users. A product is usedfor final consumption or as an intermediate product in the production of othergoods in the domestic market, or it may be exported as well as imported. Thedemands for final consumption and exports net of imports are estimatedthrough some other forecasting method, and its demand for intermediateuse is estimated through a survey of its user industries.COMPLEX STATISTICAL METHODSWe shall now move from simple to complex set of methods ofdemand forecasting. Such methods are taken usually from statistics. As such,you may be quite familiar with some the statistical tools and techniques, asa part of quantitative methods for business decisions.Time series analysis or trend method: Under this method, the time series dataon the under forecast are used to fit a trend line or curve eithergraphically or through statistical method of Least Squares. The trend line is worked out by fitting a trend equation totime series data with the aid of an estimation method. The trend equation couldtake either a linear or any kind of non-linear form. (Some of the most suitabletrend equations for demand forecasting are given in the Appendix )The trend method outlined above often yields a dependable forecast. Theadvantage in this method is that it does not require the formal knowledgeof economic theory and the market, it only needs the time series data.The only limitation in this method is that itassumes that the past is repeated in future. Also, it is an appropriate method for long-runforecasts, but inappropriate for short-run forecasts. Sometimes the time series analysismay not reveal a significant trend of any kind. In that case, the moving average method orexponentially weighted moving average method is used to smoothen the series. Barometric Techniques or Lead-Lag indicators method: This consists in discoveringa set of series of some variables which exhibit a close association in their movement overa period or time.It shows the movement of agricultural income (AY series) and the sale of tractors(ST series). The movement of AY is similar to that of ST, but the movement in STtakes place after a year’s time lag compared to the movement in AY. Thus if oneknows the direction of the movement in agriculture income (AY), one can predictthe direction of movement of tractors’ sale (ST) for the next year.Thus agricultural income (AY) may be used as a barometer (a leadingindicator) to help the short-term forecast for the sale of tractors.Generally, this barometric method has been used in some of the developedcountries for predicting business cycles situation. For this purpose, somecountries construct what are known as ‘diffusion indices’ by combining themovement of a number of leading series in the economy so that turning points in
  8. 8. business activity could be discovered well in advance. Some of the limitations of thismethod may be noted however. The leading indicator method does not tell youanything about the magnitude of the change that can be expected in thelagging series, but only the direction of change. Also, the lead period itself maychange overtime. Through our estimation we may find out the best-fitted lagperiod on the past data, but the same may not be true for the future. Finally, it maynot be always possible to find out the leading, lagging or coincident indicatorsof the variable for which a demand forecast is being attempted.3) Correlation and Regression: These involve the use of econometric methodsto determine the nature and degree of association between/among a setof variables. Econometrics, you may recall, is the use of economic theory,statistical analysis and mathematical functions to determine the relationshipbetween a dependent variable (say, sales) and one or more independentvariables (like price, income, advertisement etc.). The relationship may beexpressed in the form of a demand function, as we have seen earlier.Such relationships, based on past data can be used for forecasting. The analysiscan be carried with varying degrees of complexity. Here we shall not get into themethods of finding out ‘correlation coefficient’ or ‘regression equation’, you musthave covered those statistical techniques as a part of quantitative methods.Similarly, we shall not go into the question of economic theory. We shallconcentrate simply on the use of these econometric techniques in forecasting.we are on the realm of multiple regression and multiple correlation. The form ofthe equation may be:DX = a + b1 A + b2PX + b3PyYou know that the regression coefficients b 1, b2, b3 and b4 are the components ofrelevant elasticity of demand. For example, b 1 is a component of price elasticityof demand. The reflect the direction as well as proportion of change in demandfor x as a result of a change in any of its explanatory variables. For example, b 2<0 suggest that DX and PX are inversely related; b4 > 0 suggest that x and y aresubstitutes; b3 > 0 suggest that x is a normal commodity with commoditywith positive income-effect.Given the estimated value of and b i, you may forecast the expected sales (D X), ifyou know the future values of explanatory variables like own price (P X), relatedprice (Py), income (B) and advertisement (A). Lastly, you may also recall that thestatistics R2 (Co-efficient of determination) gives the measure of goodness of fit.The closer it is to unity, the better is the fit, and that way you get a more reliableforecast.The principle advantage of this method is that it is prescriptive as welldescriptive. That is, besides generating demand forecast, it explains why thedemand is what it is. In other words, this technique has got both explanatory andpredictive value. The regression method is neither mechanistic like the trendmethod nor subjective like the opinion poll method. In this method of forecasting,you may use not only time-series data but also cross-section data. The only
  9. 9. precaution you need to take is that data analysis should be based on the logic ofeconomic theory. Simultaneous Equations Method: Here is a very sophisticated method offorecasting. It is also known as the ‘complete system approach’ or ‘econometricmodel building’. In your earlier units, we have made reference tosuch econometric models. Presently we do not intend to get into thedetails of this method because it is a subject by itself. Moreover, this method isnormally used in macro-level forecasting for the economy as a whole; in thiscourse, our focus is limited to micro elements only. Of course, you, as corporatemanagers, should know the basic elements in such an approach.The method is indeed very complicated. However, in the days of computer, whenpackage programmes are available, this method can be used easily toderive meaningful forecasts. The principle advantage in this method isthat the forecaster needs to estimate the future values of only theexogenous variables unlike the regression method where he has to predictthe future values of all, endogenous and exogenous variables affecting thevariable under forecast. The values of exogenous variables are easier topredict than those of the endogenous variables. However, sucheconometric models have limitations, similar to that of regression method.Thus we may conclude that each and every method has its own meritsand demerits and we need to bare in mind this when we select a particular tool.ExercisesHow is the slope of demand curve different from price elasticity of demand?---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------You can verify in the above numerical that the elasticity will have the same valuewhether you consider a price fall from Rs. 3 or prices rise from Rs. 3 to Rs. 4..................................................................................................................................................................................................................................................................................................................................................................................................................................................................................Complete the table below:
  10. 10. Unitary ealstic %∆Q=%∆PRelatively elastic e>1Perfectly elastic %∆P=0Relatively inelastic e <1Perfectly inelastic %∆Q=0 Given the following table on price and quantity, determine whether demand iselastic, unitary elastic, or less elastic when price rises from Rs. 7 to Rs. 8.Price of commodity Quantity demanded ofgasoline gasoline(Rs. per litre) (in litres) 10 100 9 120 8 150 7 175 6 180 Why does the Government prefer to levy an excise tax on commodities which are less elastic in demand (like gasoline)? ................................................................................................................................. ................................................................................................................................. ................................................................................................................................. .............................................................................. If you complete the following table, as an exercise, you should be absolutely clear about the concepts and measure of different types of elasticities:Values Zero One Greater LessConcepts than one than onee dQ dQ dP dP dQ dP dQ dP =0 = ----- - = 0 ---- - > ----- - < Q -- - P -- -- - Q P Q P Q P eij er ea E In the above table, the symbols stand for:
  11. 11. Elasticity Assumptione = own price or direct priceelasticity of demand Qx = a (Px)eij = Qi = f (Pj)er = Qx = r(R)ea = Qx = a (A) X1/Xs= 2 = X (MRS x1-x2) P1E= +1 = P (Pt) d ded = Discretionary income elasticity of E e = c (1 )demand for consumer durables. Note : The assumptions a restatement from the generalized demand function you have seen earlier except the Dx and a symbol has been replaced by Qx, and d that D e stands for expenditure on consumer durable, Id for discretionary income, and ed is accordingly termed. You should now be in a position to coin any term of elasticity or use a symbol which has a typical appeal to you. In developed countries, market experiments are used to assess the demand function for a particular product. By this method, product prices are varied from time to time or between different regions of the country, and then the impact of such price-variation on sales is assessed. Comment on the uses and abuses of such a method of demand forecasting. ................................................................................................................................. ................................................................................................................................. ................................................................................................................................. ................................................................................................................................. ................................................................................................................................. ................................................................................................................................. . List the demand forecasting techniques which are based on consumers’ interview. ................................................................................................................................. ................................................................................................................................. ................................................................................................................................. ................................................................................................................................. ................................................................................................................................. ................................................................................................................................. Recall your understanding of the concepts of prediction, projection
  12. 12. and forecasting. What is the significance of demand forecasting?
  13. 13. Distinguish between the following types of forecasts: 1) Economic and Non-economic forecasts 2) Micro and Macro forecasts 3) Short-term and Long-term forecasts 4) Conditional and non-conditional forecasts 5) Ex-ante and Ex-post forecasts.What is the role of time element in the context of demand forecasting?What factors would you normally consider in choosing a forecasting technique?Discuss the suitability of forecasting technique, if you want to forecast thedemand for: 1) Coal 2) Car 3) Plastic tea-cups and saucers 4) New productJoel Dean has suggested the following set of approaches withregard to techniques of forecasting the demand for new products: 5) Evolutionary Approach 6) Substitute Approach 7) Growth Curve Approach 8) Opinion Poll Approach 9) Sales Experience Approach 10) Vicarious Approach Explain each of these approaches separately. Note: Some of these terms may be new; but if you get back to recommended reading No. 3 by Joel Dean and run down those few pages, you should be able to discover all these approaches in this unit itself. And then you can attempt integration. Compare and contrast briefly the simultaneous equation and the regression methods of demand forecasting......................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................
  14. 14. .................................................................................................................................Since statistics can prove or disprove anything, it is better to use non-statisticalmethods for forecasting. One such non-statistical method, which is freefrom subjectivity, is the Historical Analogy Method. Under this method, thedemand forecasting is done in two stages: 1)selection of a country A which sometime in the past (periodt*), particularly with respect to industry i, the demand of whose product isunder forecasting, was in the same stage of development as country B forwhich forecasts are being made at present (period t), 2)forecasting of the demand for industry i’s product in country B in periodt + 1, t + 2 .................., t + n on the basis of actual demand of that industry’sproduct in country A in periods t* + 1, t* + 2, .............. t* + n. Thus, the size of colour TV demand in India in 1988 is approximately the same as the one experienced by the USA in 1968. On the assumption of this 20 years lag, as per this method, India’s demand in 1998 will roughly be the same as USA’s demand in 1978. State the limitations of this method.Draw a tree diagram indicating the Methods of Demand ForecastingAs a manager, you should predict the event, project the course of variables andforecast the data. Keeping this in mind, fill in the blanks in the table below. Notethe suggested guideline.Manager type Predicted event Forecast dataMarketing Manager Demand recession Sales volumeFinance Manager Cash flowpersonnel Manager Employee turnover Machine breakdown Costs of productionProduction Manager Imported material contentADDITIONALREADINGS
  15. 15. Adhikary, M. (1987) Managerial Economics, Khosla Publishing House: N. Delhi(Ch. VIII).Gupta, G.S. (1974) ‘Forecasting Techniques’, Management Annual, Vol. IV, Nov.1974, pp. 8-21.Dean, Joel (1976) Managerial Economics, Prentice-Hall of India: N. Delhi(Ch. IV).Chopra, O.P. (1984) Managerial Economics, Tata-McGraw Hill. .Appendix 1) Linear trend : D = a + dT where D is the demand for the productunder forecast, T is the trend variable which may be normalized to take the value of1 in the first period, 2 in the second period and so on a (intercept) and b (slope) areparametric information which can be estimated. The trend line assumes thatthere will be a constant absolute amount of change (=b) every period. bT2) Exponential trend : D = ae or logeD = loge a + bT. This semi-log function-assumes a constant growth rate = b each period. 23) Second (and higher) degree polynomials trend : D = a + dT + cTIn this case, the slope of the parabola is given by the term dD and it changes dTdirection only once, either from positive to negative or vice-versa. The shape andlocation with respect to axis will vary according to the values of constant a, b andc. biv) Double-log (Cobb-Douglas type) trend : D = aT
  16. 16. or, log eD = loge a + b loge TThis double-log trend assumes a constant elasticity = b every period.POINTS TO PONDER _______________Slide 1 _______________ Demand forecasting ______________ _____ ______________ MeaningMe of forecasting: _______________ _______ Forecasting forwardrwa projectionpro of data_______________ ______________ Also known as sales forecasting _____ ______________ _______________ _______ _______________ ______________ _____ ______________ _______________ _______ _______________ ______________ _____ ______________ _______________ _______Slide 2 _______________ ______________ Need forfo demandnd _____ forecasting ______________ Demand forecasting is needeed _______________ _______ concepts and theth techniquestec _______________ ______________ _____ ______________ _______________ _______ _______________ ______________ _____ ______________ forecastingca canca be appliedpli _______
  17. 17. Slide 3 __________________________________ _ __________________________________ _ __________________________________ _ __________________________________ _ __________________________________ _ __________________________________ Types of forecast _Economiconom and Non-economic forecast __________________________________MicroMi and MacroMa forecastActiveAct and passivepa forecastfoca _ forecConditionalitio and nonno-conditionalnd astfo runru and long runrunShortSh forecastre
  18. 18. Slide 3 __________________________________ _ __________________________________ _ __________________________________ _ __________________________________ _ __________________________________ _ __________________________________ Types of forecast _Economiconom and Non-economic forecast __________________________________MicroMi and MacroMa forecastActiveAct and passivepa forecastfoca _ forecConditionalitio and nonno-conditionalnd astfo runru and long runrunShortSh forecastre
  19. 19. Slide 3 __________________________________ _ __________________________________ _ __________________________________ _ __________________________________ _ __________________________________ _ __________________________________ Types of forecast _Economiconom and Non-economic forecast __________________________________MicroMi and MacroMa forecastActiveAct and passivepa forecastfoca _ forecConditionalitio and nonno-conditionalnd astfo runru and long runrunShortSh forecastre

×