Broadly speaking, there are two approaches to demand forecasting. Survey method and Statistical method are further sub-divided into various methods.
The former obtains information about the consumers’ intentions by conducting consumers’ interviews, through collecting experts’ opinions. The later using past experience as a guide and by extrapolating past statistical- relationships suggests the level of future demand. Survey methods are found appropriate for short term forecasting or demand estimation, while statistical methods are more suitable for long term demand forecasting or business and economic forecasting. Either of the methods may be used for forecasting demand for existing products, but the demand for new products, in the absence of any historical data, must be forecast through the survey method only.
Under survey methods surveys are conducted about the consumers’ intentions, opinions of experts, survey of managerial plans, or of markets. Data obtained through these methods are analyzed, and forecasts on demand are made. These methods are generally used to make short-run forecast of demand.
The former obtains information about the consumers’ intentions by conducting consumers’ interviews, through collecting experts’ opinions. The later using past experience as a guide and by extrapolating past statistical- relationships suggests the level of future demand. Survey methods are found appropriate for short term forecasting or demand estimation, while statistical methods are more suitable for long term demand forecasting or business and economic forecasting. Either of the methods may be used for forecasting demand for existing products, but the demand for new products, in the absence of any historical data, must be forecast through the survey method only.
Under survey methods surveys are conducted about the consumers’ intentions, opinions of experts, survey of managerial plans, or of markets. Data obtained through these methods are analyzed, and forecasts on demand are made. These methods are generally used to make short-run forecast of demand.
Survey methods are further sub-divided in to:
Consumers’ survey involves direct interview of the potential consumers who are contacted by the interviewer and asked how much they would be willing to buy a given product at different prices. Consumers’ survey may take any form as:
- Consumers’ Survey and
- Experts’ Opinion and
- Survey of Managerial Plans.
Consumers’ survey involves direct interview of the potential consumers who are contacted by the interviewer and asked how much they would be willing to buy a given product at different prices. Consumers’ survey may take any form as:
- Complete Enumeration
- Sample Survey, or
- End-Use Method
1. Complete Enumeration Method:
In complete enumeration survey, all the consumers of the product are contacted and asked to indicate their plans to purchasing the production in question for the forecast period. The demand forecast for the total census consumption is obtained simply by adding the intended demand of all consumers as
DF = Id 1 + ID2 + ……IDn
In complete enumeration survey, all the consumers of the product are contacted and asked to indicate their plans to purchasing the production in question for the forecast period. The demand forecast for the total census consumption is obtained simply by adding the intended demand of all consumers as
DF = Id 1 + ID2 + ……IDn
Where,
DF = demand forecast for all consumers,
ID1 = intended demand of consumer 1.
D2 = intended demand of consumer 2.
The probably demand of all the consumers are summed up to obtain the sales forecast. This method facilitates the collection of first hand information and is free from bias. The method has its share of disadvantages too. This method can be applied in case of those products only whose consumers are located in a certain region. If the consumers of the product are widely dispersed, this method proves to be costly and time consuming. Demand estimation through this method may not be reliable because consumers have not thought out in advance what they would do in these hypothetical situations. Also
DF = demand forecast for all consumers,
ID1 = intended demand of consumer 1.
D2 = intended demand of consumer 2.
The probably demand of all the consumers are summed up to obtain the sales forecast. This method facilitates the collection of first hand information and is free from bias. The method has its share of disadvantages too. This method can be applied in case of those products only whose consumers are located in a certain region. If the consumers of the product are widely dispersed, this method proves to be costly and time consuming. Demand estimation through this method may not be reliable because consumers have not thought out in advance what they would do in these hypothetical situations. Also
- consumers may not be aware of their exact demand and hence may not be able or willing to answer the questions;
- the consumers may give hypothetical answers to hypothetical questions;
- their responses may be biased according to their own expectations about the market conditions; and
- their plans may get altered with alterations in the factors not included in the questionnaire.
- when we consider the effects of advertising on demand, the issues of such a direct enquiry approach becomes even more evident.
2. Sample Survey Method:
Useful data for forecasting demand can also be obtained from surveys of consumer plans. Unlike the complete enumeration method, under the sample survey method, only a few potential consumers from the relevant market selected through an appropriate sampling method, are interviewed. The survey may be conducted either through direct-interview or mailed questionnaire to the sample consumers. The total demand may be forecast with the help of following formula:
Useful data for forecasting demand can also be obtained from surveys of consumer plans. Unlike the complete enumeration method, under the sample survey method, only a few potential consumers from the relevant market selected through an appropriate sampling method, are interviewed. The survey may be conducted either through direct-interview or mailed questionnaire to the sample consumers. The total demand may be forecast with the help of following formula:
N
DF =, (ID + ID + …..ID) (n)
Where N= the population of consumers, N sample surveyed
Then the probable demand expressed by each selected unit is summed up to get the total demand for the forecast period. Total sample demand is then multiplied by the ratio of number of consuming units in the population to the number of consuming units in the sample. If the sample selected is adequately representative of the population, the results of the sample are more likely to be similar with the results of the population. This method is simpler, economical and time- saving as compared to the complete enumeration survey. Although surveys of consumer demand can provide useful data for demand forecasting, their importance depends on the skills of their initiators. Effective surveys need careful focus to each phase of the process. In order to avoid ambiguity questions must be precisely worded. The sample ought to be properly selected so that responses will be representative of all customers. Ultimately, the administration of survey methods should produce a high response rate and avoid biasing the answers of those surveyed or A nonrandom sample or poorly phrased questions can result in data of little value.
Even the most carefully designed surveys do not always predict consumer demand with adequate accuracy. In certain cases, respondents do not possess adequate information to determine if they would buy a product. In other conditions the respondents may be short of time and may be unwilling to devote much thought to their answers. Many a times the response may demonstrate a desire to put oneself in a favorable light or to gain approval from those administering the survey. For these limitations, forecasts rarely rely completely on results of consumer surveys. Therefore, these data are taken as supplemental sources of information for decision- making.
3. End-use Method: The end-use method of demand forecasting has considerable amount of both theoretical and practical values. This method involves a survey of firms in all industries using the product and projects the sale of the product under consideration based on demand survey of the industries using this product as an intermediate product. Demand for the final product is the end-user demand of the intermediate product used in the production of this final product.
The end-use technique of demand forecasting comprises of four different stages of estimation.
(1) Obtain the information about the potential uses of the product in question...
(2) Determine suitable technical ‘norms’ of consumption for each and every use of the product under study.
(3) For the application of the norms, it is necessary to know the desired or targeted levels of output of the individual industries for the reference year and also the likely development in other economic activities which use the product and the likely output targets.
(4) Finally, the product-wise content of the item for which the demand is to be forecast, is aggregated which gives the estimate of demand for the product as a whole for the as a whole for the terminal year in question.
Thus, end-use demand estimation of an intermediate product may involve many final goods industries using this product at home and abroad. Once the demand for final consumption goods including their export net of imports is known, the demand for the product used as intermediate good in the production of these final consumption goods with the help of input-output coefficients can be estimated. The input-output tables containing input-output coefficients for particular periods are made available in every country either by the government or by research organizations. Except in the case of intermediate products, demand forecasting through end-use method is neither desirable nor feasible. Further, as the number of end-users of a product increases it becomes more and more inconvenient to use this method. This method is quite useful for industries that are largely producers' goods.
Making forecasts by this method requires building up a schedule of probable aggregate demand for inputs in future by consuming industries and various sectors. This method takes care of, structural and technological changes that might influence the demand. This aspect of the end-use approach is of particular importance.
(1) It helps to estimate the future demand for an industrial product in considerable detail by types and size. By probing into the present use-pattern of consumption of the product, the end use approach affords every opportunity to determine the types, categories and sizes likely to be demanded in future.
(2) The method assists to trace and pinpoint at any time in future as to where and why the actual consumption has deviated from the estimated demand. Suitable revisions can also be made from time to time based on such examination.
DF =, (ID + ID + …..ID) (n)
Where N= the population of consumers, N sample surveyed
Then the probable demand expressed by each selected unit is summed up to get the total demand for the forecast period. Total sample demand is then multiplied by the ratio of number of consuming units in the population to the number of consuming units in the sample. If the sample selected is adequately representative of the population, the results of the sample are more likely to be similar with the results of the population. This method is simpler, economical and time- saving as compared to the complete enumeration survey. Although surveys of consumer demand can provide useful data for demand forecasting, their importance depends on the skills of their initiators. Effective surveys need careful focus to each phase of the process. In order to avoid ambiguity questions must be precisely worded. The sample ought to be properly selected so that responses will be representative of all customers. Ultimately, the administration of survey methods should produce a high response rate and avoid biasing the answers of those surveyed or A nonrandom sample or poorly phrased questions can result in data of little value.
Even the most carefully designed surveys do not always predict consumer demand with adequate accuracy. In certain cases, respondents do not possess adequate information to determine if they would buy a product. In other conditions the respondents may be short of time and may be unwilling to devote much thought to their answers. Many a times the response may demonstrate a desire to put oneself in a favorable light or to gain approval from those administering the survey. For these limitations, forecasts rarely rely completely on results of consumer surveys. Therefore, these data are taken as supplemental sources of information for decision- making.
3. End-use Method: The end-use method of demand forecasting has considerable amount of both theoretical and practical values. This method involves a survey of firms in all industries using the product and projects the sale of the product under consideration based on demand survey of the industries using this product as an intermediate product. Demand for the final product is the end-user demand of the intermediate product used in the production of this final product.
The end-use technique of demand forecasting comprises of four different stages of estimation.
(1) Obtain the information about the potential uses of the product in question...
(2) Determine suitable technical ‘norms’ of consumption for each and every use of the product under study.
(3) For the application of the norms, it is necessary to know the desired or targeted levels of output of the individual industries for the reference year and also the likely development in other economic activities which use the product and the likely output targets.
(4) Finally, the product-wise content of the item for which the demand is to be forecast, is aggregated which gives the estimate of demand for the product as a whole for the as a whole for the terminal year in question.
Thus, end-use demand estimation of an intermediate product may involve many final goods industries using this product at home and abroad. Once the demand for final consumption goods including their export net of imports is known, the demand for the product used as intermediate good in the production of these final consumption goods with the help of input-output coefficients can be estimated. The input-output tables containing input-output coefficients for particular periods are made available in every country either by the government or by research organizations. Except in the case of intermediate products, demand forecasting through end-use method is neither desirable nor feasible. Further, as the number of end-users of a product increases it becomes more and more inconvenient to use this method. This method is quite useful for industries that are largely producers' goods.
Making forecasts by this method requires building up a schedule of probable aggregate demand for inputs in future by consuming industries and various sectors. This method takes care of, structural and technological changes that might influence the demand. This aspect of the end-use approach is of particular importance.
(1) It helps to estimate the future demand for an industrial product in considerable detail by types and size. By probing into the present use-pattern of consumption of the product, the end use approach affords every opportunity to determine the types, categories and sizes likely to be demanded in future.
(2) The method assists to trace and pinpoint at any time in future as to where and why the actual consumption has deviated from the estimated demand. Suitable revisions can also be made from time to time based on such examination.
A. OPINION POLL METHODS: The opinion poll methods make demand estimation by using opinions of those who possess knowledge of the market, such as professional marketing experts and consultants, sales representatives and executives. The collective judgment of knowledgeable persons can be an important source of data. In fact, some forecasts are done almost entirely on the basis of personal insights of key decision makers involving managers conferring to develop projections based on their assessment of economic conditions encountering the firm. In other situations, the company sales’ personnel may be enquired to assess future prospects. In other cases, consultants may be hired to develop forecasts based on their knowledge of the business. These methods consist of:
1. Experts’ Opinion: The researcher identifies the experts on the commodity whose demand forecast is being estimated, and investigates with them on the probably demand for the product in the forecast period. This method consists of securing views of the salesmen and/or sales management personnel. There are many variations. The combined view of the sales force as to future sales expectations may be secured by carefully scrutinizing at successive executive levels and future sales estimates submitted by the salesmen individually. Another method would be to rely only on the specialized knowledge of the company's sales executives in preparing sales forecasts.
The advantages consist of: This method makes use of specialized knowledge of persons closest to the market; provides sales force with greater confidence in getting sales quotas developed; greater stability through magnitude of sample; placing of responsibility for the forecasts on those who are expected to produce results; and
The disadvantages are that:a. Salesmen are poor estimators being unduly optimistic; b. Salesmen are often unaware of the broad economic patterns and cannot forecast long-term trends; c. The sales force's time is in this way curtailed for the primary job of selling; and; d. Salesmen may intentionally understate the demand if quotas are set on the basis of this information.
2. Delphi Method:
Under Delphi method opinions are collected from experts and efforts are made to match them. This is done by bringing the experts together, arranging meetings and arriving at some narrow range for the forecast under attempt to give the interval forecast directly and for arriving at a point forecast by tampering it with the overall assessment of the researcher or the coordinator of the forecasting exercise. Generally, the forecast proceeds through the following stages.
(i) Request is made to all the experts of product to give their individual estimates for the likely demand.
(ii) If the difference in forecasts is significant, the experts are invited for a conference on the subject, present the problem with regard to differences in their estimates. By arguing, convincing other and getting convinced, exchanging views with colleagues efforts are made to narrow the limits for likely demand.
(iii) If the range of variations is still large the exercise continues till the coordinator is able to arrive at an acceptable range
(iv) Declare the so arrived range as the interval demand forecast for the product for the period for which it is done.
(v) Take a simple average of the lower and upper values of the forecast and declare the point forecast for the variable under forecasting.
The use of Delphi technique can be explained where a panel of six outside experts is asked to forecast a firm's sales for the next year. Working in an independent manner, two panel experts estimate an 8 percent increase, three members assess a 5 percent increase, and one person makes no increase in sales. On the basis of the responses of the other experts, each expert is then asked to revise his sales forecast. Expert expecting rapid sales growth on the basis of the judgments of other expert, may present less optimistic forecasts in the second round. On the contrary, experts predicting slow growth may revise their responses upward. However, there may be some experts who make no adjustment of their initial forecast. Suppose that a second round of predictions by the experts includes one estimate of a 2 percent, one of 5 percent, two of 6 percent, and two of 7 percent. The panel members again are shown each other's responses and asked to revise their forecasts further. This process goes on till a consensus is arrived or until further repeatition generate little or no change in sales estimates. Delphi method is quite is quite sound but it could be tedious and costly. In the situations where the number of experts is not too large and they are co-cooperative, and the researcher has the necessary fund and the authority to perform the task, the Delphi method could be appropriate for demand forecasting.
The value of the Delphi technique is that it aids individual panel members in assessing their forecasts. They are asked to consider why their judgment differs from that of other experts. This estimation process should bring out more precise forecasts than other processes. The usefulness of expert opinion depends on the skill and insight of the experts employed to make predictions. One problem with the Delphi method can be its expense. Frequently, the most knowledgeable people in an industry are in a position to command large fees for their work as consultants. They may be hired by the firm, but have other important responsibilities. This implies that there can be a significant opportunity cost in involving them in the planning process. Moreover, experts are unwilling to be influenced by the predictions of others on the panel. Although predictions by experts are not always the product of "hard data," their usefulness should not be undervalued. Really, the insights of closely connected with a business can be of great value in forecasting
(c) Surveys of Managerial Plans:
Surveys of managerial plans can be an important source of data for forecasting demand. The logic of conducting such surveys is that plans generally form the basis of future activities. For example, capital expenditure budgets for large corporations are usually planned in advance. Thus a survey of investment plans by such corporations should make available a reasonably accurate forecast of future demand for capital goods.
(d) Market Experiments:
Market experiments (actual or simulated) are performed to generate demand forecasts. A potential problem with survey method is that survey responses may not translate into actual consumer behavior. Consumers do not necessarily do what they say they are going to do. This weakness can partially be overcome by use of market experiments designed to generate data prior to the full-scale introduction of a product or implementation of a policy. Market experiment can be performed in two forms:
1. Test Market :
In order to set a market experiment the firm first selects a test market that may consist of different cities, a part of the country, or a representative sample of consumers taken from a mailing list. The experiment may incorporate a number of features such as evaluating consumers’ perception of a new product in the test area. Different prices for an existing product might be set in various cities in order to determine elasticity of demand in other cases. Another possibility would be a test of consumer reaction to a new advertising campaign. There are several factors that managers should consider in selecting a test market. The size of the location should be manageable. Too large an area may be costly and difficult to conduct the experiment and to analyze the data. Another, the sample of the test market should be representative of the overall population of the in age, education, and income otherwise the results may not be generalized to other areas. Ultimately, it should be possible to engage advertising that is directed only to those who are being tested.
2. Laboratory Tests :
Another way of conducting market experiment is consumer clinic or controlled laboratory experiment. Here, consumers are given some money to buy in a stipulated store goods with varying prices, packages; displays etc. and consumers’ responsiveness to these variations are studied. Thus the laboratory experiment and the field market experiment yield the same results.
Market experiments have an advantage over surveys in that they reflect real consumer behavior. Market experiments have limitations. It involves risk. In test markets once prices are raised, consumer may go to products of competitors. When the experiment has ended and the price is brought to its original level, it may be difficult to bring back those customers. Also the firm cannot manager all the factors that influence demand. Bad weather, changing economic scenario or the tactics of competitors can also influence the results of some market experiments. Since experiments are of relatively short duration, consumers may not be completely aware of pricing or advertising changes and their responses may understate the probable impact of those changes.
Limitations:
The market experiment methods have certain serious limitations that reduce the reliability of the method considerably. Experimental methods are very expensive so small firms cannot afford them. Being a costly affair, experiments are usually carried out on a scale too small to permit generalization with a high degree of reliability. Experimental methods are based on short-term and controlled conditions that are difficult to be found in an uncontrolled market. Therefore, the results may not be applied to the uncontrolled long-term conditions of the market. Changes in socio-economic conditions taking place during the field experiments, such as local strikes or lay-offs, advertising program by competitors, political changes, natural calamities, may invalidate the results. "Tinkering with price increases may cause a permanent loss of customers to competitive brands that might have been tried. Despite these limitations, however, market experiment method is often used to provide an alternative estimate of demand, and also as a check on results obtained from statistical studies. Besides, this method generates elasticity coefficients which are necessary for statistical analysis of demand relationships.
1. Experts’ Opinion: The researcher identifies the experts on the commodity whose demand forecast is being estimated, and investigates with them on the probably demand for the product in the forecast period. This method consists of securing views of the salesmen and/or sales management personnel. There are many variations. The combined view of the sales force as to future sales expectations may be secured by carefully scrutinizing at successive executive levels and future sales estimates submitted by the salesmen individually. Another method would be to rely only on the specialized knowledge of the company's sales executives in preparing sales forecasts.
The advantages consist of: This method makes use of specialized knowledge of persons closest to the market; provides sales force with greater confidence in getting sales quotas developed; greater stability through magnitude of sample; placing of responsibility for the forecasts on those who are expected to produce results; and
The disadvantages are that:a. Salesmen are poor estimators being unduly optimistic; b. Salesmen are often unaware of the broad economic patterns and cannot forecast long-term trends; c. The sales force's time is in this way curtailed for the primary job of selling; and; d. Salesmen may intentionally understate the demand if quotas are set on the basis of this information.
2. Delphi Method:
Under Delphi method opinions are collected from experts and efforts are made to match them. This is done by bringing the experts together, arranging meetings and arriving at some narrow range for the forecast under attempt to give the interval forecast directly and for arriving at a point forecast by tampering it with the overall assessment of the researcher or the coordinator of the forecasting exercise. Generally, the forecast proceeds through the following stages.
(i) Request is made to all the experts of product to give their individual estimates for the likely demand.
(ii) If the difference in forecasts is significant, the experts are invited for a conference on the subject, present the problem with regard to differences in their estimates. By arguing, convincing other and getting convinced, exchanging views with colleagues efforts are made to narrow the limits for likely demand.
(iii) If the range of variations is still large the exercise continues till the coordinator is able to arrive at an acceptable range
(iv) Declare the so arrived range as the interval demand forecast for the product for the period for which it is done.
(v) Take a simple average of the lower and upper values of the forecast and declare the point forecast for the variable under forecasting.
The use of Delphi technique can be explained where a panel of six outside experts is asked to forecast a firm's sales for the next year. Working in an independent manner, two panel experts estimate an 8 percent increase, three members assess a 5 percent increase, and one person makes no increase in sales. On the basis of the responses of the other experts, each expert is then asked to revise his sales forecast. Expert expecting rapid sales growth on the basis of the judgments of other expert, may present less optimistic forecasts in the second round. On the contrary, experts predicting slow growth may revise their responses upward. However, there may be some experts who make no adjustment of their initial forecast. Suppose that a second round of predictions by the experts includes one estimate of a 2 percent, one of 5 percent, two of 6 percent, and two of 7 percent. The panel members again are shown each other's responses and asked to revise their forecasts further. This process goes on till a consensus is arrived or until further repeatition generate little or no change in sales estimates. Delphi method is quite is quite sound but it could be tedious and costly. In the situations where the number of experts is not too large and they are co-cooperative, and the researcher has the necessary fund and the authority to perform the task, the Delphi method could be appropriate for demand forecasting.
The value of the Delphi technique is that it aids individual panel members in assessing their forecasts. They are asked to consider why their judgment differs from that of other experts. This estimation process should bring out more precise forecasts than other processes. The usefulness of expert opinion depends on the skill and insight of the experts employed to make predictions. One problem with the Delphi method can be its expense. Frequently, the most knowledgeable people in an industry are in a position to command large fees for their work as consultants. They may be hired by the firm, but have other important responsibilities. This implies that there can be a significant opportunity cost in involving them in the planning process. Moreover, experts are unwilling to be influenced by the predictions of others on the panel. Although predictions by experts are not always the product of "hard data," their usefulness should not be undervalued. Really, the insights of closely connected with a business can be of great value in forecasting
(c) Surveys of Managerial Plans:
Surveys of managerial plans can be an important source of data for forecasting demand. The logic of conducting such surveys is that plans generally form the basis of future activities. For example, capital expenditure budgets for large corporations are usually planned in advance. Thus a survey of investment plans by such corporations should make available a reasonably accurate forecast of future demand for capital goods.
(d) Market Experiments:
Market experiments (actual or simulated) are performed to generate demand forecasts. A potential problem with survey method is that survey responses may not translate into actual consumer behavior. Consumers do not necessarily do what they say they are going to do. This weakness can partially be overcome by use of market experiments designed to generate data prior to the full-scale introduction of a product or implementation of a policy. Market experiment can be performed in two forms:
1. Test Market :
In order to set a market experiment the firm first selects a test market that may consist of different cities, a part of the country, or a representative sample of consumers taken from a mailing list. The experiment may incorporate a number of features such as evaluating consumers’ perception of a new product in the test area. Different prices for an existing product might be set in various cities in order to determine elasticity of demand in other cases. Another possibility would be a test of consumer reaction to a new advertising campaign. There are several factors that managers should consider in selecting a test market. The size of the location should be manageable. Too large an area may be costly and difficult to conduct the experiment and to analyze the data. Another, the sample of the test market should be representative of the overall population of the in age, education, and income otherwise the results may not be generalized to other areas. Ultimately, it should be possible to engage advertising that is directed only to those who are being tested.
2. Laboratory Tests :
Another way of conducting market experiment is consumer clinic or controlled laboratory experiment. Here, consumers are given some money to buy in a stipulated store goods with varying prices, packages; displays etc. and consumers’ responsiveness to these variations are studied. Thus the laboratory experiment and the field market experiment yield the same results.
Market experiments have an advantage over surveys in that they reflect real consumer behavior. Market experiments have limitations. It involves risk. In test markets once prices are raised, consumer may go to products of competitors. When the experiment has ended and the price is brought to its original level, it may be difficult to bring back those customers. Also the firm cannot manager all the factors that influence demand. Bad weather, changing economic scenario or the tactics of competitors can also influence the results of some market experiments. Since experiments are of relatively short duration, consumers may not be completely aware of pricing or advertising changes and their responses may understate the probable impact of those changes.
Limitations:
The market experiment methods have certain serious limitations that reduce the reliability of the method considerably. Experimental methods are very expensive so small firms cannot afford them. Being a costly affair, experiments are usually carried out on a scale too small to permit generalization with a high degree of reliability. Experimental methods are based on short-term and controlled conditions that are difficult to be found in an uncontrolled market. Therefore, the results may not be applied to the uncontrolled long-term conditions of the market. Changes in socio-economic conditions taking place during the field experiments, such as local strikes or lay-offs, advertising program by competitors, political changes, natural calamities, may invalidate the results. "Tinkering with price increases may cause a permanent loss of customers to competitive brands that might have been tried. Despite these limitations, however, market experiment method is often used to provide an alternative estimate of demand, and also as a check on results obtained from statistical studies. Besides, this method generates elasticity coefficients which are necessary for statistical analysis of demand relationships.
No comments:
Post a Comment