The forecasting of the mobile Internet in Taiwan by diffusion model

From the government's perspective, it is very important to estimate the growing path of the mobile Internet market and then to forecast the trend. The purpose of this paper is to propose a diffusion model that reveals the growth pattern of the mobile Internet subscriber in Taiwan utilizing the concepts of the “technical substitution” and the “multi-product competition”, which suits the characteristics in the mobile Internet market in Taiwan. From the regression results, the estimated ultimate market potential of GPRS is 6.4 million, which is going to saturate in about 2008Q1. On the other hand, the estimated range of the market potential of PHS/3G is about 7.2 to 8.0 million. That is, the total mobile Internet market in Taiwan is forecasted to be around 13.6 to 14.4 million subscribers.     

A product diffusion model incorporating repeat purchases

A logistic-based model for forecasting the rate of product diffusion given aggregate time series data was constructed. The model differs from earlier models based on fitting the logistic to aggregate data in that it includes a submodel to separate replacement demand from first-time sales. We fit the theoretical model to data and show that forecasts will be significantly more accurate using this model instead of the logistic curve.     

Spanish diffusion indexes

We use the Stock-Watson diffusion index methodology to summarize the information contained in a wide set of monthly series (published in the Statistical Bulletin of the Bank of Spain) by means of a reduced number of factors. We find that the first two factors may be used as indicators of the core inflation and the business cycle dynamics of the Spanish economy, respectively. In addition, we study the effects of incorporating large information sets for the analysis of monetary policy. Finally, we show that forecasting prices and output with our factors outperforms other standard alternative forecasting procedures.JEL Classification: E31, E32, E37We are most grateful to Pilar Bengoechea, Ramón María-Dolores, and Javier Vallés for valuable comments. We would like to thank Gabriel Pérez-Quirós and two anonymous referees for constructive suggestions leading to improvements in the content and presentation of the paper. We however stand responsible for any remaining errors and omissions.     

Multigeneration diffusion model for economic assessment of new technology

In the era of 21st century, development of emerging information technology is the essence of the advancement. This kind of new technology, however, often requires a great deal of amount of initial investment for both procedures of R&D and commercialization. As cost invested in developing the specified technology is increasing, investors are paying more attention to cost to benefit analysis (CBA). One of the basic elements of CBA for new technological development is the diffusion pattern of demand of such technology. Typically, it would be hard to presume the diffusion pattern of demand when the new product or the technology is under development. In this case, a simulation study is necessary. Many studies of technology evaluation have adopted a single generation model to simulate the diffusion pattern of demand. This approach, however, considers the diffusion of the new technology itself, not taking into account newer generation, which can replace the one just invented. In the real market situation, one must consider the competition and substitution phenomena between old and new technologies. In this paper, we show how multigeneration technology diffusion model can be applied for more accurate CBA for information technology. Additionally, Monte Carlo simulation is performed to find influential factors on the CBA of a cybernetic building system (CBS).     

A model of multiple-unit ownership as a diffusion process

This paper develops and tests a new model for multiple-unit adoptions of durable goods based on the diffusion modeling tradition. Multiple-unit adoptions are a major component of sales for many consumer durable product categories. For instance, sales of multiple-unit adoptions for televisions have been higher than both first adoptions and replacement purchases since 1977, while for automobiles, they have represented more than 20% of sales since 1966 in Australia. The structural drivers of multiple-unit adoptions are quite different from either first purchase or replacement purchase. Hence, identifying and modeling the multiple-unit component of sales is important for aggregate sales forecasts. Moreover, consumer requirements for additional units of a product are likely to be considerably different than for the other components of sales (first purchases and replacement purchases). As such, the ratio of the first, multiple, and replacement sales components will strongly influence the product mix requirements of the market.

While forecasting and influencing multiple-unit sales are an important managerial issue, very little attention has been given to multiple-unit ownership in the diffusion modeling literature. The only model available was developed for the purpose of modeling relatively short-term behavior of multiple-unit adoptions, rather than the longer-term pattern of sales. We propose a model of multiple-unit adoptions as a diffusion process.

We apply the model to both color television and automobiles. Analysis of the model's long-term fit and forecasts in these applications provide support for the structure of the new model.     

A fast estimation procedure for discrete choice random coefficients demand model

We document speed-up gains of graphical processing unit (GPU) computing over central processing unit (CPU) for the estimation of discrete choice random coefficient demand model. When we use a moderate-sized GPU, the computation is six to twenty times faster, where the smallest speed-up factor, six, is obtained from a comparison with the parallel computing over sixteen CPU cores.     

On the combination of exponential smoothing and diffusion forecasts: An application to broadband diffusion in the OECD area

The innovation diffusion literature has established that the spread of a successful innovation over time typically follows a sigmoid curve. Therefore, the forecasting in this area has been monopolized by the use of well known aggregate diffusion models. Time series forecasting has been surprisingly neglected, as it provides mainly accurate short term forecasts. In this work, a method of exponential smoothing, the Holt's damped trend with a modification, is applied in recent broadband diffusion data of two large regions after the reach of the inflection point. As validated with holdback sample data ranging from 6 up to 30 months, the key for successful forecasting is the use of the estimated saturation level calculated from a diffusion model, in order to specify the appropriate trend. The results indicate improved predictions compared to two popular diffusion models, the Gompertz and the Linear Logistic model. The paper concludes with the application of the proposed method in a 48-month forecasting horizon, as well as the suggestions for further research.     

A dynamic diffusion model for managing customer's expectation and satisfaction

The paper aims at answering the generic question on how suppliers make the suitable and well-timed decisions in diffusing new technology effectively to adopters. Three major attempts are made for the study: First, investigating the entire process of the adoption and diffusion of technology innovation with reasonably well-accepted models in each areas. Second, proposing an integrated model by concatenating in structured manner the three prominent models for the management of technology innovation such as diffusion model, adoption model, and customer satisfaction model. Third, exploring the dynamic mechanism underlying outward behaviors of the integrated model proposed in the study which depicts the causal relationships that influence technology adoption and diffusion behaviors. An exploration of the dynamic mechanism underlying outward behaviors of the integrated model is presented in the study by introducing the system dynamics simulation technique. These attempts made for the study and the results perhaps allow both researchers and practitioners to gain insight into the causal factors influencing customers' adoption decision making processes and thereby into the potential diffusion patterns resulting from those adoption processes.     

Demand forecasting for multigenerational products combining discrete choice and dynamics of diffusion under technological trajectories

The discrete choice model generally captures consumers' valuation of the product's quality within the framework of a cross-sectional analysis, while the diffusion model captures the dynamics of demand within the framework of a time-series analysis. We propose an adjusted discrete choice model that incorporates the choice behavior of the consumer into the dynamics of product diffusion. In addition, a new estimation structure is proposed, within the framework of the time-series analysis, which enables the estimation of the discrete choice model on market-level data to be performed in such a way as to avoid the problem of price endogeneity and to obtain greater flexibility in forecasting demand. As an empirical application, the suggested model is applied to the case of the worldwide DRAM (dynamic random access memory) market. In forecasting future demand of DRAM generations, we integrate Moore's law and learning by doing to reflect the future technological trajectories of DRAM innovations, as well as consumers' consumption trends to reflect the dynamics of demand environments. As a result, the suggested model shows better performance in explaining the diffusion of new-generation product with limited number of data observations.     

A technology replacement model with variable market potential — An empirical study of CRT and LCD TV

The rapidly changing economic environment and increasingly fierce competition indicate that companies must innovate in both their products and marketing strategies if they are to continue to flourish. Specifically, the ability to accurately predict the demand for products is crucial when firms decide to allocate their resources, especially in the fast moving high technology industries, where there is very high investment in R&D and production facilities. This study establishes a forecast model for technology replacement based on the diffusion model with population growth used for the variable market potential. The proposed model is then applied to investigate the CRT and LCD TV market.The results suggest that the new model is more accurate than the constant market potential model in fitting and forecasting performance. Consumers who purchase a TV for the first time are likely more attracted to LCD TV rather than CRT TV. As for those individuals who already own a CRT TV, the attraction is not strong enough to encourage them to replace their current CRT TV with a new LCD TV. Moreover, it is noted that the falling price of LCD TV is an essential factor in encouraging purchases.     

Discrete choice model analysis of mobile telephone service demand in Japan

This paper analyzes the demand for mobile telephones including second generation (2G) and third generation (3G) by using a discrete choice model called a mixed logit model. First, we examine the substitution patterns of the demand for mobile telephones and show that demand substitutability among alternatives is stronger within the provider nest category than within the standard nest category in mobile telephone services. The closest substitute for NTT’s 3G service is NTT’s 2G service, rather than KDDI’s 3G service, for example. Second, we investigate the elasticities of demand for various functions including e-mail, Web browsing, and moving picture delivery. Consequently, we cannot observe marked differences between 2G and 3G services based on these calculated elasticities, indicating that it takes time for 3G subscribers to gain proficiency with such new services.      

Forecasting future demand for large-screen television sets using conjoint analysis with diffusion model

The methodological framework proposed in this paper addresses two limitations of the basic Bass diffusion model: that it does not reflect competition among products nor does it forecast demand for products that do not exist in the marketplace. The model consists of four steps. First, to investigate consumer preferences for product attributes, we use conjoint analysis to estimate the utility function of consumers. Next we estimate the dynamic price function of each competing product to reflect technological changes and the evolving market environment. Then we derive dynamic utility function by combining the static utility function and the price function. Finally, we forecast the sales of each product using estimated market share and sales data for each period, which are derived from the dynamic utility function and from the Bass diffusion model, respectively.We apply this model to South Korea's market for large-screen televisions. The results show that (1) consumers are sensitive to picture resolution and cost and (2) in the near future, should the market see the introduction of liquid crystal display (LCD) TVs with screens larger than 50 inches, the high resolution and steep price drop of LCD will lead LCD TVs to capture a larger market share than TVs with other display types. Finally, our results show that TVs with 40-inch screens are preferred over TVs with larger screens.     

Modelling intervention options to reduce GHG emissions in housing stock — A diffusion approach

The building sector is regarded as having one of the highest benefit-cost ratios from greenhouse gas (GHG) emission reduction strategies. However, because of uncertainties around household behaviour patterns, it is very difficult to assess and compare the GHG reduction impacts of different intervention schemes for whole housing stock. Intervention schemes include policy instruments such as incentives or rebates for energy efficient appliances or renewable energy, and regulatory building code requirements for energy efficiency. This paper presents a decision support tool based on mathematical diffusion that evaluates the adoption levels of different schemes or pathways towards reducing GHG emissions in housing stock. It is an extension of the Bass diffusion model that accommodates financial and non-financial benefits, ceilings of adoption and interactions between intervention options. The model capability was tested using a case study of seven suburbs in Brisbane, Australia, comprising of 25,000 houses and units. Estimates of GHG emission reductions to 2019 of a household rebate scheme for solar panels and a rebate scheme for solar hot water compared to a base case of no rebates were presented and analysed. Modelling also allowed identification of important characteristics of adoption trends that could assist policy makers and industry to substantially improve the design of effective intervention options.     

A simple agent model of an epidemic

This paper presents an agent model that simulates the spread of an infection in a population. The epidemic depicted could be any attribute that is passed from a one person to others in society, for example, a disease, an idea or belief, a fad, a market or a behavioral pattern. The model was constructed to study the sensitivity of factors such as virility of the infectious agent, the “reach” of the vector and the density of the population in which the epidemic takes place. A further goal was to begin the development of a general-purpose forecasting model based on the use of agents. The model and its results are presented in this paper.     

A general revealed preference theorem for stochastic demand behavior

Summary. We present a general revealed preference theorem concerning stochastic choice behavior by consumers. We show that, when the consumer spends her entire wealth, the Weak Axiom of Stochastic Revealed Preference due to Bandyopadhyay, Dasgupta, and Pattanaik (1999) is equivalent to a restriction on stochastic demand behavior that we call stochastic substitutability. We also show that the relationship between the Weak Axiom of Revealed Preference and Samuelson's inequality in the deterministic theory, and the main result of Bandyopadhyay, Dasgupta, and Pattanaik (1999) are both special cases of our result.Received: 10 September 2001, Revised: 4 April 2003, JEL Classification Numbers: D11. Correspondence to: Prasanta K. PattanaikOur greatest debt is to the referee of this paper, who made numerous helpful suggestions. We thank Robin Cubitt, Kunal Sengupta and seminar audiences at Jawaharlal Nehru University, Indian Statistical Institute, University of East Anglia, Universidad Carlos III, University of Essex and University of Montreal for their helpful comments. Prasanta K. Pattanaik acknowledges his intellectual debt to Salvador Barbera, Tapas Majumdar and Amartya Sen.     

Modelling the faddish, fashionable and efficient diffusion of agricultural technologies: A case study of the diffusion of wool testing technology in Australia

This study investigates the nature of innovation diffusion in an agricultural context. The dominant agricultural diffusion models assume that an economically rational choice is made to adopt or reject agricultural technologies. However, recent studies of agricultural innovation highlight the ‘irrational’ and potentially ‘inefficient’ nature of the diffusion in this context. To investigate how and why agricultural technologies are adopted or rejected, we examine the diffusion of wool testing technologies in the Australian wool industry using the Bass diffusion model and Abrahamson's diffusion and rejection typology. The results show that diffusion of agricultural innovation is not simply an efficient choice made to close observable performance gaps. The findings suggest that the adoption of inefficient innovations and the rejection of efficient innovations can be driven by an adopter's social context, powerful external influences and imitation within an adopter group and that these drivers change over time, suggesting an evolutionary social process underlies the diffusion of agricultural technologies.     

A rank-dependent utility approach to model intra- and inter-individual heterogeneity in risky choice behaviours

ABSTRACT

Using a stated preferences survey, the objective of this paper is to investigate the intra- and inter-individual heterogeneity of mode choice, when travel time is subject to variability. By‘inter-individual heterogeneity’ is meant that people are different in terms of attitude to risk and have different utility functions. By ‘intra-individual heterogeneity’ is meant that the behaviour may be different even when performed by the same individual when faced with a different mode of transport. Based on Rank-Dependent Utility Theory, the paper shows that the occurrence of delays associated with train trips is overestimated whereas they are underestimated for car trips. A latent-class logit model offers a somewhat different perspective: if, overall, car users are more likely to perceive possible delays for train trips than for car trips, train users tend to consider the objective occurrence of delays as they are presented in the survey and adopt a risk neutral choice behaviour.     

Forecasting the diffusion of photovoltaic systems in southern Europe : A learning curve approach

Most analysts disagree upon whether photovoltaic systems (PV) will be able to play an important role in the energy scenarios of the future. A few scholars also question the appropriateness of policies that envisage the use of public subsidies to stimulate the growth of this industry and to accelerate market penetration. This paper contributes to this debate by examining whether carefully designed policies may initiate a process of large-scale diffusion of grid-connected PV, even without the deployment of external subsidies. Building upon a disaggregated characterization of the electricity market, it takes endogenously into account the learning curve phenomenon and simulates the diffusion of PV building-integrated systems in five European countries. The analysis is restricted to crystalline silicon systems and is repeated under four different macroeconomic scenarios corresponding to four different energy policies. The results suggest that already today there are opportunities for PV diffusion in many islands of the Mediterranean region, which may trigger sufficient scale economies to render the technology competitive in larger markets. They also show that the diffusion process could be accelerated through the implementation of carbon-tax policies that support initial penetration. The environmental benefits (net avoided CO₂ emissions over the system life cycle) associated with the forecasted penetration are also evaluated.     

Industrial leadership in science-based industries: A co-evolution model

In this paper, we seek to analyse the role of national university systems in combination with technological and market factors as sources of industrial leadership and industry growth in science-based industries. We propose a model in which national university systems and their respective national firms and industries are considered as co-evolving. National firms compete on a worldwide level and they rely on the progress of science and the availability of scientists to innovate. As the global industry develops, firms try to mold their national university systems, but they achieve different degrees of success. Apart from highlighting the role of institutional responsiveness as a source of competitive advantage, our model points to the access to essential inputs for production, the technological and strategic characteristics of firms, the international diffusion of knowledge, and the initial distribution of market demand as key sources of leadership and industry growth. The international mobility of scientists seems to foster the emergence of industrial leadership shifts.