A Methodology to Improve the Mobile Diffusion Forecasting: the Case of Greece (original) (raw)
Related papers
Modelling and forecasting mobile telecommunication services: the case of Greece
Applied Economics Letters, 2010
In this paper we try to model the adoption pattern of mobile telecommunication services into the Greek market for the period from 1993 to 2005. Two separate sigmoid curves, the Gompertz and the Logistic, are fitted to the observed number of subscribers by means of non-linear least squares. The in-sample fit to data favoured the use of the Logistic curve in describing the diffusion process, fact which is further supported by Frances' parametric test (1994b). The dominance of the Logistic curve over the Gompertz is also verified via a pseudo out-of-sample forecasting exercise. Furthermore, an attempt is made to predict the expected number of subscribers up to 2015, solely based on the Logistic curve. Taking into account the prediction's uncertainty, the variance of the forecast errors is calculated utilising the non-parametric bootstrap method. Our empirical results reached to three conclusions. First, the introduction of the pre-paid mobile telephony in 1997 along with the entry of the third mobile operator in 1998 has boosted the diffusion process in Greece; second, the levelling-off process in the diffusion of mobile phones has already begun; finally, the average expected growth rate in new subscribers is less than half percent for the period between 2006 and 2015.
2018
Growth models, based on the theory of diffusion of innovations, are highly proficient in developing an empirical understanding of country-wide diffusion of mobile services. The currently available literature lacks in explanation of the diffusion of successive generations (G’s) of mobile services in various countries. This study furthers the research by analyzing the diffusion of 2G through 4G in Germany, UK, France and Italy, the four largest economies of Europe. We select Bass, Gompertz and Simple Logistic growth models, to analyze the diffusion process, and forecast the adoption of 3G, 4G and 5G mobile broadband, in the four countries. A comparative analysis of the diffusion model parameters, and the forecasting accuracies, estimated through non-linear least-square regression, determines Gompertz and Simple Logistic model as best suited to explain 3G and 4G diffusion, and Bass model as best suited to explain 2G diffusion. Market potential for 3G, 4G and 5G is the highest in France...
Modeling and Forecasting the Diffusion of Mobile Telephony in Balkan Countries
9th INTERNATIONAL CONFERENCE Information Systems and Technology Innovations - Smart economy and digital transformation, 2019
Mobile telephony has become one of the main factors driving the social and economic development of a country. This study examines the diffusion process of mobile telephony in Albania,. The main objective of this research is to model and to forecast the diffusion rate of mobile telephony using Logistic and Gompertz models, and World Bank data. Results indicated that Logistic model outperform Gompertz model and give the minimum forecast error to mobile telephony diffusion rate for countries in the study excluding Greece. Comparing the estimated parameters of the best fitted models, Bulgaria has the highest estimated speed of diffusion of 0.647, whereas Albania has the lowest diffusion speed (0.178). The results of Logistic model, the best model for prediction of the mobile telephony diffusion rate in Albania, indicate that the maximum level of mobile diffusion of 132% is predicted to be achieved in year 2025. Diffusion of mobile technology of other countries in the study has achieved the maximum level. These findings are useful to customers, telecommunication operators, and policy makers.
Modeling and Forecasting the Diffusion of Mobile Telephony in Albania and Turkey
Journal of Engineering Technology and Applied Sciences
Mobile telephony has become a main factor driving the social and economic development of a country. This study examines the diffusion process of mobile telephony in Albania and Turkey. The aim of this research is to model and to forecast the diffusion rate of mobile telephony using Logistic and Gompertz models, and World Bank data. The results of estimated models indicated that the Gompertz model fits best with the actual data of mobile telephony in Albania, and the Logistic model fits best with the actual data of mobile telephony in Turkey. According to the results of the Logistic model, the best model for predicting the diffusion rate of mobile telephony in Albania, the maximum level of the mobile diffusion rate of 131.89% will be achieved in the year 2025. The results of the Gompertz model, the best model for predicting the mobile telephony in Turkey indicate that the maximum diffusion rate of 97.98% is predicted to be achieved after the year 2025. These findings are useful to telecommunication operators, policymakers, and customers.
Diffusion models of mobile telephony in Greece
Telecommunications Policy, 2008
This paper examines and presents the diffusion rate of mobile telephony subscriptions in Greece. Following the evaluation of the most widely used aggregate technology diffusion models (such as the Bass model, the Fisher-Pry model, the Gompertz models and some representatives of the logistic variants), it becomes evident that these S-shaped models are suitable enough for accurate fitting and forecasting the diffusion of mobile telephony. The analysis of the diffusion process in Greece provides some interesting aspects of mobile penetration such as the correlation between the diffusion speed and the number of competing operators as well as other socioeconomic and regulatory aspects. As a result of the estimation of 2G's diffusion process parameters, the potential market size and the analysis of the techniques for the appropriate model selection, this analysis can be considered as a means of providing an insight into the estimation of the diffusion shapes of the forthcoming generations of mobile telephony and telecommunication products and services in Greece and elsewhere. r
The objective of this paper is to present a short research about the overall broadband penetration in Greece. In this research, a new empirical deterministic model is proposed for the short-term forecast of the cumulative broadband adoption. The fitting performance of the model is compared with some widely used diffusion models for the cumulative adoption of new telecommunication products, namely, Logistic, Gompertz, Flexible Logistic (FLOG), Box-Cox, Richards, and Bass models. The fitting process is done with broadband penetration official data for Greece. In conclusion, comparing these models with the empirical model, it could be argued that the latter yields well enough statistics indicators for fitting and forecasting performance. It also stresses the need for further research and performance analysis of the model in other more mature broadband markets.
Modelling multinational telecommunications demand with limited data
International Journal of Forecasting, 2002
Forecasting the diffusion of innovations in the telecommunications sector is a constantly recurring problem for national providers. The problem is characterised by short data series making the estimation of model parameters unreliable. However, the same innovation will be diffusing simultaneously in other national markets, although with a different start date. The use of this cross-sectional data in constructing innovation diffusion models is investigated here. Four models for pooling the cross-sectional data are described and two diffusion models are discussed although only one, the Gompertz model is used throughout. Three innovation data sets are used in the evaluation of the models: digital cellular telephones, ISDN connections and fax connections. The pooled diffusion forecasts proved to be more accurate in several comparisons relativë to a naıve benchmark and to individual forecasts when available.
Computational Economics, 2007
The objective of this paper is to investigate the impact of the timedelay effect on the diffusion of mobile telecommunication services in EU. It has been proved from several studies that the time-delay between the awareness and the adoption phase of mobile services-potential users determines the speed of the mobile telecommunication service diffusion and can be used effectively for ranking or cluster purposes in cases when the diffusion of a new product in different countries is studied. The proposed modeling approach originates from the well-known logistic model where it is assumed that the ordinary contagion process does not take place instantly but after some certain amount of time. A proper modification of the proposed model described by a time lag ordinary differential equation can be solved analytically and its properties for several parameters' combination are investigated. Moreover, a new diffusion speed index is proposed and the correlation between the time-delay index and the proposed diffusion speed index is examined. Finally the model is applied to real data concerning the mobile services diffusion in fifteen counties of EU from 1990 to 2002. Based on the estimated parameters of the model produced for each country a ranking and a clustering of the EU countries based on their derived diffusion speed and time-delay indexes are provided.
Diffusion of Mobile Telephony in China: Drivers and Forecasts
IEEE Transactions on Engineering Management, 2012
Analyzing mobile telephony diffusion involves identifying drivers and forecasting growth using a growth model. However, to our knowledge, no framework for model selection exists. To eliminate ad hoc model selection, this study presents a novel model-comparison method based on an analysis of mobile telephony diffusion in China, which accounts for one-fifth of global mobile telephony subscriptions. Determinants of the diffusion rate are then analyzed using the most appropriate model identified by the proposed model-comparison method in terms of minimum root-mean-square error. Empirical results identify the Gompertz model as the best model for diffusion forecasting. The three most significant determinants are low-costmobile handsets, prepaid services, and personal handy-phone system (PHS) services.All of these determinants contribute to meeting the demand in China’s lowend market. This study combines the proposed model-comparison method with estimates of determinants of diffusion rate to improve analysis and forecasting accuracy for mobile telephony diffusion. Moreover, model comparisons using data from eight representative countries (Brazil, China, France, Germany, India, Russia, the U.K., and the U.S.) provide a valuable reference formodel selection for mobile telephony diffusion.