Forecasting using belief functions: An application to marketing econometrics

A method is proposed to quantify uncertainty on statistical forecasts using the formalism of belief functions. The approach is based on two steps. In the estimation step, a belief function on the parameter space is constructed from the normalized likelihood given the observed data. In the prediction step, the variable Y to be forecasted is written as a function of the parameter θ and an auxiliary random variable Z with known distribution not depending on the parameter, a model initially proposed by Dempster for statistical inference. Propagating beliefs about θ and Z through this model yields a predictive belief function on Y. The method is demonstrated on the problem of forecasting innovation diffusion using the Bass model, yielding a belief function on the number of adopters of an innovation in some future time period, based on past adoption data.

[1]  Didier Dubois,et al.  The principle of minimum specificity as a basis for evidential reasoning , 1986, IPMU.

[2]  Rory A. Fisher,et al.  Statistical methods and scientific inference. , 1957 .

[3]  F. Bass.  A new product growth model for consumer durables , 1976 .

[4]  Véronique Berge-Cherfaoui,et al.  Controlling Remanence in Evidential Grids Using Geodata for Dynamic Scene Perception , 2014, Int. J. Approx. Reason..

[5]  Thierry Denoeux,et al.  Combining statistical and expert evidence using belief functions: Application to centennial sea level estimation taking into account climate change , 2014, Int. J. Approx. Reason..

[6]  Ambar G. Rao,et al.  New Models from Old: Forecasting Product Adoption by Hierarchical Bayes Procedures , 1990 .

[7]  Jean-Yves Jaffray,et al.  Application of Linear Utility Theory to Belief Functions , 1988, IPMU.

[8]  Arthur P. Dempster,et al.  The Dempster-Shafer calculus for statisticians , 2008, Int. J. Approx. Reason..

[9]  Sébastien Destercke,et al.  An extension of Universal Generating Function in Multi-State Systems Considering Epistemic Uncertainties , 2013, IEEE Transactions on Reliability.

[10]  Glenn Shafer.  Constructive Probability , 2008, Classic Works of the Dempster-Shafer Theory of Belief Functions.

[11]  R. A. Fisher,et al.  Statistical methods and scientific inference. , 1957 .

[12]  Hung T. Nguyen,et al.  On Random Sets and Belief Functions , 1978, Classic Works of the Dempster-Shafer Theory of Belief Functions.

[13]  Yi-Chung Hu,et al.  Quadratic-interval Bass model for new product sales diffusion , 2009, Expert Syst. Appl..

[14]  Orakanya Kanjanatarakul,et al.  Comparison of sales forecasting models for an innovative agro-industrial product: Bass model versus logistic function , 2012 .

[15]  Arthur P. Dempster,et al.  New Methods for Reasoning Towards PosteriorDistributions Based on Sample Data , 1966, Classic Works of the Dempster-Shafer Theory of Belief Functions.

[16]  D. Dubois,et al.  A set-theoretic view of belief functions: Logical operations and approximations by fuzzy sets , 1986 .

[17]  I. Gilboa.  Expected utility with purely subjective non-additive probabilities , 1987 .

[18]  Arthur P. Dempster,et al.  Upper and Lower Probabilities Induced by a Multivalued Mapping , 1967, Classic Works of the Dempster-Shafer Theory of Belief Functions.

[19]  Glenn Shafer,et al.  A Mathematical Theory of Evidence , 2020, A Mathematical Theory of Evidence.

[20]  Jun Xie,et al.  Large scale two sample multinomial inferences and its applications in genome-wide association studies , 2014, Int. J. Approx. Reason..

[21]  Glenn Shafer,et al.  Perspectives on the theory and practice of belief functions , 1990, Int. J. Approx. Reason..

[22]  Hung T. Nguyen,et al.  An Introduction to Random Sets , 2006 .

[23]  Orakanya Kanjanatarakul,et al.  Sufficient Number of Observations for Sales Forecasts with Limited Information: A Case of an Innovative Agro-Industrial Product , 2013 .

[24]  J. Jaffray,et al.  Decision making with belief functions: Compatibility and incompatibility with the sure-thing principle , 1993 .

[25]  Vijay Mahajan,et al.  Maximum Likelihood Estimation for an Innovation Diffusion Model of New Product Acceptance , 1982 .

[26]  Geoffrey Gregory,et al.  Foundations of Statistical Inference , 1973 .

[27]  L. Wasserman.  Belief functions and statistical inference , 1990 .

[28]  Laurent Mouchard,et al.  Dealing with uncertainty and imprecision in image segmentation using belief function theory , 2014, Int. J. Approx. Reason..

[29]  A. Dempster.  Upper and Lower Probabilities Generated by a Random Closed Interval , 1968 .

[30]  Robert Piché,et al.  Forecasting the Diffusion of Innovation: A Stochastic Bass Model With Log-Normal and Mean-Reverting Error Process , 2011, IEEE Transactions on Engineering Management.

[31]  Yoram Wind,et al.  Organizational Psychographics and Innovativeness , 1980 .

[32]  Mikel Aickin,et al.  Connecting Dempster–Shafer Belief Functions with Likelihood-based Inference , 2000, Synthese.

[33]  A. Edwards.  Likelihood (Expanded Edition) , 1972 .

[34]  Philippe Smets,et al.  Belief functions: The disjunctive rule of combination and the generalized Bayesian theorem , 1993, Int. J. Approx. Reason..

[35]  Thierry Denux,et al.  Likelihood-based belief function: Justification and some extensions to low-quality data , 2014, Int. J. Approx. Reason..

[36]  N. Meade,et al.  Modelling and forecasting the diffusion of innovation – A 25-year review , 2006 .

[37]  A. Dempster.  Upper and lower probability inferences based on a sample from a finite univariate population. , 1967, Biometrika.

[38]  Paolo Ghirardato,et al.  Coping with ignorance: unforeseen contingencies and non-additive uncertainty , 2001 .

[39]  Frank M. Bass,et al.  A New Product Growth for Model Consumer Durables , 2004, Manag. Sci..

[40]  Alessandro Saffiotti,et al.  The Transferable Belief Model , 1991, ECSQARU.