Modelling diffusion and replacement

Replacement sales represent about 75% of total sales for many consumer durables, thus modelling this component well should lead to better overall forecasting. This paper surveys and evaluates forecasting models for total sales of durables which include both a diffusion component and a replacement component. The diffusion process, describing the behaviour of first time purchasers, is represented by a version of the Bass model and several different models of the replacement process are examined. The choice of replacement model is shown to have a major effect on forecasting performance. Two approaches are explored, model parameters are estimated with and without the use of prior estimates of expected service lifetime. Some of the two parameter replacement models are shown to offer forecasting performance superior to that of single parameter models, but their main disadvantage is only a 30–50% probability of successful parameter estimation. A robust approach to forecasting total sales is offered in conclusion.