tailieunhanh - Handbook of Economic Forecasting part 102

Handbook of Economic Forecasting part 102. Research on forecasting methods has made important progress over recent years and these developments are brought together in the Handbook of Economic Forecasting. The handbook covers developments in how forecasts are constructed based on multivariate time-series models, dynamic factor models, nonlinear models and combination methods. The handbook also includes chapters on forecast evaluation, including evaluation of point forecasts and probability forecasts and contains chapters on survey forecasts and volatility forecasts. Areas of applications of forecasts covered in the handbook include economics, finance and marketing | 984 PH. Franses Abstract With the advent of advanced data collection techniques there is an increased interest in using econometric models to support decisions in marketing. Due to the sometimes specific nature of variables in marketing the discipline uses econometric models that are rarely if ever used elsewhere. This chapter deals with techniques to derive forecasts from these models. Due to the intrinsic non-linear nature of these models these techniques draw heavily on simulation techniques. Keywords forecasting marketing Koyck model Bass model attraction model unobserved heterogeneity JEL classification M30 C22 C23 C53 Ch. 18 Forecasting in Marketing 985 1. Introduction In their recent bestseller Kotler Jain and Maesincee 2002 p. x state that Today s businesses must strive to satisfy customers needs in the most convenient way minimizing the time and energy that consumers spend in searching for ordering and receiving goods and services . Obviously these authors see an important role for marketing activities to support that objective. At the same time this statement indicates that marketing activities can be targeted at the level of an individual consumer s level and that time is an important factor. Time can consider the speed at which consumers can respond but it also concerns the ability to evaluate the success or failure of marketing activities. For a quick evaluation one benefits from detailed data observed at a high frequency and preferably including performance data of competitors. With the advent of advanced data collection techniques optic scanner data and web-based surveys today s decisions on the relevant marketing activities can be supported by econometric models that carefully summarize the data. These basically concern links between performance measures like sales with marketing input like prices and advertising. Direct mailings for example can now be targeted at specific individuals bonus offers in retail stores can be given to only a selected set