An empirical comparison of new product trial forecasting models
Article Abstract:
An evaluation of the different models forecasting trial sales of new products reveals that simple models allows for significantly better forecasts than more complex specifications when dealing with consumer packaged goods. Also, models that explicitly accomodate heterogeneity in purchasing rates across consumers tend to offer better forecasts than those that do not and that maximum likelihood estimation appears to provide more accurate and stable predictions than non-linear least squares.
Publication Name: Journal of Forecasting
Subject: Mathematics
ISSN: 0277-6693
Year: 1998
User Contributions:
Comment about this article or add new information about this topic:
Parameter variation and new product diffusion
Article Abstract:
An analysis of parameter variation in new product diffusion models reveals that stochastic parameter specifications can be easily used to produce substantially better fits. Moreover, the study also reveals that stochastic parameter specifications are useful in the case of weak priors on the likely pattern of variation and that it may be used to specify the exact form of variation.
Publication Name: Journal of Forecasting
Subject: Mathematics
ISSN: 0277-6693
Year: 1998
User Contributions:
Comment about this article or add new information about this topic:
- Abstracts: Unemployment variation over the business cycles: a comparison of forecasting models
- Abstracts: Asymptotic properties of equilibrium forecasts in Bayesian learning models. Observable implications of equilibrium behavior on finite data
- Abstracts: A comparison of the real-time performance of business cycle dating methods. Modelling around-the-clock price discovery for cross-listed stocks using state space methods
- Abstracts: Non-temporal components of residential real estate appreciation
- Abstracts: Non-temporal components of residential real estate appreciation. part 2 An experimental comparison of dispute rates in alternative arbitration systems