search query: @author Chen, L. / total: 5
reference: 5 / 5
« previous | next »
Author: | Anandalingham, G. Chen, L. |
Title: | Linear combination of forecasts: a general bayesian model. (!Combining forecasts) |
Journal: | Journal of Forecasting
1989 : JUL-SEP, VOL. 8:3, p. 199-214 |
Index terms: | FORECASTING BAYESIAN STATISTICS |
Language: | eng |
Abstract: | The most important factor in forecasting is accuracy. Today numerous forecasting models are available to produce "optimal" forecasts, but each of them is developed based on a particular set of assumptions. Thus a principal motivation for combining forecasts has been to avoid the a priori choice of which forecasting method to use. A general Bayesian model for combining forecasts from experts (or forecasting models) - who might be biased and correlated with each other - is provided. The combination procedure involves debiasing and then combining unbiased forecasts. Furthermore a sequential method is provided for learning about the forecasters' biases in the process of combining information from them. |
« previous | next »
SCIMA