search query: @indexterm bayesian statistics / total: 167
reference: 93 / 167
| Author: | Ferelli, M. Wilson, G. T. |
| Title: | Robust estimation of level and trend |
| Journal: | Journal of Forecasting
1990 : MAR-APR, VOL.9:2, p.151-172 |
| Index terms: | BAYESIAN STATISTICS TIME SERIES ESTIMATION FREQUENCY DISTRIBUTION MODELS |
| Language: | eng |
| Abstract: | Numerical state space models are efficiently implemented for the estimation of the underlying level and trend of a time series. The model specification is chosen so that the estimation is insensitive to outliners yet adapts rapidly to step changes in level. An example illustrates, by means of projection plots, how at times of uncertainty in the evolution of the series the inferred distribution of level and trend may be multi-model. The application of these models in the area of fast-moving consumer goods and in the area of sales promotion analysis is justified. The methods presented are suitable to cope with the longer-term brand dynamics and step changes resulting from new product launches and successful brand relaunches. |
SCIMA