haku: @indexterm random sample / yhteensä: 27
viite: 14 / 27
Tekijä: | Makridakis, S. |
Otsikko: | Soliding simulations: a new approach to time series forecasting |
Lehti: | Management Science
1990 : APR, VOL. 36:4, p. 505-512 |
Asiasana: | TIME SERIES FORECASTING MODELS OPTIMIZATION SIMULATION RANDOM SAMPLE |
Kieli: | eng |
Tiivistelmä: | A new approach is proposed to time series forecasting based upon three premises. First, a model is selected not by how well it fits historical data but on its ability to accurately predict out-of-sample information. Models/methods are optimized for each forecasting horizon separately, making it possible to have different models/methods to predict each of the m horizons. In order to avoid the problems associated with model selection the forecasts of several models/methods were combined to obtain a single forecast. |
SCIMA