haku: @indexterm random sample / yhteensä: 27
viite: 10 / 27
| Tekijä: | Aczel, A. D. Josephy, N. H. |
| Otsikko: | Using the bootstrap for improved ARIMA model identification |
| Lehti: | Journal of Forecasting
1992 : JAN, VOL. 11:1, p.71-80 |
| Asiasana: | STATISTICAL METHODS TIME SERIES RANDOM SAMPLE FREQUENCY DISTRIBUTION FORECASTING METHODOLOGY |
| Kieli: | eng |
| Tiivistelmä: | A new method of identifying ARIMA time series models is presented. The bootstrap technique was used for estimating the distribution of sample autocorrelations both separately and in a simultaneous inference setting. The bootstrap has the advantage of being nonparametric and thus free of reliance on asymptotic normality which may not hold for short or medium-size series. The simultaneous procedure is unique, as it has no feasible parametric alternatives. An application to exchange rates illustrates the new methodology. In the example chosen, one can produce better forecasts using the model identified via the bootstrap technique than by earlier methods. |
SCIMA