search query: @author Aldrin, M. / total: 1
reference: 1 / 1
« previous | next »
| Author: | Aldrin, M. Damsleth, E. |
| Title: | Forecasting non-seasonal time series with missing observations. |
| Journal: | Journal of Forecasting
1989 : APR-JUN, VOL. 8:2, p. 97-116 |
| Index terms: | FORECASTING TECHNIQUES TIME SERIES |
| Language: | eng |
| Abstract: | Most forecasting methods are based on equally spaced data. In the case of missing observations the methods have to be modified. Three smoothing methods are considered: 1. simple exponential smoothing; 2. double exponential smoothing; 3. the Holt's method. A new, unified approach is also presented to handle missing data within the smoothing methods. This approach is compared with previously suggested modifications. The comparison is done on 12 real, non-seasonal time series. It is shown that the smoothing methods, properly modified, usually perform well if the time series have a moderate number of missing observations. |
« previous | next »
SCIMA