Minimum Sample Size requirements for Seasonal Forecasting Models
Authors Rob Hyndman and Andrey Kostenko discuss the bare minimum data requirements for fitting three common types of seasonal models: regression with seasonal dummies, exponential smoothing, and ARIMA. Achieving the requisite minimum numbers, however, does not ensure adequate estimates of seasonality. The amount of additional data required depends on the amount of noise (random variation) in the data. Unfortunately, there are no simple rules about sample size, and the authors note that published tables on sample size requirements are overly simplified. Copyright International Institute of Forecasters, 2007
Year of publication: |
2007
|
---|---|
Authors: | Hyndman, Rob J. ; Kostenko, Andrey V. |
Published in: |
Foresight: The International Journal of Applied Forecasting. - International Institute of Forecasters - IIF. - 2007, 6, p. 12-15
|
Publisher: |
International Institute of Forecasters - IIF |
Saved in:
Online Resource
Saved in favorites
Similar items by person
-
25 Years of IIF Time Series Forecasting: A Selective Review
de Gooijer, Jan G., (2005)
-
Long-term forecasts of age-specific labour market participation rates with functional data models
Url, Thomas, (2016)
-
Forecasting Swiss exports using Bayesian forecast reconciliation
Eckert, Florian, (2019)
- More ...