a shortcoming of exponential smoothing has been the lack of a statistical framework that produces both prediction intervals and point fore- casts. The innovations state space approach provides this framework while retaining the intuitive nature of exponential smoothing in its measurement and state equations. It provides prediction intervals, maximum likelihood estimation, procedures for model selection, and much more.
CITATION STYLE
Hyndman, P. R., Koehler, P. A., Ord, P. K., & Snyder, A. P. R. (2008). Forecasting with Exponential Smoothing. Springer Series in Statistics (pp. 1–356). Springer Berlin Heidelberg.
Mendeley helps you to discover research relevant for your work.