Prediction and interpolation of time series by state space models
A large amount of data collected today is in the form of a time series. In order to make realistic inferences based on time series forecasts, in addition to point predictions, prediction intervals or other measures of uncertainty should be presented. Multiple sources of uncertainty are often ignored due to the complexities involved in accounting them correctly. In this dissertation, some of these problems are reviewed and some new solutions are presented. A state space approach is also advocated for an e cient and exible framework for time series forecasting, which can be used for combining multiple types of traditional time series and other models.
Artikkeliväitöskirja. Sisältää yhteenveto-osan ja neljä artikkelia. Article dissertation. Contains an introduction part and four articles.
PublisherUniversity of Jyväskylä
- Article I: Helske, J., & Nyblom, J. (2015). Improved Frequentist Prediction Intervals for Autoregressive Models by Simulation. In S. J. Koopman, & N. Shephard (Eds.), Unobserved Components and Time Series Econometrics (pp. 291-309). Oxford University Press.
- Article II: Helske, J. and Nyblom, J. (2014). Improved frequentist prediction intervals for ARMA models by simulation. In Knif, J. and Pape, B., editors, Contributions to Mathematics, Statistics, Econometrics, and Finance: Essays in Honour of Professor Seppo Pynnönen, (pp. 71-86). Acta Wasaensia, 296. Vaasa: Vaasan Yliopisto.
- Article III: Helske, J., Nyblom, J., Ekholm, P., & Meissner, K. (2013). Estimating aggregated nutrient fluxes in four Finnish rivers via Gaussian state space models. Environmetrics, 24 (4), 237-247. doi:10.1002/env.2204
- Article IV: Helske, J. (2015). KFAS: Exponential family state space models in R. (Submitted; not available online)
MetadataShow full item record
- Väitöskirjat