16.09.2015
Doctoral Dissertation

24.10. M.Sc. Jouni Helske (Faculty of Mathematics, Statistics) and Science, tilastotiede)

Time:

24.10.2015 12:00 — 15:00


Location: Seminaarinmaki , H320
M.Sc. Jouni Helske defends his doctoral dissertation in Statistics ”Prediction and interpolation of time series by state space models” . Opponent Professor Siem Jan Koopman (VU University Amterdam, the Netherlands) and custos Professor Jukka Nyblom (University of Jyväskylä).

Jouni Helske, photo Wilma TyniM.Sc. Jouni Helske defends his doctoral dissertation in Statistics ”Prediction and interpolation of time series by state space models” . Opponent Professor Siem Jan Koopman (VU University Amterdam, the Netherlands) and custos Professor Jukka Nyblom (University of Jyväskylä).

The doctoral dissertation is held in English.

Abstract

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 efficient and flexible framework for time series forecasting, which can be used for combining multiple types of traditional time series and other models.  An R package KFAS is introduced which allows user to define arbitrary exponential family state space models for prediction and other analysis.

More information

Jouni Helske

None

jouni.helske@jyu.fi