Prediction and interpolation of time series by state space models

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 e cient and exible framework for time series forecasting, which can be used for combining multiple types of traditional time series and other models.