Statistical inference for nonlinear state space models: an application to the analysis of forest fire counts in Canada

Tang, Zhian (2017) Statistical inference for nonlinear state space models: an application to the analysis of forest fire counts in Canada. Masters thesis, Memorial University of Newfoundland.

[img] [English] PDF - Accepted Version
Available under License - The author retains copyright ownership and moral rights in this thesis. Neither the thesis nor substantial extracts from it may be printed or otherwise reproduced without the author's permission.

Download (763Kb)

Abstract

Nonlinear state space models occupy a predominant position in statistical stud- ies. They are widely used in various fields such as economics, finance, ecology and epidemiology. However, such models may be problematic when it comes to statistical inference, due to the fact that they could be quite sensitive to small variations in system states and parameters. In this dissertation, we present three estimation pro- cedures and their respective algorithms for the statistical inference of such nonlinear, non-Gaussian state space models. Also, simulation studies are carried out to evaluate the performance of these methods. At the end, we analyze the time series of forest fire counts that annually occurred in Canada using the proposed methodologies.

Item Type: Thesis (Masters)
URI: http://research.library.mun.ca/id/eprint/12589
Item ID: 12589
Additional Information: Includes bibliographical references (pages 62-64).
Keywords: Nonlinear, State Space Models, Particle Filter, Iterated Filtering, Approximate Bayesian Computation, Particle Markov Chain Monte Carlo, Forest Fires
Department(s): Science, Faculty of > Mathematics and Statistics
Date: March 2017
Date Type: Submission
Library of Congress Subject Heading: Nonlinear systems; Mathematical statistics; Forest fire forecasting -- Mathematical models

Actions (login required)

View Item View Item

Downloads

Downloads per month over the past year

View more statistics