The first chapter of this thesis gives a general discussion of the issues experienced when standard tests are applied to an economic time series when either or both of the order of integration of a series or the distribution driving the innovation sequence is unknown. In the second chapter a new procedure for detecting additive outliers in a univariate time series is proposed based on a bootstrap implementation of the test of Pen'on and Rodr'lguez (2003, Journal of Time Series Analysis 24, 193-220). This procedure is used to test the null hypothesis that a time series is uncontaminated by additive outliers against the alternative that one or more additive outliers are present. In the third chapter a testing procedure for the presence of a deterministic linear trend in a univariate time series is developed which is robust to whether a series is 1(0) or 1(1) and requires no knowledge of the form of weak dependence in the data. In the fourth chapter a test for the presence of nonlinear deterministic components in a univariate time series is developed, where the nonlinear deterministic component of a series is approximated using a Fourier series expansion, that is designed to be asymptotically robust to the order of integration of the process and to any weak dependence present in the data. In the fifth chapter tests for the presence of deterministic components in a seasonally observed univariate time series are developed . These tests are designed to be asymptotically robust to the order of integration of the series at both the zero and seasonal frequencies. In the sixth and final chapter concluding remarks are made about the results from all other chapters of the thesis, and avenues for further research are detailed. "
Identifer | oai:union.ndltd.org:bl.uk/oai:ethos.bl.uk:605992 |
Date | January 2013 |
Creators | Astill, Sam |
Publisher | University of Nottingham |
Source Sets | Ethos UK |
Detected Language | English |
Type | Electronic Thesis or Dissertation |
Page generated in 0.0014 seconds