2006.43: Testing Nonstationary Time Series for Gaussianity and Linearity using the Evolutionary Bispectrum: An application to Internet Traffic Data
2006.43: T Subba Rao and E Tsolaki (2006) Testing Nonstationary Time Series for Gaussianity and Linearity using the Evolutionary Bispectrum: An application to Internet Traffic Data.
Full text available as:
|PDF - Requires a PDF viewer such as GSview, Xpdf or Adobe Acrobat Reader|
We propose statistical tests for Gaussianity and linearity of nonstationary time series based on the evolutionary bispectrum. These tests can be applied to a particular subclass of nonstationary processes, the so-called oscillatory (also known as slowly-varying) processes. We then apply these tests to time series of network measurements arising from internet traffic. Recent works by several researchers have demonstrated that such internet trafic processes are typically nonstationary. Also, the question of whether such processes can be described by some model whose parameters vary with time has been raised and studied at some length. We use the tests developed in this paper to show that there is evidence of non Gaussianity and nonlinearity in such processes uner the assumption that they are described by a model whose parameters (and so its spectral characteristics) vary slowly with time.
|Item Type:||MIMS Preprint|
|Subjects:||MSC 2000 > 62 Statistics|
|Deposited By:||Dr Peter Neal|
|Deposited On:||24 March 2006|