Estimating deterministics in univariate time series

Walsh, Christopher

Preview

PDF
WalshDissertation.pdf - Published
Download (7MB)

URL:	https://madoc.bib.uni-mannheim.de/36633
URN:	urn:nbn:de:bsz:180-madoc-366333
Document Type:	Doctoral dissertation
Year of publication:	2014
Place of publication:	Mannheim
University:	Universität Mannheim
Evaluator:	Mammen, Enno
Date of oral examination:	26 May 2014
Publication language:	English
Institution:	School of Law and Economics > Graduiertenkolleg VWL/BWL Außerfakultäre Einrichtungen > Graduate School of Economic and Social Sciences - CDSE (Economics) School of Law and Economics > Statistik (Mammen)
Subject:	310 Statistics 330 Economics
Subject headings (SWD):	Nichtparametrische Regression , Nichtstationäre Zeitreihenanalyse
Keywords (English):	Univariate Time Series , Nonprametric Regression , Nonstationarities , Deterministics , Time Series Decomposition
Abstract:	This thesis deals with regression approaches to analyse discrete univariate time series allowing for certain types of nonstationarities. It contains three chapters that each deal with a model containing some sort of deterministic components leading to the nonstationarity of the series. In Chapter 2 we analyse an additive model allowing for deterministics in the form of seasonal effects and a smooth time trend. Chapter 3 looks at a multiplicative volatility model that allows for a deterministic scale function. Finally, Chapter 4 looks at a model that combines the information about season and trend in a single deterministic function.