Fractional integration and cointegration in financial time series

Authors	P. Stakėnas
Supervisors	H.P. Boswijk
Award date	21-11-2012
ISBN	9789036103275
Number of pages	126
Publisher	Amsterdam: Thela Thesis
Organisations	Faculty of Economics and Business (FEB) - Amsterdam School of Economics Research Institute (ASE-RI)
Abstract	This thesis analyzes different aspects of fractionally integrated and cointegrated time series models and contributes to the literature by suggesting new asymptotic inference procedures in (co)fractional models. In particular, this thesis proposes a new model for fractionally cointegrated time series and studies estimation and inference in the model based on the conditional Gaussian likelihood. Theoretical results of the thesis are illustrated using U.S. interest rate series.
Document type	PhD thesis
Note	Tinbergen Institute research series no. 545 Research conducted at: Universiteit van Amsterdam
Language	English
Downloads	Thesis Cover Title pages Acknowledgements Contents 1: General introduction and overview 2: Estimation and inference of fractionally integrated time series 3: Testing for no fractional cointegration: a Monte Carlo study 4: Dynamic OLS estimation of fractionally cointegrated regressions 5: Likelihood-based inference in fractionally cointegrated systems Summary Samenvatting (Summary in Dutch) Bibliography Recent titles in the Tinbergen Institute research series
Permalink to this page

Back

UvA-DARE