Use this URL to cite or link to this record in EThOS:
Title: Multi-factor dynamic modelling and forecasting of interest rates and equity markets
Author: Tunaru, Diana E.
ISNI:       0000 0004 6424 0011
Awarding Body: University of Westminster
Current Institution: University of Westminster
Date of Award: 2017
Availability of Full Text:
Access from EThOS:
Access from Institution:
In this thesis, several theoretical specifications and estimation techniques are employed towards the dynamic modelling and forecasting of the term structure of interest rates, both independently and in conjunction with equity markets. The first empirical investigation is motivated by the recent call for richer specifications following the global financial crisis of 2007-2009. In that regard, several existing multi-factor continuous-time models are extended to four and five factors to assess the benefit of richer models. The Gaussian estimation methods for dynamic Continuous-Time models yield insightful comparative results concerning the two different segments of the yield curve. The dynamics of the more volatile short-end of the yield curve are best explained by the most flexible models which consistently outperform all the other less complex models in terms of both in-sample and out-of-sample performance. For the long-end flatter segment, the benchmark discrete-time parsimonious models seem hard to beat, while the addition of extra factors has a minimal benefit in terms of forecasting performance. In a second empirical study, the term structures of three Scandinavian countries are modelled using multi-latent-factor models. The empirical results produced by Kalman filter estimation method indicate that the three-factor specification captures most of the changes over time in the shape of the yield curve for Denmark and Norway, while for Sweden the statistical tests do not reject the two-factor model against the three-factor formulation. Finally, the third investigation brings new empirical evidence of the impact of the 2007-2009 financial crisis on the return and volatility linkages between the U.S. - the country where the shock originated and other major economies using a multivariate methodology for the simultaneous modelling of interest rates and equity markets. During the global financial crisis of 2007-2009 the financial markets around the world have communicated through a more complex network of information transmission routes. The channels with most intensity of information transmission were the indirect international ones, bringing new evidence of the importance of this type of routes that has previously been investigated very little in the spillovers literature.
Supervisor: Not available Sponsor: Not available
Qualification Name: Thesis (Ph.D.) Qualification Level: Doctoral
EThOS ID:  DOI: Not available