| Abstract : | The purpose of this Thesis is to document an original contribution in the areas of model determination and volatility modeling. Model determination is the procedure that evaluates the ability of competing hypothesized models to describe a phenomenon under study. Volatility modeling in the present context, involves developing models that can adequately describe the volatility process of a financial time series. In this Thesis we focus on the development of efficient algorithms for Bayesian model determination using Markov Chain Monte Carlo (MCMC), which are also used to develop a family of nonlinear flexible models for volatility. We propose a new method for Bayesian model determination that incorporates several desirable characteristics, resulting in better mixing for the MCMC chain and more precise estimates of the posterior density. The new method is compared with various existing methods in an extensive simulation study, as well as more complex model selections problems based on linear regression, with both simulated and real data comprising of 300 to 1000 variables. The method seems to produce rather promising results, overperforming several other existing algorithms in most of the analyzed cases. Furthermore the method is applied to gene selection using logistic regression, with a famous dataset including 3226 genes. The problem lies in identifying the genes related to the presence of a specific form of breast cancer. The new method again proves to be more efficient when compared to an existing Population MCMC sampler, while we extend the findings of previous medical studies on this issue. We present a new class of flexible threshold models for volatility. In these models the variables included, as well as the number and location of the threshold points are estimated, while the exogenous variables are allowed to be observed on lower frequencies than the dependent variable. To estimate these models we use the new method for Bayesian model determination, enriched with new move types, the use of which is validated through additional simulations. Furthermore, we propose a comparative model based on splines, where the number and location of the spline knots is related to a set of exogenous variables. The new models are applied to estimate and predict the variance of the Euro-dollar exchange rate, using as exogenous variables a set of U.S. macroeconomic announcements. The results indicate that the threshold models can provide significantly better estimates and projections than the spline model and typical conditional volatility models, while the most important macroeconomic announcements are identified. The threshold models are then generalised to the multivariate case. Under the proposed methodology, the estimation of the univariate variances is only required, as well as a rather small collection of regression coefficients. This simplifies greatly the inference, while the model is found to perform rather well in terms of predictability. A detailed review of both the available algorithms for Bayesian Model determination and nonlinear models for financial time series is also included in this Thesis. We illustrate how the existing methods for model determination are embedded into a common general scheme, while we discuss the properties and advantages each method has to offer. The main argument presented is that there is no globally best or preferable method, but their relative performance and applicability, depends on the dataset and problem of interest. With respect to the nonlinear models for financial time series and volatility we present in a unified manner, the main parametric and nonparametric classes of these models, while there is also a review of event studies analyzing the effect of news announcements on volatility.
|
|---|
Copyright © 2013 Library AUEB. All rights reserved.