Browsing by Subject "Stochastic volatility"

This thesis discusses novel developments in Bayesian analytics for high-dimensional multivariate time series. The focus is on the class of multiregression dynamic models (MDMs), which can be decomposed into sets of univariate models processed in parallel yet coupled for forecasting and decision making. Parallel processing greatly speeds up the computations and vastly expands the range of time series to which the analysis can be applied.

I begin by defining a new sparse representation of the dependence between the components of a multivariate time series. Using this representation, innovations involve sparse dynamic dependence networks, idiosyncrasies in time-varying auto-regressive lag structures, and flexibility of discounting methods for stochastic volatilities.

For exploration of the model space, I define a variant of the Shotgun Stochastic Search (SSS) algorithm. Under the parallelizable framework, this new SSS algorithm allows the stochastic search to move in each dimension simultaneously at each iteration, and thus it moves much faster to high probability regions of model space than does traditional SSS.

For the assessment of model uncertainty in MDMs, I propose an innovative method that converts model uncertainties from the multivariate context to the univariate context using Bayesian Model Averaging and power discounting techniques. I show that this approach can succeed in effectively capturing time-varying model uncertainties on various model parameters, while also identifying practically superior predictive and lucrative models in financial studies.

Finally I introduce common state coupled DLMs/MDMs (CSCDLMs/CSCMDMs), a new class of models for multivariate time series. These models are related to the established class of dynamic linear models, but include both common and series-specific state vectors and incorporate multivariate stochastic volatility. Bayesian analytics are developed including sequential updating, using a novel forward-filtering-backward-sampling scheme. Online and analytic learning of observation variances is achieved by an approximation method using variance discounting. This method results in faster computation for sequential step-ahead forecasting than MCMC, satisfying the requirement of speed for real-world applications.

A motivating example is the problem of short-term prediction of electricity demand in a "Smart Grid" scenario. Previous models do not enable either time-varying, correlated structure or online learning of the covariance structure of the state and observational evolution noise vectors. I address these issues by using a CSCMDM and applying a variance discounting method for learning correlation structure. Experimental results on a real data set, including comparisons with previous models, validate the effectiveness of the new framework.

This dissertation consists of two main essays in which it extends our knowledge on how stock market investors process the information from macro announcements. In the first essay, we extend the existing econometric theory to study the relation between jumps in multiple processes at a high-frequency. More specifically, we develop new high-frequency-based inference procedures for analyzing the relationship between jumps in instantaneous moments of stochastic processes. The estimation consists of two steps: the nonparametric determination of the jumps as differences in local averages, followed by a minimum-distance type estimation of the parameters of interest under general loss functions that include both least-square and more robust quantile regressions as special cases. The resulting asymptotic distribution of the estimator, derived under an infill asymptotic setting, is highly nonstandard and generally not mixed normal. In addition, we establish the validity of a novel bootstrap algorithm for making feasible inference including bias-correction. In the second essay, the new methods are applied to determine whether investors disagree when they process relevant macro-news announcements. If investors do disagree, we investigate the systematic components that drive disagreement. The high frequency data on stocks price and trade enable us to precisely isolate the news impact, and we use the volume-volatility elasticity framework to interpret our estimation. We consider a set of stock characteristics that might contribute to investor disagreement: idiosyncratic volatility, market size, value, and institutional ownership. Our findings suggest that investors do disagree whenever there is more uncertainty about future payoffs. Furthermore, the different stock characteristics explain, to a large extent, the deviation from the case of no disagreement. For last, we explore how the direction of stock misprice affects the elasticity and verify that the overall investor disagreement may not be entirely observed due to arbitrage constraints.

Numerical methods such as Monte Carlo method (MCM), finite difference method (FDM) and finite element method (FEM) have been successfully implemented to solve financial partial differential equations (PDEs). Sophisticated computational algorithms are strongly desired to further improve accuracy and efficiency.

The relatively new spectral element method (SEM) combines the exponential convergence of spectral method and the geometric flexibility of FEM. This dissertation carefully investigates SEM on the pricing of European options and their Greeks (Delta, Gamma and Theta). The essential techniques, Gauss quadrature rules, are thoroughly discussed and developed. The spectral element method and its error analysis are briefly introduced first and expanded in details afterwards.

Multi-element spectral element method (ME-SEM) for the Black-Scholes PDE is derived on European put options with and without dividend and on a condor option with a more complicated payoff. Under the same Crank-Nicolson approach for the time integration, the SEM shows significant accuracy increase and time cost reduction over the FDM. A novel discontinuous payoff spectral element method (DP-SEM) is invented and numerically validated on a European binary put option. The SEM is also applied to the constant elasticity of variance (CEV) model and verified with the MCM and the valuation formula. The Stochastic Alpha Beta Rho (SABR) model is solved with multi-dimensional spectral element method (MD-SEM) on a European put option. Error convergence for option prices and Greeks with respect to the number of grid points and the time step is analyzed and illustrated.