UC Riverside

The theme of this dissertation is the risk and return modeling of financial time series. The dissertation is broadly divided into three chapters; the first chapter focuses on measuring risks and uncertainty in the U.S. stock market; the second on measuring risks of individual financial assets; and the last chapter on predicting stock return. The first chapter studies the movement of the S&P 500 index driven by uncertainty and fear that cannot be explained by economic fundamentals. A new measure of uncertainty is introduced, using the tone of news media coverage on the equity market and the economy; aggregate holding of safe financial assets; and volatility in S&P 500 options trading. Major contributions of this chapter include uncovering a significant non-linear relationship between uncertainty and changes in the business cycle. An increase in uncertainty is found to be associated with drastic but short-lived falls in stock prices; while economic fundamentals have a small but prolonged effect on the stock market prices. The second chapter proposes a new Value at Risk (VaR) and Expected Shortfall (ES) estimation procedure that involves estimating the variance of return using conditional semiparametric approach introduced by Mishra, Su and Ullah (2010). Thus, estimation of variance is independent from the assumed distribution. Monte Carlo simulations are used to compare the performance of these new estimates using normal, Student-t, laplace, ARCH, GARCH, and GJR GARCH distributions. VaR and ES for Amazon, SP500, Microsoft, Nasdaq, USD/GBP and USD/Yen are estimated and the performance of each estimation method is further tested using a battery of tests. The third chapter explores whether non-parametric and semi parametric methods can reduce the bias in predictive regressions in the presence of high persistence in the predictive variables and non-linear relationship with the dependent variable. The predictive performance of the independent variables suggested in the literature to predict stock returns are re-evaluated in sample and out of sample using two step non-parametric and semi parametric models. Empirical RMSE are used to compare the proposed models with the historical average, OLS and non-parametric regression models.