||This dissertation consists of three related chapters that study financial market volatility,
jumps and the economic factors behind them. Each of the chapters analyzes a
different aspect of this problem.
The first chapter examines tests for jumps based on recent asymptotic results.
Monte Carlo evidence suggests that the daily ratio z-statistic has appropriate size,
good power, and good jump detection capabilities revealed by the confusion matrix
comprised of jump classification probabilities. Theoretical and Monte Carlo analysis
indicate that microstructure noise biases the tests against detecting jumps, and that
a simple lagging strategy corrects the bias. Empirical work documents evidence for
jumps that account for seven percent of stock market price variance.
Building on realized variance and bi-power variation measures constructed from
high-frequency financial prices, the second chapter proposes a simple reduced form
framework for modelling and forecasting daily return volatility. The chapter first
decomposes the total daily return variance into three components, and proposes
different models for the different variance components: an approximate long-memory
HAR-GARCH model for the daytime continuous variance, an ACH model for the
jump occurrence hazard rate, a log-linear structure for the conditional jump size,
and an augmented GARCH model for the overnight variance. Then the chapter
combines the different models to generate an overall forecasting framework, which
improves the volatility forecasts for the daily, weekly and monthly horizons.
The third chapter studies the economic factors that generate financial market
volatility and jumps. It extends the recent literature by separating market responses
into continuous variance and discontinuous jumps, and differentiating the market’s
disagreement and uncertainty. The chapter finds that there are more large jumps on
news days than on no-news days, with the fixed-income market being more responsive
than the equity market, and non-farm payroll employment being the most influential
news. Surprises in forecasts impact volatility and jumps in the fixed-income market
more than the equity market, while disagreement and uncertainty influence both
markets with different effects on volatility and jumps.
JEL classification: C1, C2, C5, C51, C52, F3, F4, G1, G14