Most discrete time literature uses the beta that results from a regression of an asset's simple returns on various factors to quantify risk. The departing point for this thesis is the consistent use of log-returns. When log-returns are considered, the relevant measure of systematic risk becomes...

A model that realistically defines market liquidity and depth is introduced. Liquidity is the expected rate of order execution in shares per minute. Depth is the average density of the limit order book in shares per dollar. Illiquid markets tend to exhibit longer execution delays and indirectly...

Dividend yields have been widely used in previous research to relate stock market valuations to cash flow fundamentals. However, this approach relies on the assumption that dividend yields are stationary. Due to the failure to reject the hypothesis of a unit root in the classical dividend-price...

We propose two new risk measures (i-beta and i-gamma) for a stock, which aim to distinguish between noise and information. Noise allows the stock price evolution to happen along a continuous path. Market wide economic information is transmitted via price jumps. Noise is idiosyncratic and does...

It is shown that, for CRRA agents, the sensitivity of risk correction for any cumulant depends on the cumulant of the next order. This result is then used to derive some interesting approximations for variance and skewness correction. The first corollary is that negative skewness alone leads to...

The inherent incompleteness of continuous-time economies driven by market microstructure noise (modeled here as a Levy process) forces agents to price assets in new ways that have no analog in the dynamically complete continuous-path markets driven by a diffusion. It is shown that microstructure...

The Regression Tree (RT) sorts the samples using a specific feature and finds the split point that produces the maximum variance reduction from a node to its children. Our key observation is that the best factor to use (in terms of MSE drop) is always the target itself, as this most clearly...