We propose and evaluate a variety of penalized regression methods for forecasting and economic decision making in a data-rich environment under parameter uncertainty. Empirically, we explore the statistical and economic performance across different asset classes such as stocks, bonds, and...

We show that low-order autoregression models for short-term expected returns imply long-term dynamics that have a (too) fast vanishing persistence when compared with the evidence from long-horizon predictive regressions. We then propose a novel modeling framework that exploits the low-frequency...

We provide a measure of sparsity for expected returns within the context of classical factor models. Our measure is inversely related to the percentage of active predictors. Empirically, sparsity varies over time and displays an apparent countercyclical behavior. Proxies for financial conditions...

We show that machine learning methods, in particular extreme trees and neural networks (NNs), provide strong statistical evidence in favor of bond return predictability. NN forecasts based on macroeconomic and yield information translate into economic gains that are larger than those obtained...

We pit individual theoretical predictors of the equity premium against a variety of data-driven statistical methods. Theoretically motivated predictive regressions outperform conventional penalised regressions but have similar out-of-sample R2 and lower economic gains relative to more agnostic...

We propose a novel Markov regime-switching Poisson regression model with time-varying transition distributions to test existing theories on determinants of wave-like patterns in same-industry merger and acquisitions (M&As). We show that the dynamics and persistence of merger waves change...

The variance risk premium represents the compensation paid to index option sellers for the risk of losses following upward movements in realized market return volatility. Common wisdom connects these spikes with elevated uncertainty on economic fundamentals. I incorporate this link within a...

We propose a Markov Switching Graphical Seemingly Unrelated Regression (MS-GSUR) model to investigate time-varying systemic risk based on a range of multi-factor asset pricing models. Methodologically, we develop a Markov Chain Monte Carlo (MCMC) scheme in which latent states are identified on...