Financial analysts typically estimate volatilities and correlations from monthly or higher frequency returns when determining the optimal composition of a portfolio. Although it is widely acknowledged that these measures are not necessarily stationary across samples, most analysts assume...

A striking feature of private equity (PE) is that performance is persistent, with many PE firms consistently producing high (or low) returns net of fees. We use a new variance decomposition model to isolate three components of performance persistence. We find a large amount of long-term...

The Sharpe ratio is the most widely used metric for comparing performance across investment managers and strategies, and the information ratio is as commonly used to evaluate performance relative to a benchmark. Although it is widely recognized that non-linearities arising from the inclusion of...

For the popular mean-variance portfolio choice problem in the case without a risk-free asset, we develop a new portfolio strategy to mitigate estimation risk. We show that in both calibrations and real datasets, optimally combining the sample global minimum variance portfolio with a sample...

When a benchmark model is inefficient, including additional assets to the benchmark portfolios can improve its performance. In reality, however, the efficiency of a benchmark model relative to a given set of test assets is ex ante unknown, and the optimal portfolio is constructed based on...

We propose a unified set of distance-based performance metrics that address the power and extreme-error problems inherent in traditional measures for asset-pricing tests. From a Bayesian perspective, the distance metrics coherently incorporate both pricing errors and their standard errors....

We introduce an ensemble learning method based on Gaussian Process Regression (GPR) for predicting conditional expected stock returns given stock-level and macro-economic information. Our ensemble learning approach significantly reduces the computational complexity inherent in GPR inference and...

Sparse models, though long preferred and pursued by social scientists, can be ineffective or unstable relative to large models, for example, in economic predictions (Giannone et al., 2021). To achieve sparsity for economic interpretation while exploiting big data for superior empirical...

We implement a long-horizon static and dynamic portfolio allocation involving a risk-free and a risky asset. This model is calibrated at a quarterly frequency for ten European countries. We also use maximum-likelihood estimates and Bayesian estimates to account for parameter uncertainty. We find...

The specification of prior parameters is a common practical problem when implementing Bayesian approaches to portfolio optimization. The precision parameter of the prior on the expected asset returns reflects the confidence of the investor in the prior knowledge. Within the framework of the...