Open Source Cross-Sectional Asset Pricing (with Tom Zimmermann)
Solicited by the Critical Finance Review
We provide data and code that successfully reproduces nearly all cross-sectional stock return predictors. The data consists of 315 characteristics and 1,260 "anomaly" portfolios, and successfully replicates statistical significance for 98% of predictors.
The Limits of P-Hacking: Some Thought Experiments
Zeroing in on the Expected Returns of Anomalies (with Mihail Velikov)
R&R, Journal of Financial and Quantitative Analysis
Media Coverage: Wharton's Behind the Markets Podcast (at the Jacobs-Levy 2019 Conference)
After adjusting for trading costs, stale data (before publication or before 2005), and data-mining, the best anomalies' expected returns are approximately zero.
Eastern Finance Association 2019 Outstanding Paper in Investments (Trading Strategies)
Do t-stat Hurdles Need to be Raised?
Permanent Working Papers
Semi-Parametric Restrictions on Production-Based Asset Pricing Models
Matching the data on asset prices requires either extremely volatile IST shocks or huge capital adjustment costs.
The best parts of this paper are extended and can be found in "An Irrelevance Theorem for Risk Aversion and Time-Varying Risk" with Francisco Palomino.
Financing Concerns in April 2020 Appear Worse Than in 2008 Based on Earnings Calls (with Jie Yang)