Decomposing Momentum: Eliminating its Crash Component
Pascal Büsing (University of Muenster), et al.
July 15, 2021
We propose a purely cross-sectional momentum strategy that avoids crash risk and does not depend on the state of the market. To do so, we simply split up the standard momentum return over months t-12 to t-2 at the highest stock price within this formation period. Both resulting momentum return components predict subsequent returns on a stand-alone basis. However, the long-short returns associated with the first component completely avoid negative skewness since momentum crashes are entirely driven by the second component.
Have Risk Premia Vanished?
Simon Smith (Federal Reserve) and Allan Timmermann (UCSD)
November 10, 2020
We apply a new methodology for identifying pervasive and discrete changes (“breaks”) in cross-sectional risk premia and find empirical evidence that these are economically important for understanding returns on US stocks. Size and value risk premia have fallen off to the point where they are insignificantly different from zero at the end of the sample. The market risk premium has also declined systematically over time but remains significant and positive as does the momentum risk premium. We construct a new instability risk factor from cross-sectional differences in individual stocks’ exposure to time-varying risk premia and show that this factor earns a premium comparable to that of commonly used risk factors. Using industry- and characteristics-sorted portfolios, we show that some breaks to the return premium process are broad-based, affecting all stocks regardless of industry- or firm characteristics, while others are limited to stocks with specific style characteristics. Moreover, we identify distinct lead-lag patterns in how breaks to the risk premium process impact stocks in different industries and with different style characteristics.
Correlation scenarios and correlation stress testing
N. Packham (Berlin School of Economics and Law) and
F. Woebbeking (Goethe University Frankfurt)
July 15, 2021
We develop a general approach for stress testing correlations of financial asset portfolios. The correlation matrix of asset returns is specified in a parametric form, where correlations are represented as a function of risk factors, such as country and industry factors. A sparse factor structure linking assets and risk factors is built using Bayesian variable selection methods. Regular calibration yields a joint distribution of economically meaningful stress scenarios of the factors. As such, the method also lends itself as a reverse stress testing framework: using the Mahalanobis distance or highest density regions (HDR) on the joint risk factor distribution allows to infer worst-case correlation scenarios. We give examples of stress tests on a large portfolio of European and North American stocks.
Diversified reward-risk parity in portfolio construction
Jaehyung Choi (Goldman Sachs), et al.
June 18, 2021
We introduce diversified risk parity embedded with various reward-risk measures and more general allocation rules for portfolio construction. We empirically test advanced reward-risk parity strategies and compare their performance with an equally-weighted risk portfolio in various asset universes. All reward-risk parity strategies we tested exhibit consistent outperformance evidenced by higher average returns, Sharpe ratios, and Calmar ratios. The alternative allocations also reflect less downside risks in Value-at-Risk, conditional Value-at-Risk, and maximum drawdown. In addition to the enhanced performance and reward-risk profile, transaction costs can be reduced by lowering turnover rates. The Carhart four-factor analysis also indicates that the diversified reward-risk parity allocations gain superior performance.
The Overnight Drift in U.S. Equity Returns
Nina Boyarchenko (NY Federal Reserve), et al.
May 26, 2021
Since the advent of electronic trading in the late 1990s, S&P 500 futures have traded close to 24 hours a day. In this post, which draws on our recent Staff Report, we document that holding U.S. equity futures overnight has earned a large positive return during the opening hours of European markets. The largest positive returns in the 1998–2019 sample have accrued between 2 a.m. and 3 a.m. U.S. Eastern time—the opening of European stock markets—and averaged 3.6 percent on an annualized basis, a phenomenon we call the overnight drift.
Can Financial Soundness Indicators Help Predict Financial Sector Distress?
Marcin Pietrzak (Brown University)
July 23, 2021
This paper shows how the role of Financial Soundness Indicators (FSIs) in financial surveillance can be usefully enhanced. Drawing from different statistical techniques, the paper illustrates that FSIs generate signals that can accurately detect, with 4 to 12 quarters lead, emerging financial distress—as measured by tight financial conditions.
Economic drivers of volatility and correlation in precious metal markets
Theu Dinh (University of Paris-Saclay), et al.
July 27, 2021
We investigate the time-varying dynamics of the precious metal markets. We employ a mixed data sampling technique to identify the impact of macroeconomic and financial drivers from G7 and BRICS countries on the daily volatility and pairwise correlation of gold, silver, platinum, and palladium. We find that the U.S. and Chinese economies especially influence the precious metal markets, but in opposite directions. Besides, the stock markets and trade balance of both G7 and BRICS countries as well as the consumer confidence of G7 countries are the key drivers for the volatility of precious metals. The most influential drivers for correlation are stock markets, money supply, and the inflation rate. Surprisingly, the economic policy uncertainty does not affect the dynamics as much as expected. Lastly, the global financial crisis 2008 affected the direction of most of the macroeconomic and financial drivers.
The Bitcoin Gold Correlation Puzzle
Dirk G. Baur and Lai T. Hoang (University of Western Australia)
July 1, 2021
Bitcoin is regularly referred to as new gold, digital gold or gold 2.0. If Bitcoin is indeed gold-like the correlation of Bitcoin and gold returns should be positive. We estimate the correlation of the two assets across time, across different return frequencies and across quantiles and find a near-zero correlation inconsistent with the claimed similarity. We offer two explanations for this puzzle: either the similarity is only a narrative and not accepted by investors or there are other forces at play that depress the true correlation. Such forces could be a substitution effect, investors sell gold and buy Bitcoin, and a catching up effect, investors buy Bitcoin to catch up with the market weight of gold.
Exploring Risk Premium Factors for Country Equity Returns
Giovanni Calice (Loughborough University) and
Ming-Tsung Lin (University of Essex)
April 6, 2021
In this paper, we study a comprehensive set of risk premia of country equity returns for 45 countries over the sample period 2002 to 2018 in both a single and a multiple factor setting. Using a new three-pass estimation method for factor risk premia by Giglio and Xiu (2021), we find that several factors, including default risk, are also priced in country equity excess returns, controlled by the Fama-French 5-factor and Carhart model. Moreover, we apply a novel approach to investigate the multi-factor impact on country equity returns. We find that the multi-factor information, constructed from the first principal component of the statistically significant single factors, provides a consistent and stronger prediction of anomalies in country equity returns.
Identifying Signals of the Cross Section of Stock Returns
Tengjia Shu and Ashish Tiwari (University of Iowa)
Augiust 2, 2021
The proliferation of anomalies and the resulting `factor zoo’ has challenged finance researchers to identify firm characteristics that are genuinely related to the cross-sectional variation in expected stock returns. We address this challenge using a Bayesian ensemble of trees approach, namely, Bayesian Additive Regression Trees (BART), which combines the advantages of machine learning with a Bayesian inference framework. Applying the methodology to U.S. stock returns and a large set of characteristics, we find a firm’s market value is the sole consistently relevant characteristic. A BART framework that exploits the information content of a sparse set of characteristics identified in real time, offers substantial gains over competing models in both statistical and economic terms. We further confirm that the stochastic discount factor based on a sparse set of factors can successfully explain most of the variation in expected returns. A key reason for the sparsity of the factor set identified by BART is the methodology’s ability to incorporate non-linearities and high order interaction effects in a non-parametric manner. Our findings suggest that the vast majority of the documented anomalies are redundant, and in this sense our results offer a more optimistic view of the state of affairs in asset pricing.
Learn To Use R For Portfolio Analysis
Quantitative Investment Portfolio Analytics In R:
An Introduction To R For Modeling Portfolio Risk and Return
By James Picerno