Corrections for Trading Frictions in Multivariate Returns

When observed stock returns are obtained from trades subject to friction, it is known that an individual stock's beta and covariance are measured with error. Univariate models of additive error adjustment are available and are often applied simultaneously to more than one stock. Unfortunately, these multivariate adjustments produce non-positive definite covariance and correlation matrices, unless the return sample sizes are very large. To prevent this, restrictions on the adjustment matrix are developed and a correction is proposed, which dominates the uncorrected estimator. The estimators are illustrated with asset opportunity set estimates where daily returns have trading frictions.     

Empirical properties of large covariance matrices

The salient properties of large empirical covariance and correlation matrices are studied for three datasets of size 54, 55 and 330. The covariance is defined as a simple cross product of the returns, with weights that decay logarithmically slowly. The key general properties of the covariance matrices are the following. The spectrum of the covariance is very static, except for the top three to 10 eigenvalues, and decay exponentially fast toward zero. The mean spectrum and spectral density show no particular feature that would separate ‘meaningful’ from ‘noisy’ eigenvalues. The spectrum of the correlation is more static, with three to five eigenvalues that have distinct dynamics. The mean projector of rank k on the leading subspace shows that a large part of the dynamics occurs in the eigenvectors. Together, this implies that the reduction of the covariance to a few leading static eigenmodes misses most of the dynamics. Finally, all the analysed properties of the dynamics of the covariance and correlation are similar. This indicates that a covariance estimator correctly evaluates both volatilities and correlations, and separate estimators are not required.     

When do improved covariance matrix estimators enhance portfolio optimization? An empirical comparative study of nine estimators

The use of improved covariance matrix estimators as an alternative to the sample estimator is considered an important approach for enhancing portfolio optimization. Here we empirically compare the performance of nine improved covariance estimation procedures using daily returns of 90 highly capitalized US stocks for the period 1997–2007. We find that the usefulness of covariance matrix estimators strongly depends on the ratio between the estimation period T and the number of stocks N, on the presence or absence of short selling, and on the performance metric considered. When short selling is allowed, several estimation methods achieve a realized risk that is significantly smaller than that obtained with the sample covariance method. This is particularly true when T/N is close to one. Moreover, many estimators reduce the fraction of negative portfolio weights, while little improvement is achieved in the degree of diversification. On the contrary, when short selling is not allowed and T?>?N, the considered methods are unable to outperform the sample covariance in terms of realized risk, but can give much more diversified portfolios than that obtained with the sample covariance. When T?<?N, the use of the sample covariance matrix and of the pseudo-inverse gives portfolios with very poor performance.     

Random matrix ensembles of time-lagged correlation matrices: derivation of eigenvalue spectra and analysis of financial time-series

We derive the exact form of the eigenvalue spectra of correlation matrices derived from a set of time-shifted, finite Brownian random walks (time-series). These matrices can be seen as real, asymmetric random matrices where the time-shift superimposes some structure. We demonstrate that, for large matrices, the associated eigenvalue spectrum is circular symmetric in the complex plane. This fact allows us to exactly compute the eigenvalue density via an inverse Abel-transform of the density of the symmetrized problem. We demonstrate the validity of this approach numerically. Theoretical findings are then compared with eigenvalue densities obtained from actual high-frequency (5 min) data of the S&P 500 and the observed deviations are discussed. We identify various non-trivial, non-random patterns and find asymmetric dependencies associated with eigenvalues departing strongly from the Gaussian prediction in the imaginary part. For the same time-series, with the market contribution removed, we observe strong clustering of stocks into causal sectors. We finally comment on the stability of the observed patterns.     

Covariance and correlation stationarity: Experiences from seven Asian emerging markets

Because of the rising interest and the growing importance of the Asian emerging markets in international diversification, this paper examines the covariance and correlation stationarity in stock return relationships among seven Asian emerging markets. This paper also covers the issue of seasonality in stock return co-movements. Empirical results show that because the correlations among them and those with other developed markets are very small, huge gains from diversifying into the seven Asian emerging markets are possible. Results on stationarity indicate that correlation matrices of stock returns are much more stable then the corresponding variance-covariance matrices and that the length of the estimation period seems to have no impact on the stationarity of the correlation matrix. We also found that virtually no seasonality in the correlations exists among the seven Asian emerging markets. However, we did find that during our sample period covariance among stock returns is nonstationary in January. The author thanks an anonymous referee ofFinancial Engineering and the Japanese Markets for the valuable comments on the earlier version of this article.     

Is information risk priced for NASDAQ-listed stocks?

Easley et al. (J Finance 57:2185–2221, 2002), building upon the asset pricing model of Fama and French (J Finance 47:427–465, 1992), show that the probability of informed trading (PIN) is a determinant of asset returns for NYSE-listed securities. We extend this work by examining whether the PIN is a predictive factor for NASDAQ stocks, as many studies document significant differences between NYSE and NASDAQ listed securities. In the process we examine whether the use of PIN is appropriate for NASDAQ-listed securities. We find that PIN and certain stock characteristics correlate differently for our sample of NASDAQ stocks than that of Easley et al. sample of NYSE stocks. We also determine that the risk of informed trading is only weakly priced for NASDAQ stocks. Contrary to Easley et al. we do not find evidence that excess returns increases as PIN increases.     

Random matrix models for datasets with fixed time horizons

This paper examines the use of random matrix theory as it has been applied to model large financial datasets, especially for the purpose of estimating the bias inherent in Mean-Variance portfolio allocation when a sample covariance matrix is substituted for the true underlying covariance. Such problems were observed and modeled in the seminal work of Laloux et al. [Noise dressing of financial correlation matrices. Phys. Rev. Lett., 1999, 83, 1467] and rigorously proved by Bai et al. [Enhancement of the applicability of Markowitz's portfolio optimization by utilizing random matrix theory. Math. Finance, 2009, 19, 639–667] under minimal assumptions. If the returns on assets to be held in the portfolio are assumed independent and stationary, then these results are universal in that they do not depend on the precise distribution of returns. This universality has been somewhat misrepresented in the literature, however, as asymptotic results require that an arbitrarily long time horizon be available before such predictions necessarily become accurate. In order to reconcile these models with the highly non-Gaussian returns observed in real financial data, a new ensemble of random rectangular matrices is introduced, modeled on the observations of independent Lévy processes over a fixed time horizon.     

The impact of hedging on the market value of equity

We examine the annual stock performance of firms that disclose the use of derivatives to hedge over the period 1995 to 1999. We find that only 21.6% of publicly traded U.S. corporations in our sample hedged with derivative instruments over this period and their use is concentrated in the larger companies. Similar to other studies we find that when derivatives are used, interest rate and currency securities are used much more frequently than commodity products. Our sample of 1308 companies that hedge outperforms other securities by 4.3% per year on average over our sample period. This result is robust to several alternative methods of estimating abnormal returns. When we segment performance by the type of hedge used, however, we find that the over-performance is due entirely to larger firms that hedge currency. We find no abnormal returns for firms hedging either interest rates or commodities. The abnormal returns in firms hedging currency is robust to alternative models that seek to control for exchange rate fluctuations and global equity returns; however, we find no significant abnormal returns to currency hedgers when using an augmented model that controls for the role of intangible assets.     

The Number of Factors in Security Returns

Both factor analysis of security returns and the analysis of eigenvalues seem to indicate that a market factor explains the major part of security returns. We find that such evidence is consistent with an economy where there are in fact k “equally important” priced factors; eigenvalue analysis in the context of such an economy will lead an investigator to the false inference that the one important “factor” is the return on an equally weighted market index.     

UK Evidence on the Characteristics versus Covariance Debate

We evaluate the Fama–French three‐factor model in the UK using the approach of Daniel and Titman (1997) to determine whether characteristics or covariance risk better explains the size and value premiums. Across all three factors, we find that return premiums bear little relationship to the corresponding loadings. We show that small and value stocks earn higher returns irrespective of their return covariance. Our study contributes to the existing literature by reporting original findings on the Fama–French three‐factor model in the UK and by reporting results that complement existing evidence from similar studies in the USA and Japan.     

The Irrelevance of Margin: Evidence from the Crash of '87

Following the crash of 1987, one contentious regulatory issue has been whether margin activity exacerbated the decline in equity values. We contrast the crash behavior of NASDAQ securities eligible for margin trading with the behavior of ineligible ones. Consistent with the hypothesis that margin-eligible securities were more frequently subjected to margin calls and forced sales, we find that abnormal volumes were uniformly larger for eligible securities. However, there is no evidence that this activity provoked additional price depreciation. Margin-eligible securities actually fell by one percent less than the ineligible securities over the period.     

Adjusting covariance matrix for risk management

The covariance matrix of asset returns can change drastically and generate huge losses in portfolio value under extreme conditions such as market interventions and financial crises. Estimation of the covariance matrix under a chaotic market is often a call to action in risk management. Nowadays, stress testing has become a standard procedure for many financial institutions to estimate the capital requirement for their portfolio holdings under various stress scenarios. A possible stress scenario is to adjust the covariance matrix to mimic the situation under an underlying stress event. It is reasonable that when some covariances are altered, other covariances should vary as well. Recently, Ng et al. proposed a unified approach to determine a proper correlation matrix which reflects the subjective views of correlations. However, this approach requires matrix vectorization and hence it is not computationally efficient for high dimensional matrices. Besides, it only adjusts correlations, but it is well known that high correlations often go together with high standard deviations during a crisis period. To address these limitations, we propose a Bayesian approach to covariance matrix adjustment by incorporating subjective views of covariances. Our approach is computationally efficient and can be applied to high dimensional matrices.     

Information Uncertainty and Post-Earnings-Announcement-Drift

Abstract:  We examine whether rational investor responses to information uncertainty (IU) explain properties of and returns to the post-earnings-announcement-drift (PEAD) trading anomaly. Consistent with a rational learning explanation, we find that: (1) unexpected earnings (UE) signals that are characterized as having greater IU have more muted initial market reactions; (2) extreme UE portfolios are characterized by securities with higher IU than non-extreme UE portfolios; and (3) within the extreme UE portfolios, high IU securities are more prevalent and earn larger abnormal returns than low IU securities. Further tests show that prior evidence of greater PEAD profitability for higher idiosyncratic volatility securities is explained by the greater information uncertainty associated with these securities.     

Convertible securities in merger transactions

This paper provides a rationale for the use of convertible securities as the medium of exchange in corporate change-of-control transactions. We argue that convertible securities can resolve the information asymmetry about the bidder’s value while at the same time mitigating the information asymmetry about the target’s value. In contrast, deals with cash or stock can only address one information asymmetry or the other but not both. Empirically, we find that a bidder is more likely to offer convertible securities, rather than all cash or all stock, when both the bidder and its target face large asymmetric information problems. We also find that both bidders and targets in convertible deals enjoy positive abnormal stock returns around takeover announcements. These findings provide empirical support for the use of convertible securities to resolve the double-sided asymmetric information problem. Finally, we find that bidder returns in convertible deals are larger than in all-cash and all-stock deals, but that target returns in convertible deals are smaller than in all-cash and all-stock deals.     

The Seasonal Stability of the Factor Structure of Stock Returns

This paper investigates the month-by-month stability of (a) daily returns and correlation coefficients of stock returns, (b) correlation and covariance matrices, (c) number of return-generating factors, and (d) the APT pricing relationship. The results show that there is a January effect and a small-firm effect in stock returns. Correlation matrices are more stable than covariance matrices, but both types of matrices are not stable across months and across the sample groups. The number of return-generating factors is rather stable most of the time and for most of the sample groups, but there is some significant instability that is related to the average correlation coefficients among stocks. The APT pricing relationship does not seem to be supported by the two-stage process using the maximum-likelihood factor analysis.     

EMPIRICAL EVIDENCE ON THE IMPACT OF THE BID-ASK SPREAD ON THE CHARACTERISTICS OF CRSP DAILY RETURNS

It is widely recognized that Center for Research in Security Prices (CRSP) returns may differ from “true” returns because of the bid-ask effect. Using a large sample of New York Stock Exchange and American Stock Exchange securities, I confirm a discernible bid-ask effect, the magnitude and importance of which decrease with the security's price level (increase with the spread). I find volatility estimates using CRSP returns to be greater than those based on quote returns. However, market model properties, such as β and R², are generally unaffected. Bid-ask effects are clearly apparent in event studies, but because of certain offsetting effects commonly used test statistics remain unaffected. Low-priced stocks (below $2.00) do not conform to these patterns. Finally, the evidence raises the possibility that the existing literature on filter rule tests may underestimate the bid-ask spread component of transaction costs.     

Risk Reduction and Mean-Variance Analysis: An Empirical Investigation

Abstract:  I examine the performance of global minimum variance (GMV) and minimum tracking error variance (TEV) portfolios in UK stock returns using different models of the covariance matrix. I find that both GMV and TEV portfolios deliver portfolio risk reduction benefits in terms of significantly lower volatility and tracking error volatility relative to passive benchmarks for every model of the covariance matrix used. However, the GMV (TEV) portfolios do not provide significantly superior Sharpe (1966) (adjusted Sharpe) performance relative to passive benchmarks except for the restricted GMV portfolios. I find that a number of alternative covariance matrix models can improve the performance of the restricted TEV portfolio formed using the sample covariance matrix but not the restricted GMV portfolio. I also find that simpler covariance matrix models perform as well as the more sophisticated models.     

Factor state–space models for high-dimensional realized covariance matrices of asset returns

We propose a dynamic factor state–space model for high-dimensional covariance matrices of asset returns. It makes use of observed risk factors and assumes that the latent integrated joint covariance matrix of the assets and the factors is observed through their realized covariance matrix with a Wishart measurement density. For the latent integrated covariance matrix of the assets we impose a strict factor structure allowing for dynamic variation in the covariance matrices of the factors and the residual components as well as in the factor loadings. This factor structure translates into a factorization of the Wishart measurement density which facilitates statistical inference based on simple Bayesian MCMC procedures making the approach scalable w.r.t. the number of assets. An empirical application to realized covariance matrices for 60 NYSE traded stocks using the Fama–French factors and sector-specific factors represented by Exchange Traded Funds (ETFs) shows that the model performs very well in- and out of sample.     

THE CROSS-AUTOCORRELATION OF SIZE-BASED PORTFOLIO RETURNS IS NOT AN ARTIFACT OF PORTFOLIO AUTOCORRELATION

Prior studies find evidence of asymmetric size-based portfolio return cross-autocorrelations where lagged large firm returns lead current small firm returns. However, some studies question whether this economic relation is independent of the effect of portfolio return autocorrelation. We formally test for this independence using size-based portfolios of New York Stock Exchange and American Stock Exchange securities and, separately, portfolios of Nasdaq securities. Results from causality regressions indicate that, across all markets, lagged large firm returns predict current small firm returns, even after controlling for autocorrelation in small firm returns. These cross-autocorrelation patterns are stronger for Nasdaq securities.     

Dynamic principal component CAW models for high-dimensional realized covariance matrices

We propose a new dynamic principal component CAW model (DPC-CAW) for time-series of high-dimensional realized covariance matrices of asset returns (up to 100 assets). The model performs a spectral decomposition of the scale matrix of a central Wishart distribution and assumes independent dynamics for the principal components' variances and the eigenvector processes. A three-step estimation procedure makes the model applicable to high-dimensional covariance matrices. We analyze the finite sample properties of the estimation approach and provide an empirical application to realized covariance matrices for 100 assets. The DPC-CAW model has particularly good forecasting properties and outperforms its competitors for realized covariance matrices.