Search

In this paper we propose a novel approach to estimating and testing skewness in a stochastic volatility (SV) model. Our key idea is to replace a normal return error in the standard SV model with a split normal error. We show that this simple variation in the model brings about two large computational advantages. First, the SV can be simulated fast and efficiently using a one-block Gibbs sampling technique. Second, more importantly, this is the first to provide a marginal likelihood calculation method to formally test the skewness and SV in a Bayesian framework. We subsequently demonstrate the efficiency and reliability of our posterior sampling and model comparison methods through a simulation study. The simulation study results also show that neglecting skewness leads to inaccurate SV estimates and conditional expected returns. Our empirical applications to daily stock return data also show strong evidence of negative skewness.

Option-based measures can predict underlying stock returns, due to differences in price discovery and price pressure effects between options and underlying stocks. We investigate stock return predictability by various option price-based measures using REITs. REITs are more transparent and efficiently priced than general stocks, but REIT options are less liquid. Consistent with the model of Easley, O’Hara, and Srinivas (1998), most of the option price-based measures do not significantly forecast REIT stock returns, but changes in option implied volatilities are robust and significant return predictors. We provide further evidence supporting the informed trading channel instead of the price pressure effects.

The idiosyncratic volatility (IVOL) anomaly, documented in Ang, et al. (2006), has garnered a great deal of attention in the literature. Yet questions remain regarding the robustness and pervasiveness of the IVOL anomaly, with a particular concern that the IVOL anomaly might simply be the manifestation of market microstructure effect. In this paper, we show that the IVOL anomaly is strong and pervasive after we exclude stocks most susceptible to market microstructure noise — such as microcap stocks, penny stocks, and stocks with strong short-term return reversal. These results are robust to equal-weighting or value-weighting stocks in the IVOL portfolios. Our findings suggest that rather than being the cause of the anomaly, market microstructure noise actually weakens the IVOL anomaly.

This study shows that, to obtain a precise measure of the liquidity premium in the stock market, it is important to recognize the influence of information uncertainty on the pricing of liquidity. Information uncertainty, which is positively correlated with stock illiquidity but negatively priced in the stock market, obscures the estimation of the liquidity premium. After controlling for its influence, we find that the liquidity premium is statistically significant and economically important in the U.S. stock market. Moreover, the risk-adjusted liquidity premium remains significant in both the earlier and more recent sub-sample periods. Our study addresses the recent debate about whether liquidity is still priced in recent decades, given the significant improvement in the trading technology and increase of the trading volume during this period.

In a predictive regression, a less persistent return series is regressed on the first lag of some highly persistent predictors. Therefore, predictability could often be missed due to the persistence imbalance. The aim of this paper is to balance the predictive regression by augmenting it with an additional lag of the predictors. This second lag generally reduces the persistence level on the right-hand side of the equation to achieve balance. We then propose a simple test procedure for univariate and multivariate predictive regressions, based on least squares estimation. Empirically, we reexamine the popular predictors in the literature and find quite different results.

It has been documented that vertical customer–supplier links between industries are the basis for strong cross-sectional stock return predictability ( Menzly and Ozbas, 2010 ). We show that robust predictability also arises from horizontal links between industries, i.e., from the fact that industries are competitors or offer products, which are substitutes for each other. These horizontally linked industries exhibit positively correlated fundamentals. The signal derived from this type of connectedness is the basis for significant alpha in sorted portfolio strategies, and informed investors take the related information into account when they form their portfolios. We thus provide evidence of return predictability based on a new type of economic links between industries not captured in previous studies.

We show that when the disposition effect and anchoring bias of investors reinforce each other, the momentum profit is strengthened. When the two effects offset each other, the momentum profit decreases or disappears. Second, stocks dominated by small investors, with low analyst coverage, and illiquidity issues show greater momentum profits in presence of these mutually reinforcing biases. Third, stock return in momentum strategy show reversal in the long run when they are affected by both anchoring bias and disposition effect consistent with prior literature.

We find the momentum of predictability (MoP) that the forecasting performance of some univariate regressions is persistent. A univariate model which outperforms the benchmark during recent past period can also beat the benchmark in the near future out-of-sample. Accordingly, we propose a forecasting strategy that involves switching between a model of interest and the benchmark model, based on observations of their recent past performance. We obtain significant stock return predictability both in statistical and economic terms. Predictability is found to be stronger for longer forecasting horizons. Success of the MoP strategy is also seen in forecasting exchange rates.

This paper analyzes the effects of news and its sentiment on the idiosyncratic volatility ( IVOL ) — expected return relation. We postulate that the perceived negative IVOL -expected return relation could be the artifact of the confounding effect of public news arrivals. Using the stock return data from the Center for Research in Security Prices (CRSP) database and the news database from the RavenPack News Analytics over the period from 2000 to 2011, we show that the strength of the positive relation is reduced systematically by 50% after accounting for the arrivals of good and bad news releases, which are defined by their sentiment scores. This finding is robust to numerous model specifications, and the inclusion of firm-level characteristics, liquidity risk and information risk. When we restrict the firm-specific news to value-relevant news, the positive relation disappears. We conclude that that the public arrivals of firm-specific news play a significant role in explaining the IVOL puzzle.

I propose a test of asymmetric stock return comovement across states. The test can be viewed as a variation of Kendall's τ conditional on the state and has an asymptotic χ2-distribution. A refined version of the test is derived based on the Markov chain theory of regenerative cycles which substantially improves finite sample size and power properties. I show that the test has power against local alternatives, which is nonetheless compromised due to a finite sample convergence bound put on the implied local alternative data generating process. I evaluate the new test against traditional correlation-based measures and demonstrate power attrition of a state-free tail dependence test as parameter values are varied. Broad market-based ETFs and international indices are studied and in most cases there is no compelling evidence for asymmetric comovement across states. A list of related tests is given as an extension at the end.

This paper provides strong evidence of time-varying return predictability of the Dow Jones Industrial Average index from 1900 to 2009. Return predictability is found to be driven by changing market conditions, consistent with the implication of the adaptive markets hypothesis. During market crashes, no statistically significant return predictability is observed, but return predictability is associated with a high degree of uncertainty. In times of economic or political crises, stock returns have been highly predictable with a moderate degree of uncertainty in predictability. We find that return predictability has been smaller during economic bubbles than in normal times. We also find evidence that return predictability is associated with stock market volatility and economic fundamentals.

We examine the predictive ability of earnings-price ratios or yields for the S&P 500 index. We decompose the aggregate earnings-price ratio into its positive and negative components (“winners” vs “losers”) and find that the negative component has the most predictive ability. We also find that the earnings-price measures forecast both future returns and earnings growth. Our models display substantial variation in explanatory power over time with forecast power resurfacing in the latter 1990s. We conclude that to the extent that earnings-price yields predict future S&P 500 returns, the negative earnings component is the driving factor.

We undertake an extensive analysis of in-sample and out-of-sample tests of stock return predictability in an effort to better understand the nature of the empirical evidence on return predictability. We find that a number of financial variables appearing in the literature display both in-sample and out-of-sample predictive ability with respect to stock returns in annual data covering most of the twentieth century. In contrast to the extant literature, we demonstrate that there is little discrepancy between in-sample and out-of-sample test results once we employ out-of-sample tests with good power. While conventional wisdom holds that out-of-sample tests help guard against data mining, Inoue and Kilian [Inoue, A., Kilian, L., 2004. In-sample or out-of-sample tests of predictability: which one should we use? Econometric Reviews 23, 371–402.] recently argue that in-sample and out-of-sample tests are equally susceptible to data mining biases. Using a bootstrap procedure that explicitly accounts for data mining, we still find that certain financial variables display significant in-sample and out-of-sample predictive ability with respect to stock returns.