Jun Tu

Forecasting the Equity Risk Premium: The Role of Technical Indicators

Academic research relies extensively on macroeconomic variables to forecast the U.S. equity risk premium, with relatively little attention paid to the technical indicators widely employed by practitioners. Our paper fills this gap by comparing the predictive ability of technical indicators with that of macroeconomic variables. Technical indicators display statistically and economically significant in-sample and out-of-sample predictive power, matching or exceeding that of macroeconomic variables. Furthermore, technical indicators and macroeconomic variables provide complementary information over the business cycle: technical indicators better detect the typical decline in the equity risk premium near business-cycle peaks, whereas macroeconomic variables more readily pick up the typical rise in the equity risk premium near cyclical troughs. Consistent with this behavior, we show that combining information from both technical indicators and macroeconomic variables significantly improves equity risk premium forecasts versus using either type of information alone. Overall, the substantial countercyclical fluctuations in the equity risk premium appear well captured by the combined information in technical indicators and macroeconomic variables. Data, as supplemental material, are available at http://dx.doi.org/10.1287/mnsc.2013.1838 . This paper was accepted by Wei Jiang, finance.

Is Regime Switching in Stock Returns Important in Portfolio Decisions

The stock market displays regime switching between upturns and downturns. This paper provides a Bayesian framework for making portfolio decisions that takes this regime switching into account, together with asset pricing model uncertainty and parameter uncertainty. The findings reveal that the economic value of accounting for regimes is substantially independent of whether or not model and parameter uncertainties are incorporated: the certainty-equivalent losses associated with ignoring regime switching are generally above 2% per year and can be as high as 10%. These results suggest that the more realistic regime switching model is fundamentally different from the commonly used single-state model, and hence should be employed instead in portfolio decisions irrespective of concerns about model or parameter uncertainty.

Incorporating Economic Objectives into Bayesian Priors: Portfolio Choice under Parameter Uncertainty

This paper proposes a way to allow Bayesian priors to reflect the objectives of an economic problem. That is, we impose priors on the solution to the problem rather than on the primitive parameters whose implied priors can be backed out from the Euler equation. Using monthly returns on the Fama-French 25 size and book-to-market portfolios and their 3 factors from January 1965 to December 2004, we find that investment performances under the objective-based priors can be significantly different from those under alternative priors, with differences in terms of annual certainty-equivalent returns greater than 10% in many cases. In terms of an out-of-sample loss function measure, portfolio strategies based on the objective-based priors can substantially outperform both strategies under alternative priors and some of the best strategies developed in the classical framework.

Forecasting Government Bond Risk Premia Using Technical Indicators

While economic variables have been used extensively to forecast bond risk premia, little attention has been paid to technical indicators which are widely used by practitioners. In this paper, we study the predictive ability of a variety of technical indicators vis-a-vis the economic variables. We find that technical indicators have significant in both in- and out-of-sample forecasting power. Moreover, we find that using information from both technical indicators and economic variables increases the forecasting performance substantially. We also find that the economic value of bond risk premia forecasts from our methodology is comparable to that of equity risk premium forecasts.

Forecasting Stock Returns in Good and Bad Times: The Role of Market States

This paper proposes a state-dependent predictive regression model and finds that a market momentum predictor predicts the excess market return negatively in good times and positively in bad times. The out-of-sample R-square is 2.06% in NBER expansions and 1.84% in NBER recessions. There are similar predictability patterns in the cross-section of U.S. stocks and in the international markets. Our study shows the importance of market states in predicting stock returns, and finds that the concentration of return predictability in bad times, a well documented fact in the literature, is largely due to the assumption of a one-state predictive regression model.

Asset Allocation in the Chinese Stock Market: The Role of Return Predictability

In this article the authors investigate asset allocation in the Chinese stock market from the perspective of incorporating return predictability. Based on a host of return predictors, they find significant out-of-sample return predictability in the Chinese stock market. They then examine the performance of active portfolio strategies—such as aggregate market timing as well as industry, size, and value-rotation strategies—designed to profitably exploit return predictability. Strong evidence is found by the authors that these portfolio strategies incorporating return predictability can deliver superior performance—up to 600 basis points per annum and almost double the Sharpe ratios—compared with the passive buy-and-hold benchmarks that ignore return predictability.

Cost Behavior and Stock Returns

This paper shows that investors fail to fully incorporate cost behavior information into valuation. Firms with higher growth in operating costs generate substantially lower future stock returns. A long-short spread portfolio earns an average return of about 12% per year after controlling for extant risk factors and firm characteristics. Mean-variance spanning tests show that an investor can benefit from investing in this spread portfolio in addition to well-known factors. Firms with high cost growth also suffer from deterioration in future operating performance. The negative cost growth-return relation is much stronger around earnings announcement days, among firms with lower investor attention, higher idiosyncratic volatility, and higher transaction costs, suggesting that investor underreaction and limits to arbitrage mainly drive the effect.

Lotto, How to Win? Skew Timing Strategies

In this paper, we investigate whether the “lotto investor” can benefit from the time-varying skewness of market portfolio and how to capture the gain using skew timing strategies. We find that empirically applying the mean-variance-skewness (M-V-S) rule of Mitton and Vorkink (2007) generates similar performance as that of traditional mean-variance rule, because the optimal weight of M-V-S still mainly depends on the mean and variance unless the forecasted skewness is extremely large. To improve the M-V-S, we suggest combining two constrained versions of M-V-S, namely the mean-variance (M-V) and mean-skewness (M-S). Discarding the variance, the M-S fully considers the usefulness of skewness and the optimal weight solely depends on mean and skewness. However, M-S investor probably suffers huge loss due to forecasting errors. Combining the M-V with M-S should theoretically perform better than individual rules, and hence better than the M-V-S rule. Empirically, we find that the combination rule indeed generates superior performance, in terms of certainty equivalent returns, Sharpe ratios, and skewness of portfolio returns distribution.

Robust Measures of Earnings Surprises

In event studies of capital market efficiency, an earnings surprise has historically been measured by the consensus error, defined as earnings minus the consensus or average of professional forecasts. The rationale is that the consensus is an accurate measure of the market’s expectation of earnings. But since forecasts can be biased due to conflicts of interest and some investors can see through these conflicts, this rationale is flawed and the consensus error a biased measure of an earnings surprise. We show that the fraction of forecasts that miss on the same side (FOM), by ignoring the size of the misses, is less sensitive to such bias and a better measure of an earnings surprise. As a result, FOM out-performs the consensus error and its related robust statistics in explaining stock price movements around and subsequent to the announcement date.Event studies of market efficiency measure an earnings surprise with the consensus error (CE), defined as earnings minus the average of professional forecasts. If a subset of forecasts can be biased, the ideal but difficult to estimate parameter-dependent alternative to CE is a nonlinear filter of individual errors that adjusts for bias. We show that CE is a poor parameter-free approximation for this ideal measure. The fraction of misses on the same side FOM, by discarding the magnitude of misses, offers a far better approximation. FOM performs particularly well against CE in predicting the returns of US stocks, where bias is potentially large, than that of international stocks.