Time-varying risk premia and the cost of capital: An alternative implication of the Q theory of investment

Evidence suggests that expected excess stock market returns vary over time, and that this variation is much larger than that of expected real interest rates. It follows that a large fraction of the movement in the cost of capital in standard investment models must be attributable to movements in equity risk-premia. In this paper we emphasize that such movements in equity risk premia should have implications not merely for investment today, but also for future investment over long horizons. In this case, predictive variables for excess stock returns over long-horizons are also likely to forecast long-horizon fluctuations in the growth of marginal Q, and therefore investment. We test this implication directly by performing long-horizon forecasting regressions of aggregate investment growth using a variety of predictive variables shown elsewhere to have forecasting power for excess stock market returns.     

Category-specific EPU indices,macroeconomic variables and stock market return predictability

This paper mainly investigates whether the category-specific EPU indices have predictability for stock market returns. Empirical results show that the content of category-specific EPU can significantly predict the stock market return, no matter the individual category-specific EPU index or the principal component of category-specific EPU indices. In addition, the information of category-specific EPU indices can also have higher economic gains than traditional macroeconomic variables, even considering the trading cost and different investor risk aversion coefficients. During different forecasting windows, multi-period forecast horizons and the COVID-19 pandemic, we find the information contained in category-specific EPU indices can have better performances than that of the macroeconomic variables. Our paper tries to provide new evidence for stock market returns based on category-specific EPU indices.     

Investor Sentiment and Stock Returns: Evidence from Turkey

This paper investigates the relation between investor sentiment and stock returns on the Istanbul Stock Exchange, employing vector autoregressive (VAR) analysis and Granger causality tests. The sample period extends from July 1997 to June 2005. In the VAR models, stock portfolio returns and investor sentiment proxies are used as endogenous variables. Two dummy variables accounting for natural and economic crises are used as exogenous variables. The analysis results suggest that, excepting shares of equity issues in aggregate issues, stock portfolio returns seem to affect all investor sentiment proxies, namely closed-end fund discount, mutual fund flows, odd-lot sales-to-purchases ratio, and repo holdings of mutual funds. Investor sentiment does not appear to forecast future stock returns; only the turnover ratio of the stock market seems to have forecasting potential.     

Forecasting Japanese Stock Returns with Financial Ratios and Other Variables

This paper extends the previous analyses of the forecastability of Japanese stock market returns in two directions. First, we carefully construct smoothed market price–earnings ratios and examine their predictive ability. We find that the empirical performance of the price–earnings ratio in forecasting stock returns in Japan is generally weaker than both the price–earnings ratio in comparable US studies and the price dividend ratio. Second, we also examine the performance of several other forecasting variables, including lagged stock returns and interest rates. We find that both variables are useful in predicting aggregate stock returns when using Japanese data. However, while we find that the interest rate variable is useful in early subsamples in this regard, it loses its predictive ability in more recent subsamples. This is because of the extremely limited variability in interest rates associated with operation of the Bank of Japan’s zero interest policy since the late 1990s. In contrast, the importance of lagged returns increases in subsamples starting from the 2000s. Overall, a combination of logged price dividend ratios, lagged stock returns, and interest rates yield the most stable performance when forecasting Japanese stock market returns.     

Idiosyncratic Risk Matters!

This paper takes a new look at the predictability of stock market returns with risk measures. We find a significant positive relation between average stock variance (largely idiosyncratic) and the return on the market. In contrast, the variance of the market has no forecasting power for the market return. These relations persist after we control for macroeconomic variables known to forecast the stock market. The evidence is consistent with models of time‐varying risk premia based on background risk and investor heterogeneity. Alternatively, our findings can be justified by the option value of equity in the capital structure of the firms.     

The predictability of aggregate returns on commodity futures

This paper provides evidence that aggregate returns on commodity futures (without the returns on collateral) are predictable, both in-sample and out-of-sample, by various lagged variables from the stock market, bond market, macroeconomics, and the commodity market. Out of the 32 candidate predictors we consider, we find that investor sentiment is the best in-sample predictor of short-horizon returns, whereas the level and slope of the yield curve have much in-sample predictive power for long-horizon returns. We find that it is possible to forecast aggregate returns on commodity futures out-of-sample through several combination forecasts (the out-of-sample return forecasting R² is up to 1.65% at the monthly frequency).     

Forecasting the Correlation Structure of German Stock Returns: A Test of Firm-Specific Factor Models

This paper evaluates the performance of various factor models with firm-specific variables in forecasting correlation matrices at the German stock market. We investigate forecasts of correlations for a comprehensive sample and a sample of blue chips and analyse the impact of stock market crashes on the forecasting accuracy. Our empirical results show that the multi-factor models do not generally produce better forecasts than 'naive' models. Specifically, the traditional industry mean model significantly outperforms all other techniques in most of the time periods.     

Consumption, Aggregate Wealth, and Expected Stock Returns

This paper studies the role of fluctuations in the aggregate consumption–wealth ratio for predicting stock returns. Using U.S. quarterly stock market data, we find that these fluctuations in the consumption–wealth ratio are strong predictors of both real stock returns and excess returns over a Treasury bill rate. We also find that this variable is a better forecaster of future returns at short and intermediate horizons than is the dividend yield, the dividend payout ratio, and several other popular forecasting variables. Why should the consumption–wealth ratio forecast asset returns? We show that a wide class of optimal models of consumer behavior imply that the log consumption–aggregate wealth (human capital plus asset holdings) ratio summarizes expected returns on aggregate wealth, or the market portfolio. Although this ratio is not observable, we provide assumptions under which its important predictive components for future asset returns may be expressed in terms of observable variables, namely in terms of consumption, asset holdings and labor income. The framework implies that these variables are cointegrated, and that deviations from this shared trend summarize agents' expectations of future returns on the market portfolio.     

INTERTEMPORAL ASSET PRICING WITHOUT CONSUMPTION DATA: EMPIRICAL TESTS

In this paper I conduct tests of an intertemporal asset pricing model using variables that forecast stock returns as the risk factors. I document that the forecasting variables are priced so that expected excess returns are related to their conditional covariances with the forecasting variables. The variability in the covariance risk fails to explain the cross-sectional and time-series variation in expected stock returns. Evidence rejects restrictions on the prices of covariance risk imposed by the model with constant volatilities. I also find that an extended model that allows time-varying conditional volatilities is misspecified.     

STAR and ANN models: forecasting performance on the Spanish “Ibex-35” stock index

This paper studies whether it is possible to exploit the nonlinear behaviour of daily returns on the Spanish Ibex-35 stock index returns to improve forecasts over short and long horizons. In this sense, we examine the out-of-sample forecast performance of smooth transition autoregression (STAR) models and artificial neural networks (ANNs). We use one-step (obtained by using recursive and nonrecursive regressions) and multi-step-ahead forecasting methods. The forecasts are evaluated with statistical and economic criteria. In terms of statistical criteria, we compared the out-of-sample forecasts using goodness of forecast measures and various testing approaches. The results indicate that ANNs consistently surpass the random walk model and, although the evidence for this is weaker, provide better forecasts than the linear AR model and the STAR models for some forecast horizons and forecasting methods. In terms of the economic criteria, we assess the relative forecast performance in a simple trading strategy including the impact of transaction costs on trading strategy profits. The results indicate a better fit for ANN models, in terms of the mean net return and Sharpe risk-adjusted ratio, by using one-step-ahead forecasts. These results show there is a good chance of obtaining a more accurate fit and forecast of the daily stock index returns by using one-step-ahead predictors and nonlinear models, but that these are inherently complex and present a difficult economic interpretation.     

Forecasting stock market volatility: Further international evidence

Abstract

This paper evaluates the out-of-sample forecasting accuracy of eleven models for monthly volatility in fifteen stock markets. Volatility is defined as within-month standard deviation of continuously compounded daily returns on the stock market index of each country for the ten-year period 1988 to 1997. The first half of the sample is retained for the estimation of parameters while the second half is for the forecast period. The following models are employed: a random walk model, a historical mean model, moving average models, weighted moving average models, exponentially weighted moving average models, an exponential smoothing model, a regression model, an ARCH model, a GARCH model, a GJR-GARCH model, and an EGARCH model. First, standard (symmetric) loss functions are used to evaluate the performance of the competing models: mean absolute error, root mean squared error, and mean absolute percentage error. According to all of these standard loss functions, the exponential smoothing model provides superior forecasts of volatility. On the other hand, ARCH-based models generally prove to be the worst forecasting models. Asymmetric loss functions are employed to penalize under-/over-prediction. When under-predictions are penalized more heavily, ARCH-type models provide the best forecasts while the random walk is worst. However, when over-predictions of volatility are penalized more heavily, the exponential smoothing model performs best while the ARCH-type models are now universally found to be inferior forecasters.     

The usefulness of cross-sectional dispersion for forecasting aggregate stock price volatility

Does cross-sectional dispersion in the returns of different stocks help forecast volatility of the S&P 500 index? This paper develops a model of stock returns where dispersion in returns across different stocks is modeled jointly with aggregate volatility. Although specifications that allow for feedback from cross-sectional dispersion to aggregate volatility have a better fit in sample, they prove not to be robust for purposes of out-of-sample forecasting. Using a full cross-section of stock returns jointly, however, I find that use of cross-sectional dispersion can help improve parameter estimates of a GARCH process for aggregate volatility to generate better forecasts both in sample and out of sample. Given this evidence, I conclude that cross-sectional information helps predict market volatility indirectly rather than directly entering in the data-generating process.     

A comprehensive investigation on the predictive power of economic policy uncertainty from non-U.S. countries for U.S. stock market returns

This study uses economic policy uncertainty (EPU) indices for ten developed countries, three diffusion models, and five combination methods to forecast excess returns in the U.S. stock market. It shows empirically that, over the period January 1997 to January 2022, non-U.S. EPU indices have better predictive power for U.S. equity market excess returns than the U.S. EPU index itself. This illustrates how economic information from international markets can affect the U.S. stock market. This finding challenges the extensively recognized view that the U.S. is where important market signals are initially transmitted to other markets, suggesting that this belief is incomplete. Our outcomes are robust to a battery of tests covering model selection, model specification, forecast horizons, and the pandemic period, and their economic values are assessed. The findings are essential for the financial field to confront future fierce situations and crises.     

Real‐Time Forecasting and Political Stock Market Anomalies: Evidence for the United States

Using monthly data from 1953 to 2003, we apply a real‐time modeling approach to investigate the implications of U.S. political stock market anomalies for forecasting excess stock returns in real‐time. Our empirical findings show that political variables, chosen on the basis of widely used model‐selection criteria, are often included in real‐time forecasting models. However, political variables do not contribute systematically to improving the performance of simple trading rules. For this reason, political stock market anomalies are not necessarily an indication of market inefficiency.     

The empirical similarity approach for volatility prediction

In this paper we adapt the empirical similarity (ES) concept for the purpose of combining volatility forecasts originating from different models. Our ES approach is suitable for situations where a decision maker refrains from evaluating success probabilities of forecasting models but prefers to think by analogy. It allows to determine weights of the forecasting combination by quantifying distances between model predictions and corresponding realizations of the process of interest as they are perceived by decision makers. The proposed ES approach is applied for combining models in order to forecast daily volatility of the major stock market indices.     

Earnings and Expected Returns

The aggregate dividend payout ratio forecasts excess returns on both stocks and corporate bonds in postwar U.S. data. High dividends forecast high returns. High earnings forecast low returns. The correlation of earnings with business conditions gives them predictive power for returns; they contain information about future returns that is not captured by other variables. Dividends and earnings contribute substantial explanatory power at short horizons. For forecasting long-horizon returns, however, only (scaled) stock prices matter. Forecasts of low long-horizon stock returns in the mid-1990s are caused not by earnings or dividends, but by high stock prices.     

Forecasting daily variability of the S&P 100 stock index using historical,realised and implied volatility measurements

The increasing availability of financial market data at intraday frequencies has not only led to the development of improved volatility measurements but has also inspired research into their potential value as an information source for volatility forecasting. In this paper, we explore the forecasting value of historical volatility (extracted from daily return series), of implied volatility (extracted from option pricing data) and of realised volatility (computed as the sum of squared high frequency returns within a day). First, we consider unobserved components (UC-RV) and long memory models for realised volatility which is regarded as an accurate estimator of volatility. The predictive abilities of realised volatility models are compared with those of stochastic volatility (SV) models and generalised autoregressive conditional heteroskedasticity (GARCH) models for daily return series. These historical volatility models are extended to include realised and implied volatility measures as explanatory variables for volatility. The main focus is on forecasting the daily variability of the Standard & Poor's 100 (S&P 100) stock index series for which trading data (tick by tick) of almost 7 years is analysed. The forecast assessment is based on the hypothesis of whether a forecast model is outperformed by alternative models. In particular, we will use superior predictive ability tests to investigate the relative forecast performances of some models. Since volatilities are not observed, realised volatility is taken as a proxy for actual volatility and is used for computing the forecast error. A stationary bootstrap procedure is required for computing the test statistic and its p-value. The empirical results show convincingly that realised volatility models produce far more accurate volatility forecasts compared to models based on daily returns. Long memory models seem to provide the most accurate forecasts.     

Market Timing And Model Uncertainty: An Exploratory Study For The Swiss Stock Market

We use statistical model selection criteria and Avramov's (2002) Bayesian model averaging approach to analyze the sample evidence of stock market predictability in the presence of model uncertainty. The empirical analysis for the Swiss stock market is based on a number of predictive variables found important in previous studies of return predictability. We find that it is difficult to discard any predictive variable as completely worthless, but that the posterior probabilities of the individual forecasting models as well as the cumulative posterior probabilities of the predictive variables are time-varying. Moreover, the estimates of the posterior probabilities are not robust to whether the predictive variables are stochastically detrended or not. The decomposition of the variance of predicted future returns into the components parameter uncertainty, model uncertainty, and the uncertainty attributed to forecast errors indicates that the respective contributions strongly depend on the time period under consideration and the initial values of the predictive variables. In contrast to AVRAMOV (2002), model uncertainty is generally not more important than parameter uncertainty. Finally, we demonstrate the implications of model uncertainty for market timing strategies. In general, our results do not indicate any reliable out-of-sample return predictability. Among the predictive variables, the dividend-price ratio exhibits the worst external validation on average. Again in contrast to AVRAMOV (2002), our analysis suggests that the out-of-sample performance of the Bayesian model averaging approach is not superior to the statistical model selection criteria. Consequently, model averaging does not seem to help improve the performance of the resulting short-term market timing strategies.     

A comprehensive look at stock return predictability by oil prices using economic constraint approaches

This study investigates the predictability of oil return on stock market return using a series of economic constraints. We find that oil return has a more powerful and stable prediction ability than its asymmetric form using an unconstrained approach and three constraint approaches. A new constraint, regarding the three-sigma rule, can obtain a higher forecast accuracy than other methods. Moreover, compared to univariate macro models, incorporation of oil return can increase the average forecasting performance of 14 macroeconomic predictors. Finally, the predictive performance of oil returns varies during different periods linking to the business cycle, geopolitical risk, and financial crisis. The predictability source of oil returns can be explained from the discount rate channel and the sentiment channel.     

Forecasting GDP growth with financial market data in Finland: Revisiting stylized facts in a small open economy during the financial crisis

This paper examines the ability of financial variables to predict future economic growth above and beyond past economic activity in a small open economy in the euro area. We aim to clarify potential differences in forecasting economic activity during different economic circumstances.Our results from Finland suggest that the proper choice of forecasting variables is related to general economic conditions. During steady economic growth, the preferred choice for a financial indicator is the short-term interest rate combined with past values of output growth. However, during economic turbulence, the traditional term spread and stock returns are more important in forecasting GDP growth. The time-varying predictive content of the financial variables may be utilized by applying regime-switching nonlinear forecasting models. We propose a novel application using the negative term spread and observed recession as signals to switch between regimes. This procedure yields a significant improvement in forecasting performance at the one-year forecast horizon.