Forecasting aggregate stock market volatility with industry volatilities: The role of spillover index

In this paper, we aim to improve the predictability of aggregate stock market volatility with industry volatilities. The empirical results show that individual industry volatilities can provide useful predictive information, while the predictive contribution is limited. We further consider the spillover index between industry volatilities and find it displays strong predictive power for stock market volatility. Based on the portfolio exercise, we find that a mean-variance investor can achieve sizeable economic gains by using volatility forecasts of the spillover index. In addition, we conduct three extended analyses and further demonstrate the superior performance of the spillover index. Also, our results show robustness to a series of alternative settings. Finally, we investigate why the spillover index performs better and answer what information it contains. The results show that the spillover index can reflect and explain investor sentiments that are related to stock market volatility.     

Forecasting stock market returns over multiple time horizons

In this paper, we seek to demonstrate the predictability of stock market returns and explain the nature of this return predictability. To this end, we introduce investors with different investment horizons into the news-driven, analytic, agent-based market model developed in Gusev et al. [Algo. Finance, 2015, 4, 5–51]. This heterogeneous framework enables us to capture dynamics at multiple timescales, expanding the model’s applications and improving precision. We study the heterogeneous model theoretically and empirically to highlight essential mechanisms underlying certain market behaviours, such as transitions between bull and bear markets and the self-similar behaviour of price changes. Most importantly, we apply this model to show that the stock market is nearly efficient on intraday timescales, adjusting quickly to incoming news, but becomes inefficient on longer timescales, where news may have a long-lasting nonlinear impact on dynamics, attributable to a feedback mechanism acting over these horizons. Then, using the model, we design algorithmic strategies that utilize news flow, quantified and measured, as the only input to trade on market return forecasts over multiple horizons, from days to months. The backtested results suggest that the return is predictable to the extent that successful trading strategies can be constructed to harness this predictability.     

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.     

Time-varying correlation between oil and stock market volatilities: Evidence from oil-importing and oil-exporting countries

This paper investigates the time-varying conditional correlation between oil price and stock market volatility for six major oil-importing and oil-exporting countries. The period of the study runs from January 2000 until December 2014 and a Diag-BEKK model is employed. Our findings report the following regularities. (i) The correlation between the oil and stock market volatilities changes over time fluctuating at both positive and negative values. (ii). Heterogeneous patterns in the time-varying correlations are evident between the oil-importing and oil-exporting countries. (iii) Correlations are responsive to major economic and geopolitical events, such as the early-2000 recession, the 9/11 terrorist attacks and the global financial crisis of 2007–2009. These findings are important for risk management practices, derivative pricing and portfolio rebalancing.     

Liquidity and valuation in an uncertain world

During the 2007–2009 financial crisis there was little or no trading in a variety of financial assets, even though bid and ask prices existed for many of these assets. We develop a model in which this illiquidity arises from uncertainty, and we argue that this new form of illiquidity makes bid and ask prices unsuitable as metrics for establishing “fair value” for these assets. We show how the extreme uncertainty that traders face can be characterized by incomplete preferences over portfolios, and we use Bewley's (2002) model of decision making under uncertainty to derive equilibrium quotes and the nonexistence of trading at these quotes. We then suggest alternatives for valuing assets in illiquid markets.     

Forecasting stock market volatility and the informational efficiency of the DAX-index options market

Alternative strategies for predicting stock market volatility are examined. In out-of-sample forecasting experiments implied-volatility information, derived from contemporaneously observed option prices or history-based volatility predictors, such as GARCH models, are investigated to determine if they are more appropriate for predicting future return volatility. Employing German DAX-index return data it is found that past returns do not contain useful information beyond the volatility expectations already reflected in option prices. This supports the efficient market hypothesis for the DAX-index options market.     

Forecasting stock-return variance: toward an understanding of stochastic implied volatilities

We examine the behavior of measured variances from the optionsmarket and the underlying stock market. Under the joint hypothesesthat markets are informationally efficient and that option pricesare explained by a particular asset pricing model, forecastsfrom time-series models of the stock return process should nothave predictive content given the market forecast as embodiedin option prices. Both in-sample and out-of-sample tests suggestthat this hypothesis can be rejected. Using simulations, weshow that biases inherent in the procedure we use to imply variancescannot explain this result. Thus, we provide evidence inconsistentwith the orthogonality restrictions of option pricing modelsthat assume that variance risk is unpriced. These results alsohave implications for optimum variance forecast rules.     

The cross-section of stock returns in an early stock market

Using a new dataset which contains monthly data on 1015 stocks traded on the London Stock Exchange between 1825 and 1870, we investigate the cross section of stock returns in this early capital market. Unique features of this market allow us to evaluate the veracity of several popular explanations of asset pricing behavior. Using portfolio analysis and Fama–MacBeth regressions, we find that stock characteristics such as beta, illiquidity, dividend yield, and past-year return performance are all positively correlated with stock returns. However, market capitalization and past-three-year return performance have no significant correlation with stock returns.     

Forecasting asymmetries in aggregate stock market returns: Evidence from conditional skewness

This paper provides a time-series test for the Differences-of-Opinion theory proposed by Hong and Stein (2003) [Hong, H., Stein, J.C., 2003. Differences of opinion, short-sales constraints and market crashes. Review of Financial Studies 16, 487–525.] in the aggregate market, thus extending the cross-sectional test of Chen et al. (2001) [Chen, J., Hong, H., Stein, J.C.. 2001. Forecasting crashes: trading volume, past returns and conditional skewness in stock prices. Journal of Financial Economics 61, 345–381.] for this theory across individual stocks. An autoregressive conditional density model with a skewed-t distribution is used to estimate the effects of past trading volume on return asymmetry. Using NYSE and AMEX data from 1962 to 2000, we find that the prediction of the Hong–Stein model that negative skewness will be most pronounced under high trading volume conditions is not supported in our time-series analysis with market data.     

Momentum in stock returns: evidence from an emerging stock market

This study examines the presence and sources of momentum profits in the Dhaka stock exchange (DSE). Although the short-term reversal and intermediate-term momentum are found to be evident, short-term reversal is not as consistent and significant as intermediate-term momentum. Further examination shows that momentum profits in the DSE cannot be explained by the rational source like market factor but can be explained by the size factor. We argue that presence of large number of small stocks and lack of arbitrage opportunity could be the possible causes of momentum effect in the DSE.     

Location-specific stock market indices: an exploration

This article develops an alternative location-specific stock market index driven by investors’ ‘attachment’ towards investment at a specific location. We evaluate the performance of hypothetical stock market indices that track companies based on their state of registration, taking the US stock market as our case. Using annual data since 1980 we present raw, risk-adjusted and value-weighted state portfolios’ returns to study the extent to which stock market performance varies by state-level demographics and economic factors. A dynamic panel data estimation – with and without spatial spillover effects – is employed to establish a strong association between stock price performance and the state-level (or geography-weighted) factors. We find that spatial effects are strong and that the ‘spatial attachment’ of companies in interaction with the various location-specific variables imparts an overarching influence on stock-price performance. Comparison of model performances further supports our claims.     

Sleeplessness,distraction and stock market performance: Evidence from the world cup

We study how sleeplessness and distraction impact global stock markets using a novel proxy, the FIFA World Cup games. Using this widely viewed sporting event, we exploit the time zone differences between countries to capture the sleeplessness from staying awake overnight and the distraction from watching matches during trading hours. We find the markets experience a − 26 basis-point daily return for a day of sleeplessness and a − 22 basis-point return due to distraction. These effects are robust to methodological changes.     

Unchecked intermediaries: Price manipulation in an emerging stock market

How costly is the poor governance of market intermediaries? Using unique trade level data from the stock market in Pakistan, we find that when brokers trade on their own behalf, they earn annual rates of return that are 50-90 percentage points higher than those earned by outside investors. Neither market timing nor liquidity provision by brokers can explain this profitability differential. Instead we find compelling evidence for a specific trade-based “pump and dump” price manipulation scheme: When prices are low, colluding brokers trade amongst themselves to artificially raise prices and attract positive-feedback traders. Once prices have risen, the former exit leaving the latter to suffer the ensuing price fall. Conservative estimates suggest these manipulation rents can account for almost a half of total broker earnings. These large rents may explain why market reforms are hard to implement and emerging equity markets often remain marginal with few outsiders investing and little capital raised.     

Irrational investor response to stock splits in an emerging market

Using the creation and collapse of the Cyprus stock market bubble as a backdrop, we document substantial positive abnormal returns around the announcement and execution of stock splits in Cyprus. Split-induced returns cannot be explained by variables proxying for conventional liquidity and signalling hypotheses for stock-split activity. Positive split-induced returns are largely reversed in the post-split months. Post-split stock underperformance is inversely related to, and thus appears to be a correction for, the significant market overreaction at split execution. We suggest an investor irrationality explanation for these results, arguing that stock splits were associated with the creation of the bubble due to the inability of investors to understand splits correctly. We conclude that educating investors in emerging markets to process information correctly will improve the efficiency of such markets.     

Multiday expected shortfall under generalized t distributions: evidence from global stock market

Review of Quantitative Finance and Accounting - Earnings management research often uses discretionary accruals from Jones-type models. These models assume a linear relation between sales changes...     

Country world betas: The link between the stock market beta and macroeconomic beta

We assess the connection between stock market linkages and macroeconomic linkages by using a world index model. Specifically, we test the association between the stock market beta (the sensitivity of country stock market index to world index) and macroeconomic betas (the sensitivity of national output and inflation to world output and inflation). Output betas account for about 20–26% of the cross-section of stock market betas. Controlling for previously-documented factors affecting stock market comovements: world output volatility is somewhat significant, while inflation betas, trade openness and world stock market volatility are insignificant in accounting for variation in stock market betas.     

Spreading the fear: The central role of CBOE VIX in global stock market uncertainty

Construction of efficient portfolios is reliant on understanding the correlation between assets. If correlations change markedly during times of economic turmoil then investors are exposed to greater risk at the most inopportune time. We examine the linkages between global stock markets using measures of market uncertainty (implied volatility). Using a sample of daily changes in G7 and BRIC implied volatility measures, over a 20-year sample period, we demonstrate that uncertainty in U.S. markets plays a pivotal role in global stock market uncertainty. “Fear is spread” across markets, as heightened uncertainty in U.S. markets is transmitted across global markets. Conversely, changes in global market uncertainty do not explain changes in U.S. market uncertainty. While there is a clear increase in connectedness during crisis periods, we observe a disparity in the way that inter-dependencies change during the two major economic crises in our sample period; the GFC (2007–2009) and COVID-pandemic (2020). The additional importance of US news largely drives our results during the GFC, while the effect is spread among several countries (particularly within European markets) during COVID.     

Forecasting market states

We propose a novel methodology to define, analyze and forecast market states. In our approach, market states are identified by a reference sparse precision matrix and a vector of expectation values. In our procedure, each multivariate observation is associated to a given market state accordingly to a minimization of a penalized Mahalanobis distance. The procedure is made computationally very efficient and can be used with a large number of assets. We demonstrate that this procedure is successful at clustering different states of the markets in an unsupervised manner. In particular, we describe an experiment with one hundred log-returns and two states in which the methodology automatically associates states prevalently to pre- and post-crisis periods with one state gathering periods with average positive returns and the other state periods with average negative returns, therefore discovering spontaneously the common classification of ‘bull’ and ‘bear’ markets. In another experiment, with again one hundred log-returns and two states, we demonstrate that this procedure can be efficiently used to forecast off-sample future market states with significant prediction accuracy. This methodology opens the way to a range of applications in risk management and trading strategies in the context where the correlation structure plays a central role.     

Financial services in an increasingly integrated global financial market

This paper discusses aspects of global financial services. As part of financial globalisation, financial institutions have evolved both nationally and internationally. FDI is becoming an important vehicle for multinational banks to enter developing countries. This in turn is changing the composition of trade in financial services. The experience of regional integration in Europe and the emergence of large multinational European banks signal a new era of global competition and consolidation of financial institutions. Home bias in international financial services is much less where financial integration is taking place. With financial globalisation, one should expect more diversification of ownership of multinational banks around the world, particularly when China and India are now able to have strategic investment in some of the key investment banks around the world. Financial globalisation requires stronger and more effective international institutions as a way of monitoring the activities of multinational financial institutions at both the national and international levels.