A non-linear approach for predicting stock returns and volatility with the use of investor sentiment indices

The popular sentiment-based investor index S^BW introduced by Baker and Wurgler (2006, 2007) is shown to have no predictive ability for stock returns. However, Huang et al. (2015) developed a new investor sentiment index, S^PLS, which can predict monthly stock returns based on a linear framework. However, the linear model may lead to misspecification and lack of robustness. We provide statistical evidence that the relationship between stock returns, S^BW and S^PLS is characterized by structural instability and inherent nonlinearity. Given this, using a nonparametric causality approach, we show that neither S^BW nor S^PLS predicts stock market returns or even its volatility, as opposed to previous empirical evidence.     

The role of news-based uncertainty indices in predicting oil markets: a hybrid nonparametric quantile causality method

A recent strand in the literature emphasizes the role of news-based economic policy uncertainty (EPU) and equity market uncertainty (EMU) as drivers of oil price movements. Against this backdrop, this paper uses a kth-order nonparametric quantile causality test, to analyse whether EPU and EMU predict stock returns and volatility. Based on daily data covering the period of 2 January 1986 to 8 December 2014, we find that, for oil returns, EPU and EMU have strong predictive power over the entire distribution barring regions around the median, but for volatility, the predictability virtually covers the entire distribution, with some exceptions in the tails. In other words, predictability based on measures of uncertainty is asymmetric over the distribution of oil returns and its volatility.     

SECULAR MEAN REVERSION AND LONG‐RUN PREDICTABILITY OF THE STOCK MARKET

The empirical financial literature reports evidence of mean reversion in stock prices and the absence of out‐of‐sample return predictability over horizons shorter than 10 years. Anecdotal evidence suggests the presence of mean reversion in stock prices and return predictability over horizons longer than 10 years, but thus far, there is no empirical evidence confirming such anecdotal evidence. The goal of this paper is to fill this gap in the literature. Specifically, using 141 years of data, this paper begins by performing formal tests of the random walk hypothesis in the prices of the real S&P Composite Index over increasing time horizons of up to 40 years. Although our results cannot support the conventional wisdom that the stock market is safer for long‐term investors, our findings speak in favor of the mean reversion hypothesis. In particular, we find statistically significant in‐sample evidence that past 15‐17 year returns are able to predict the future 15‐17 year returns. This finding is robust to the choice of data source, deflator, and test statistic. The paper continues by investigating the out‐of‐sample performance of long‐horizon return forecasting based on the mean‐reverting model. These latter tests demonstrate that the forecast accuracy provided by the mean‐reverting model is statistically significantly better than the forecast accuracy provided by the naive historical‐mean model. Moreover, we show that the predictive ability of the mean‐reverting model is economically significant and translates into substantial performance gains.     

Does international oil volatility have directional predictability for stock returns? Evidence from BRICS countries based on cross-quantilogram analysis

While numerous studies have investigated the relationship between oil volatility and stock returns, it is surprising that little research has examined the quantile dependence and directional predictability from oil volatility to stock returns in BRICS (Brazil, Russia, India, China, and South Africa) countries. We address this issue by using the cross-quantilogram model proposed by Han et al. (2016). The empirical results show that, overall, oil volatility has a directional predictability for the stock returns in BRICS countries. When the oil volatility is in a low quantile (lower than its 0.1 quantiles), it is less likely to show either a large loss or a large gain in the stock market. In contrast, there is an increased likelihood of either large loss or a large gain in the stock market when the oil volatility is in a high quantile (higher than its 0.9 quantiles). The directional predictability from the oil volatility to stock returns depends on the net position of oil imports and exports of these BRICS countries in the oil market. The net oil exporters (Russia and Brazil) are less likely to have large gains and large losses in the stock market than are the net oil importers (India, China, and South Africa) when the oil volatility is in a low quantile. The net oil exporters are more likely to have large gains and large losses than are the net oil importers when the oil volatility is in a high quantile. The results are robust to change in the variable of oil volatility and the sample interval.     

Economic policy uncertainty,financial markets and probability of US recessions

We use probit recession forecasting models to assess the ability of economic policy uncertainty indexes developed by Baker et al. (2013) to predict future US recessions. The model specifications include policy indexes on their own, and in combination with financial variables, such as interest rate spreads, stock returns and stock market volatility. Both in-sample and out-of-sample analysis suggests that the policy uncertainty indexes are statistically and economically significant in forecasting recessions at the horizons beyond five quarters. The index based on newspaper reports emerges as the best predictor, outperforming the term spread at the longer forecast horizons.     

A new investor sentiment indicator (ISI) based on artificial intelligence: A powerful return predictor in China

This paper utilizes deep learning approach widely documented in artificial intelligence, and proposes an investor-sentiment indicator (ISI) that is consistent with the purpose of forecasting stock market returns. We find that ISI is positively correlated with future stock market returns at a monthly frequency, but negatively associated with subsequent returns over a longer horizon. Moreover, ISI outperforms other well-recognized predictors both in and out of sample, and can predict cross-sectional stock returns sorted by industry. We also show a positive association between monthly ISI and dividend growth rate, which indicates that investors’ expectations about future cash flows may contribute to the return predictability of ISI.     

A FURTHER EXAMINATION OF THE PRICE AND VOLATILITY IMPACT OF STOCK DIVIDENDS AT EX‐DATES*

We examine the price and volatility reaction around stock dividend ex‐dates for an Australian sample, over the period January 1992 to December 2000. We find that price reaction around stock dividend ex‐dates provides positive abnormal returns both prior, and subsequent, to the abolishment of par value of shares in July 1998. When we partitioned the sample into financial, industrial non‐financial and mining firms, the price reaction is found to be positive and significant only for industrial non‐financial companies. Volatility of daily returns for periods subsequent to ex‐dates is significantly greater than corresponding periods prior to announcement dates, while cumulative raw returns subsequent to ex‐dates are significantly lower than periods prior to announcement dates for industrial non‐financial companies. The magnitude of the price reaction is statistically significantly related to an increase in the volatility of daily returns and to a reduction in cumulative raw returns subsequent to the ex‐dates, for industrial non‐financial companies. These findings support buying pressure hypothesis suggested by Dhatt et al. (1994, 1996 ).     

Returns of Small Growth Stocks: An Empirical Analysis

I investigate the mean reversion tendency of small growth stocks. Using a carefully articulated research design employing established and empirically tested principles, my findings should support or refute the anecdotal evidence that small growth stocks make superior investments. The primary motivation for the study springs from the documented differential preference among investors for value and growth stocks. Despite evidence that value stocks tend to outperform growth stocks, investors retain strong interest in growth stocks. Yet in examining the performance of Business Week’s (BW), smaller capitalization companies (called “Hot Growth Companies”) with respect to the overall financial market, Bauman et al. [2002] found positive excess returns in the pre-publication period but negative excess returns in the post-publication period. A limitation of their study is that their analyses relied on only three criteria: sales, BW rank and return on capital, which do not represent completely a firm’s financial health. I replicate Bauman et al.’s study but use a more robust and representative variable set to test the mean reversal hypothesis — Forbes’ financial criteria — and I focus on six variables. In the current study, I look at 4,200 companies listed in Forbes from 1980 to 2000. The results of the expanded study substantiate Bauman et al.’s [2002] study showing that there are positive excess returns in the pre-publication period, but negative excess returns in the post-publication period. An expanded future study will look at five additional variables to see if they make a significant difference on the effects of the returns of small growth stocks.     

The Efficiency of the Realized Range Measure of Daily Volatility: Evidence from Greece

In this study we estimate and compare the realized range volatility, a novel efficient volatility estimator computed by summing high–low ranges for intra‐day intervals, to the recently popularized realized variance estimator obtained by summing squared intra‐day returns. Our results, derived from a Greek equity high‐frequency data set, show that realized range‐based measures improve upon the corresponding realized variance‐based ones in most cases, especially for the most actively traded stocks. The usefulness of high‐frequency data in measuring and forecasting financial volatility is apparent throughout the paper.     

South African stock return predictability in the context data mining: The role of financial variables and international stock returns

In this paper, we examine the predictive ability, both in-sample and the out-of-sample, for South African stock returns using a number of financial variables, based on monthly data with an in-sample period covering 1990:01 to 1996:12 and the out-of-sample period of 1997:01 to 2010:04. We use the t-statistic corresponding to the slope coefficient in a predictive regression model for in-sample predictions, while for the out-of-sample, the MSE-F and the ENC-NEW tests statistics with good power properties were utilised. To guard against data mining, a bootstrap procedure was employed for calculating the critical values of both the in-sample and out-of-sample test statistics. Furthermore, we use a procedure that combines in-sample general-to-specific model selection with out-of-sample tests of predictive ability to further analyse the predictive power of each financial variable. Our results show that, for the in-sample test statistic, only the stock returns for our major trading partners have predictive power at certain short and long run horizons. For the out-of-sample tests, the Treasury bill rate and the term spread together with the stock returns for our major trading partners show predictive power both at short and long run horizons. When accounting for data mining, the maximal out-of-sample test statistics become insignificant from 6-months onward suggesting that the evidence of the out-of-sample predictability at longer horizons is due to data mining. The general-to-specific model shows that valuation ratios contain very useful information that explains the behaviour of stock returns, despite their inability to predict stock return at any horizon. The model also highlights the role of multiple variables in predicting stock returns at medium- to long run horizons.     

Value at risk estimation by threshold stochastic volatility model

This article proposes a threshold stochastic volatility model that generates volatility forecasts specifically designed for value at risk (VaR) estimation. The method incorporates extreme downside shocks by modelling left-tail returns separately from other returns. Left-tail returns are generated with a t-distributional process based on the historically observed conditional excess kurtosis. This specification allows VaR estimates to be generated with extreme downside impacts, yet remains empirically widely applicable. This article applies the model to daily returns of seven major stock indices over a 22-year period and compares its forecasts to those of several other forecasting methods. Based on back-testing outcomes and likelihood ratio tests, the new model provides reliable estimates and outperforms others.     

QUANTILE FORECASTS OF FINANCIAL RETURNS USING REALIZED GARCH MODELS*

This article applies the realized generalized autoregressive conditional heteroskedasticity (GARCH) model, which incorporates the GARCH model with realized volatility, to quantile forecasts of financial returns, such as Value‐at‐Risk and expected shortfall. Student's t‐ and skewed Student's t‐distributions as well as normal distribution are used for the return distribution. The main results for the S&P 500 stock index are: (i) the realized GARCH model with the skewed Student's t‐distribution performs better than that with the normal and Student's t‐distributions and the exponential GARCH model using the daily returns only; and (ii) using the realized kernel to take account of microstructure noise does not improve the performance.     

Does measurement error matter in volatility forecasting? Empirical evidence from the Chinese stock market

Based on methods developed by Bollerslev et al. (2016), we explicitly accounted for the heteroskedasticity in the measurement errors and for the high volatility of Chinese stock prices; we proposed a new model, the LogHARQ model, as a way to appropriately forecast the realized volatility of the Chinese stock market. Out-of-sample findings suggest that the LogHARQ model performs better than existing logarithmic and linear forecast models, particularly when the realized quarticity is large. The better performance is also confirmed by the utility based economic value test through volatility timing.     

An Improved Two‐step Regularization Scheme for Spot Volatility Estimation

We are concerned with the problem of spot volatility estimation in the presence of microstructure noise. We introduce an estimator based on the technique of multi‐step regularization. A preliminary form for such an estimator was proposed in Ogawa (2008) and was shown to work in a real‐time manner. However, the main drawback of this scheme is that it needs a lot of observation data. The aim of the present paper is to introduce an improvement to this scheme, such that the modified estimator can work more efficiently and with a data set of smaller size. The technical aspects of implementation of the proposed scheme and its performance on simulated data are analysed. The scheme is tested against other spot volatility estimators, namely a realized volatility type estimator, the Fourier estimator and three kernel estimators.     

DYNAMIC CORRELATION BETWEEN STOCK RETURNS AND EXCHANGE RATE AND ITS DEPENDENCE ON THE CONDITIONAL VOLATILITIES – THE CASE OF SEVERAL EASTERN EUROPEAN COUNTRIES

The objective of the paper is to determine whether the linkage between stock returns and exchange rates in several Eastern European countries was in accordance with the flow oriented model or the portfolio‐balance approach. The dynamic interdependence between exchange rate and stock returns is determined using the Dynamic Conditional Correlation (DCC) framework. The results pointed to a negative dynamic correlation which is in line with portfolio‐balance approach. Rolling regression revealed that conditional correlation was affected primarily by conditional volatility of currency, while the impact of stock returns volatility was negligible.     

Can volume predict Bitcoin returns and volatility? A quantiles-based approach

Prior studies on the price formation in the Bitcoin market consider the role of Bitcoin transactions at the conditional mean of the returns distribution. This study employs in contrast a non-parametric causality-in-quantiles test to analyse the causal relation between trading volume and Bitcoin returns and volatility, over the whole of their respective conditional distributions. The nonparametric characteristics of our test control for misspecification due to nonlinearity and structural breaks, two features of our data that cover 19th December 2011 to 25th April 2016. The causality-in-quantiles test reveals that volume can predict returns – except in Bitcoin bear and bull market regimes. This result highlights the importance of modelling nonlinearity and accounting for the tail behaviour when analysing causal relationships between Bitcoin returns and trading volume. We show, however, that volume cannot help predict the volatility of Bitcoin returns at any point of the conditional distribution.     

A COMPARISON OF CONDITIONAL AND UNCONDITIONAL APPROACHES IN VALUE‐AT‐RISK ESTIMATION*

In this paper, we attempt to find the most important factor causing the differences in the performance of Value‐at‐Risk (VaR) estimation by comparing the performances of conditional and unconditional approaches. For each approach, we use various methods and models with different degrees of flexibility in their distributions including S_U‐normal distribution, which is one of the most flexible distribution functions. Our empirical results underscore the importance of the flexibility‐of‐distribution function in VaR estimation models. Even though it seems to be unclear which approach is better between conditional and unconditional approaches, it seems to be clear that the more flexible distribution we use, the better the performance, regardless of which approach we use.     

The dependence structure between the Canadian stock market and the USD/CAD exchange rate: a copula approach

Abstract This paper investigates the dependence structure between the real Canadian stock returns and the real USD/CAD exchange rate returns, using the Symmetrized Joe‐Clayton (SJC) copula function. We estimate the SJC copula with monthly data over the period 1995:1 to 2006:12. Our results show significant asymmetric static and dynamic tail dependence between the real stock returns and the real exchange rate returns, such that the two returns are more dependent in the left than in the right tail of their joint distribution. We explain this asymmetric dependence in terms of an asymmetric interest rate policy by Canadian monetary authorities in response to changes in the real exchange rate during sub‐periods of falling and rising commodity prices.     

Improving the predictability of the oil–US stock nexus: The role of macroeconomic variables

In this study, we revisit the oil–stock nexus by accounting for the role of macroeconomic variables and testing their in-sample and out-of-sample predictive powers. We follow the approaches of Lewellen (2004) and Westerlund and Narayan (2015), which were formulated into a linear multi-predictive form by Makin et al. (2014) and Salisu et al. (2018) and a nonlinear multi-predictive model by Salisu and Isah (2018). Thereafter, we extend the multi-predictive model to account for structural breaks and asymmetries. Our analyses are conducted on aggregate and sectoral stock price indexes for the US stock market. Our proposed predictive model, which accounts for macroeconomic variables, outperforms the oil-based single-factor variant as well as the constant returns (historical average) model for both in-sample and out-of-sample forecasts. We find that it is important to account for structural breaks in our proposed predictive model, although asymmetries do not seem to improve predictability. In addition, we show that it is important to pre-test the predictors for persistence, endogeneity, and conditional heteroscedasticity, particularly when modeling with high-frequency series. Our results are robust to different forecast measures and forecast horizons and are useful for making effective hedging decisions in the US stock market.     

Daily happiness and stock returns: The case of Chinese company listed in the United States

Existing literature exclusively focuses on the association between local investor sentiment and local stock market performance. In this paper, we investigate the contemporaneous and the lead-lag relationship between local daily happiness sentiment extracted from Twitter and stock returns of cross-listed companies, i.e., the Chinese companies listed in the United States. The empirical results show that: 1) by respectively controlling for the firm capitalization, liquidity and volatility, there exists the largest skewness on the Most-happiness subgroup. (2) There exist bi-directional relationships between daily happiness sentiment and market variables, i.e., the stock return, range-based volatility and excess trading volume. (3) There are significantly positive stock returns, higher excess trading volume and higher range-based volatility around the daily happiness sentiment spike days. These findings not only suggest that there exists significant interdependence between online activities and stock market dynamics, but also provide evidence for the existence of “home bias”.