Daily Stock Returns Research Articles

Analysis of efficient market anomaly on stock returns on Indonesia's composite stock price index and global stock price index

Market anomaly is an occurring phenomenon in the market. Supposedly, an anomaly does not exist in markets that are considered efficient. An anomaly is an aberration in the efficient market theory where existing information does not reflect stock prices; therefore, investors can earn abnormal returns. This study examines how The Day Of The Week Effect and The Month Of The Year Effect affect stock returns on the Indonesian Stock Price Index and the Global Stock Price Index. Samples in this study are daily stock return data and return data on stocks of IHSG, DJIA, SSEC, and N225. The Generalized Autoregressive Conditional Heteroscedasticity (GARCH) model is used to analyze data. The results show that in IHSG and SSEC, there was no The Day Of The Week Effect. The DJIA and N225 were found in The Day of the Week Effect. The Month of the Year Effect was found in IHSG, DJIA, SSEC, and N225.

Commodity price volatility and stock market returns in an emerging economy

AbstractThe paper examined commodity price volatility and stock returns on the Ghana Stock Exchange (GSE). Utilising Threshold Generalised Autoregressive Conditional Heteroskedasticity (TGARCH) estimation technique, the study also evaluated the likely leverage effect on the stock market and further interrogated if autocorrelation existed in the daily stock returns series, for how many days and on what day does it disappear by specifying an autoregressive model as a mean equation. The study concludes that changes in commodity prices and their volatilities on the international market exert a significant level of diverse impact on daily stock returns and return volatility on the GSE. For instance, whilst coffee price changes result in reduction in daily stock returns, changes in crude and gold prices result in an increment in returns on the GSE. The study also confirms the existence of autocorrelation in the daily stock returns for up to seven days, fading out on the eighth day as well as the existence of the leverage effect on the GSE. This result should influence investment decisions in respect to trading on the GSE. Observance of changes in price of these key commodities could enhance predictions and lead to the formulation of strategies to maximise revenues on the GSE

Top management team gender diversity and firm risk-taking in the hospitality industry

PurposeThe purpose of this study is to investigate the link between top management team (TMT) gender diversity and firm risk-taking in hospitality companies. The study also links female leadership to risk-taking. Finally, this study examines the moderating effects of TMT incentive pay and TMT age on the relationship between TMT gender diversity and firm risk-taking.Design/methodology/approachThis study uses an unbalanced data set of 81 hospitality firms and 888 firm-year observations over the period of 1992–2020. The study uses fixed-effects regression estimation for primary analyses and addresses potential endogeneity concerns via two-stage least square regression with firm fixed-effects instrumental variable regression. Risk-taking is measured by total firm risk (i.e. the annualized volatility of daily stock returns). Main results are supported with alternative measures of firm risk and estimation methods.FindingsThe study finds that increasing TMT gender diversity leads to a reduction in firm risk-taking in the hospitality industry. Moreover, the study finds that hospitality firms led by a female CEO experience lower firm risk compared to firms led by a male CEO. Finally, the study finds evidence that the relationship between TMT gender diversity and firm risk is contingent on the level of incentive pay awarded to TMT members and the age of TMT members. Increasing incentive pay and aging executive teams decrease the risk reduction effect of TMT gender diversity.Practical implicationsThe findings of this study recommend that firm risk-taking in the hospitality industry is related to gender diversity in TMTs. Hence, the board of directors should pay attention to gender composition for executive positions for risk management. Moreover, the results also suggest that care should be exercised when using incentive pay to align the interests of managers and shareholders. Finally, the board of directors needs to consider both gender diversity and age of the TMT members for TMT composition to manage executives’ risk-taking behavior.Originality/valueThis study fills a research gap in the hospitality literature by providing empirical evidence for the link between TMT gender diversity and firm risk-taking. Additionally, the study introduces incentive pay and age of TMT as contingency factors for the link between TMT gender diversity and firm risk-taking.

Predicting the Global Minimum Variance Portfolio

We propose a novel dynamic approach to forecast the weights of the global minimum variance portfolio (GMVP) for the conditional covariance matrix of asset returns. The GMVP weights are the population coefficients of a linear regression of a benchmark return on a vector of return differences. This representation enables us to derive a consistent loss function from which we can infer the GMVP weights without imposing any distributional assumptions on the returns. In order to capture time variation in the returns’ conditional covariance structure, we model the portfolio weights through a recursive least squares (RLS) scheme as well as by generalized autoregressive score (GAS) type dynamics. Sparse parameterizations and targeting toward the weights of the equally weighted portfolio ensure scalability with respect to the number of assets. We apply these models to daily stock returns, and find that they perform well compared to existing static and dynamic approaches in terms of both the expected loss and unconditional portfolio variance.

Bootstrap Tests for High-Dimensional White-Noise

The testing of white-noise (WN) is an essential step in time series analysis. In a high dimensional set-up, most existing methods either are computationally infeasible, or suffer from highly distorted Type-I errors, or both. We propose an easy-to-implement bootstrap method for high-dimensional WN test and prove its consistency for a variety of test statistics. Its power properties as well as extensions to WN tests based on fitted residuals are also considered. Simulation results show that compared to the existing methods, the new approach possesses much better power, while maintaining a proper control over the Type-I error. They also provide proofs that even in cases where our method is expected to suffer from lack of theoretical justification, it continues to outperform its competitors. The proposed method is applied to the analysis of the daily stock returns of the top 50 companies by market capitalization listed on the NYSE, and we find strong evidence that the common market factor is the main cause of cross-correlation between stocks.

Efekat dana u nedelji na južnoafričkom tržištu akcija - a garch analysis

Understanding dynamics of daily stock returns provide insight in trading opportunities available in stock markets. The purpose of the study was to examine whether day of the week effect exists in the South African equity market. Daily data from Top 40, All Shares, Basic Materials, Industrials, Consumer Goods, Health Care, Consumer Services, Telecommunications, Financials and Technology indices were collected for period 1995 to 2018. Exponential and threshold generalized auto regressive conditional heteroskedasticity models were employed to analyse day of the week anomaly. Findings of the day of the week for the mean equation revealed a positive Monday effect for aggregate indices namely Top 40 and All shares whilst the sectorial analysis showed a positive Monday effect for Basic materials, Consumer goods, Health care and Telecommunication. Furthermore, the mean equation for day of the week depicted a positive Tuesday effect for Financials sector, positive Wednesday effect for Consumer services sector and Thursday effect for Industrials and Technology sectors. The variance equation highlighted negative Monday effect for Top 40 and All shares as well as Basic materials, Consumer goods, Health care, Consumer services, Telecommunication and Financials sectors. However, Industrials sector indicated a negative Friday effect. The existence of day of the week effect nullifies the efficient market hypothesis in its weak form. In practice, it is recommended that for Mondays investors should invest in Top 40 and All shares, for Tuesday and Wednesday it would be prudent for investors to invest in Financial and Consumer services sectors respectively. Returns for Thursdays are attractive to an investor investing in the Industrial sector. An investor can reduce exposure by diversifying in the Health sector on Monday and in the by Industrial sector on Friday. Unlike previous studies that focussed on aggregate market indices, this study extended the analysis to sectors that constitute the market index.

Volatility Estimation When the Zero-Process is Nonstationary

Financial returns are frequently nonstationary due to the nonstationary distribution of zeros. In daily stock returns, for example, the nonstationarity can be due to an upwards trend in liquidity over time, which may lead to a downwards trend in the zero-probability. In intraday returns, the zero-probability may be periodic: It is lower in periods where the opening hours of the main financial centers overlap, and higher otherwise. A nonstationary zero-process invalidates standard estimators of volatility models, since they rely on the assumption that returns are strictly stationary. We propose a GARCH model that accommodates a nonstationary zero-process, derive a zero-adjusted QMLE for the parameters of the model, and prove its consistency and asymptotic normality under mild assumptions. The volatility specification in our model can contain higher order ARCH and GARCH terms, and past zero-indicators as covariates. Simulations verify the asymptotic properties in finite samples, and show that the standard estimator is biased. An empirical study of daily and intradaily returns illustrate our results. They show how a nonstationary zero-process induces time-varying parameters in the conditional variance representation, and that the distribution of zero returns can have a strong impact on volatility predictions.

Does inter-region portfolio diversification pay more than the international diversification?

Recent literature supports the view that returns of most of the international equity markets are significantly integrated. However, diversification based across different regions remains a focus of attention for the investment community. We examine the presence of returns integration among BRICS, Latin American, and emerging and frontier Asian equity markets by utilizing panel co-integration and panel regression, i.e., fully modified ordinary least square (FMOLS), to examine portfolio diversification opportunities. Our sampling of data comprises of daily stock return from 1st September 1997 to 30th November 2018. Our findings highlight that within the region, portfolio diversification does not provide optimal returns. Furthermore, empirical results from the vector error correction model (VECM) suggest the benefits of portfolio diversification in the short-run. In particular, not all equity markets are significantly linked with gold, oil, and forex markets. Our empirical analysis reveals that within the region, equity-commodity portfolios may lead to greater diversification gains.

Pandemic and Indonesia Stock Market Performance

This study aims to analyze the impact of the COVID-19 pandemic on Indonesia’s stock market performance. Considering the characteristics of daily stock return data that shows the characteristics of volatility clustering, the analytical method used is to develop a heteroscedastic model specification whose parameters are estimated using the maximum likelihood method. Based on data from March 2020 to January 2021, this study finds that the Exponential-GARCH asymmetric model is the best model compared to the Standard-GARCH symmetric model or the asymmetric Threshold-GARCH model. The inference analysis conducted on the Exponential-GARCH asymmetric model in this study shows that the stock market's performance that is significantly affected by this pandemic is the volatility of its returns. Stock price volatility is one of the important variables in stock market performance. This study produces empirical findings that government policies on social restrictions contribute significantly to suppressing stock market volatility. As for government policies in mitigating the risk of the spread of the epidemic, in this study, it is measured through a stringency index. This index was released by the Oxford COVID-19 Government Response Tracker (OxCGRT) which monitors the government's response to the coronavirus in 160 countries and is a parameter that evaluates the policies taken by a country's government based on nine metrics. This index does not measure the effectiveness of a country's government response, but only the level of tightness. However, the results of the tests carried out in this study did not find a significant impact of pandemic indicators, the number of cases, and the number of daily deaths related to COVID-19 on stock returns.

A Comparative Study on the Efficiency of Korean Stock Markets: KOSPI and KOSDAQ

Purpose - This study aims to examine and compare the weak-form efficiency of the KOSPI and KOSDAQ markets in Korea based upon the random walk process framework. Design/Methodology/Approach - This study uses multiple variance ratio tests with the purpose of testing the random walk process for daily returns of stocks to investigate the efficiency of stock markets in Korea. Chow-Denning and Richardson-Smith multiple variance ratio tests have been employed in order to find out the level of the efficiency of Korea’s stock markets. Findings - First, the daily return of both market indexes did not follow the random walk process for the sampling period, indicating that the Korean stock market indexes are not weak-form efficient. Second, all the individual stocks used for the analysis are shown to be inefficient in the weak form. Only three sample stocks in KOSPI market out of ten stocks accept the null hypothesis under the heteroscedasticity assumption, but the null hypothesis in these stocks is rejected under the homoscedasticity assumption. Research Implications - This study suggests that under the random walk hypothesis framework, the market index and individual stocks in Korean stock market show the informational inefficiency in a weak form. Accordingly, it seems that domestic and foreign investors may still be able to get the yield better than market average, or market index, in the Korea’s stock markets including KOSDAQ market by doing fundamental and technical analysis on the stock markets.

The Eurozone banking sector in the time of COVID-19: Measuring volatility connectedness

This article investigates the volatility connectedness of the Eurozone banking system over the last 15 years (from 2005 to 2020). Applying the Diebold-Yilmaz Connectedness Index model to the daily stock return volatilities of 30 major Eurozone banks, we are able to measure the risk spillover effects and to capture the COVID-19 outbreak's impact on banking stability. The empirical findings show that the 30 banks are highly interconnected. Furthermore, we show the strong impact of the COVID-19 pandemic on the volatility dynamics, i.e., on the structure of the Eurozone banking system. Dynamically, we find that volatility connectedness increases during crises, reaching its maximum peak at the time of COVID-19. The analysis points out the critical role of volatility transmission played by large banks, highlighting the “too-big-to-fail” characteristic of this banking system. However, we find that small-medium banks are important actors of contagion, supporting the thesis that the Eurozone banking system is also “too-interconnected to fail.” Finally, we document the heterogeneity effect of the COVID-19 pandemic between Eurozone banking systems. This heterogeneity impact could be a future source of financial instability within the Eurozone.

Empirical distribution of daily stock returns of selected developing and emerging markets with application to financial risk management

Empirical distribution of daily stock returns of selected developing and emerging markets with application to financial risk management

An Analysis of the Stock Market Volatility Spread in Emerging Countries

This article provides results on the volatility spread for stock markets in emerging economies. Empirical studies on determining or predicting volatility in national and international financial markets provide information for investors. The aim of this study is also to analyze volatility spreads from the United States of America, France, Germany, Japan Turkey, China, India, Indonesia from emerging markets within the scope of EGARCH models, which take into account the asymmetric effects using daily stock returns for the period of January 2008 - April 2020. The a symmetric effect parameter (λ or µt-i/ht-1) appears to be negative and statistically significant at 1% for all countries, except the Shanghai Composite Stock Exchange, China. This result shows that the asymmetric effect, or the leverage effect in other words, is valid in stock markets other than China. The volatility spreads from the Dow Jones Industrial Average Index – USA to Borsa Istanbul and the Shanghai Stock Exchange – China. Also, the S & P 500 Index – USA is significant on the volatility spread of the Borsa Istanbul and Shanghai Stock Exchange. The volatility spread between Jakarta Stock Exchange - Indonesia and Borsa Istanbul is two-way and mutual. 

The long-term effects of section transfers on return volatility: Intraday and overnight periods

PurposeStudies on transfers to a more regulated section show an increase in information disclosure and stocks’ liquidity levels. Classical theories suggest that volatility should also be reduced. This study aims to analyse the long-term effects of a section transfer to a more regulated section (TSE 1/TSE 2) on stock return volatility.Design/methodology/approachThis study uses an empirical framework relying on two-sample t-tests and panel regressions. These use robust standard errors and control for fixed effects, day effects and macroeconomic factors. The return variance of comparable stocks’ benchmark sample, instead of market variance, is used as a control variable. Comparable stocks operate within the same industry and do not transfer during the sample period. The authors test our results’ robustness using generalized autoregressive conditional heteroskedasticity estimates.FindingsThe study’s main findings show that pre-transferred stocks are more volatile than the stocks’ benchmark sample. The transfer to a more regulated section leads to a gradual decrease in the total daily stock return volatility, intraday return volatility and overnight return volatility.Originality/valueTo the best of my knowledge, this study is the first to empirically address the volatility change caused by the stocks’ transfer to a more regulated section. This study highlights the benefits of choosing section transfers to reduce volatility.

Herding in the bad times: The 2008 and COVID-19 crises

The objective of this paper is to analyze the imitation behavior of investors in especially convulsed periods, such as the 2008 financial crisis and the recent global pandemic, both of which could affect investors' emotions and behavior, although both have different characteristics and might have different implications. The cross-sectional dispersion of returns is used to measure the level of herding in the markets of Spain and Portugal, using a survivorship-bias-free dataset of daily stock returns during the period January 2000–May 2021, in turn divided into several sub-periods classified as pre-2008 crisis, 2008 crisis, post-2008 crisis, Covid-19 and post Covid-19. Additionally, the existence is studied of differences between days of positive and negative returns, or between days of high volatility compared to the rest, and whether the cross-sectional dispersion of returns in one market is affected by the cross-sectional dispersion of returns in the other market. The results indicate that herding appears with greater intensity in periods prior to the crisis, disappearing during the financial crisis and reappearing, although with less intensity, after it, while it is not generally detected in Covid-19 times. However, herding behavior can be observed in the market during the pandemic on high volatility days.

Is it possible to forecast KOSPI direction using deep learning methods?

Deep learning methods have been developed, used in various fields, and they have shown outstanding performances in many cases. Many studies predicted a daily stock return, a classic example of time-series data, using deep learning methods. We also tried to apply deep learning methods to Korea’s stock market data. We used Korea’s stock market index (KOSPI) and several individual stocks to forecast daily returns and directions. We compared several deep learning models with other machine learning methods, including random forest and XGBoost. In regression, long short term memory (LSTM) and gated recurrent unit (GRU) models are better than other prediction models. For the classification applications, there is no clear winner. However, even the best deep learning models cannot predict significantly better than the simple base model. We believe that it is challenging to predict daily stock return data even if we use the latest deep learning methods.

The Impact of COVID-19 Lockdown in Banks and Financial Institutions' Stock Performance: Evidence from Nepal

This paper examines the impact of COVID-19 lockdown on daily stock returns of banks and financial institutions (BFI) in Nepal. Employing the panel data regression models, this study examines the effect of daily COVID-19 positive cases to the stock returns – during pre-lockdown, lockdown, and after-lockdown period – of 74 listed firms in Nepal from 2 May 2019 to 25 April 2021. The empirical results confirm that there was no significant impact of daily increased number of COVID-19 positive cases to the stock returns of BFIs in Nepal throughout the entire study period. Furthermore, this study inquires the influence of pandemic period to the individual class of the BFIs sector in NEPSE[1]. It discloses that the commercial banks, development banks and microfinance companies’ stock returns were adversely impacted during the pre-lockdown and lockdown period. However, after-lockdown period had significantly rebounded the overall BFIs stock returns in Nepal with the highest returns earned by microfinance companies and lowest return by commercial banks. [1] Nepal Stock Exchange Limited

Forecasting the conditional heteroscedasticity of stock returns usingasymmetric models based on empirical evidence from Eastern Europeancountries: Will there be an impact on other industries?

This empirical study investigates the leverage effect in six Eastern European countries under normal and non-normaldistribution densities for the sample period from January 2020 to August 2020. We find three countries, Bulgaria, CzechRepublic and Russia which are subject to ARCH effect whereas Poland, Romania and Hungary do not exhibit ARCHeffect in daily stock returns. Further, our study finds leverage effect, where past bad news affects is asymmetrical, pastnegative returns cause more volatility in current stock returns as compared to past positive returns, in three EasternEuropean countries. Based on the AIC and BIC model selection criteria we find that the non-normal student t-distributionand GED produce reliable estimates for Bulgaria, Czech Republic and Poland, respectively. The autocorrelation functionQ1 statistic confirms the insignificance of autocorrelation in residuals of TGARCH model. The impact of stock marketdynamics on other industries, such as pharmaceutical industry, textile and clothing industry, automotive industry issignificant, especially in the conditions of COVID-19 pandemic

COVID-19 Pandemic, Stimulus Packages and Stock Returns in Vietnam

This paper investigates the impacts of COVID-19’s new cases and stimulus packages on the daily stock returns of five key economic sectors (Finance, Fast-moving-consumer-goods (FMCG), Healthcare, Oil and Gas, and Telecommunication) in Vietnam – one of the best countries in the world for handling COVID-19. The research team uses the Pool OLS method, with the panel data of 11 342 observations from 107 listed firms in these five sectors in the period January-June 2020. The key findings are (i) all sectors’ stock returns are negatively affected by daily new confirmed cases of COVID-19, the hardest hit is on the financial sector, followed by FMCG, healthcare, oil and gas, and telecommunications sectors. Vietnam did not have many affected cases, but low average income makes investors and consumers more careful and hesitate to spend/invest; (ii) in contrast to prior studies, stimulus packages did not accelerate the growth of stock returns in all sectors, with the order from most to least negatively affected: finance, oil and gas, telecommunication, healthcare, and FMCG. The slow implementation made investors skeptical of the growth potential of firms, they assess the stimulus packages as the signs of economic downturn. This fact leads to different recommendations for the Vietnamese Government in combating COVID-19.

Investigating efficiency of frontier stock markets using multifractal detrended fluctuation analysis

PurposeThe investigation of the fractal nature of financial data has been growing in the literature. The purpose is to investigate the multifractal behavior of frontier markets using multifractal detrended fluctuation analysis (MFDFA).Design/methodology/approachThis study used daily closing prices of nine frontier stock markets up to 31-Aug-2020. A preliminary analysis reveals that these markets exhibit fat tails and clustering patterns. For a more robust analysis, a combination of Seasonal and Trend Decomposition using Loess (STL) and MFDFA has been employed. The former method is used to decompose daily stock returns, where later detected the long rang dependence in the series.FindingsThe results confirm varying degree of multifractality in frontier stock markets, implying that they exhibit long-range dependence. Based on these multifractality levels, Serbian and Romanian stock markets are the ones exhibiting least long-range dependence, while Slovenian and Mauritius stock markets indicating highest dependence in their series. Furthermore, the markets of Kenya, Morocco, Romania and Serbia exhibit mean reversion (anti-persistent) behavior while the remaining frontier markets show persistent behaviors.Practical implicationsThe information given by the detection of the fractal measure of data can support for investment and policymaking decisions.Originality/valueFrontier markets are of great potential from the perspective of international diversification. However, most of the research focused on other emerging and developed markets, especially in the context of multifractal analysis. This study combines the STL method and a physics-based robust technique, MFDFA to detect the multifractal behavior of frontier stock markets.