Stock Return Data Research Articles

Month of Ramadan effect swings and market becomes adaptive

PurposeThis paper aims to enhance the existing literature on adaptive market hypothesis (AMH) as this study first time links the month of Ramadan with AMH that permits the performance of well-known Ramadan effect to fluctuate over time.Design/methodology/approachTo fulfill the purpose, the authors inspect the daily returns of 107 individual firms listed at Pakistan Stock Exchange over the period of 20 years. To explore the varying degree of return predictability during Ramadan, the authors use four different subsamples comprising equal length of observations of five years each. The authors use a GARCH (1,1) regression model which facilitates for time varying nature of volatility in equity returns. To facilitate the non-normal nature of stock return data, the authors use Kruskal–Wallis test statistic.FindingsThe authors find that behavior of Ramadan effect evolves over time, as performance of this effect varies from time to time and consistent with AMH. Finally, the paper proposes that AMH is well elucidation of behavior of Ramadan effect than traditional efficient market hypothesis.Research limitations/implicationsFirst limitation is related to the choice of sub-sample as the study uses a sub-sample of five years. Second, the authors ignore transection cost (commissions, fee and taxes) as it is freely negotiated and varies between 4 and 10% (Khan, 2013). Due to such varying information we ignore the transaction cost. It is suggested that a sub-sample analysis of long period may be a more appropriate method to elucidate the idea of AMH in future research and suggest the current method could be adapted and helpful to examine other calendar and market anomalies in different equity markets.Practical implicationsThe paper includes implications for investors to choose a better model for investment. Investors can exploit greater returns in future month of Ramadan periods. Furthermore, the researchers can easily extend the methodology used in the study to address multiple issues like adaptive behavior of returns from bonds, real estate investment trusts, cryptocurrencies and trading rules of strategies.Social implicationsStudy confirms from sample t-test and GARCH (1,1) model that Ramadan effect is present in the full and in certain sub-samples; therefore, based on these discrepancies investors can earn abnormal returns by developing specific investment strategies as investors usually make investments in share according to the religious context of Islamic Calendar. The results provide good references for suitable time of investment in stock market. The findings of this study will be helpful to investors and brokers as well as portfolio managers to capture favorable returns across the Islamic calendar.Originality/valueThe paper identified need to study why behavior of Ramadan effect varies over time. The data set comprises daily returns of 107 individual companies over the period of 20 years to better investigate the varying nature of anomalous effect of month of Ramadan. The findings are valuable for international investors and portfolio managers.

Frank copula on value at risk (VaR) of the construction of bivariate portfolio (Case Study: stocks of companies awarded with the IDX top ten blue with stock period of 20 october 2014 to 28 february 2018)

Value at Risk (VaR) is a method to estimate the worst risk of an investment. The stock data is one of the financial time series data which often has high volatility which causes inconstant residual variance. The combination between several stocks in the portfolio makes the assumption of residual normality of the joint distribution model difficult to fulfill. The previous research on VaR by Sofiana in 2011 [3] and Hermansyah in 2017 [4] found that VaR value was reliable only for the data fulfilling normality assumption. Therefore, it is necessary to estimate VaR without ignoring the presence of heteroscedasticity and unfulfilled residual normality of the joint distribution model. This research aims to measure the VaR using Frank Copula-GARCH method with stock return data of BBRI, TLKM and UNVR for the period of 20 October 2014 to 28 February 2018. The research found that a pair of bivariate portfolio was TLKM and UNVR because they had the highest residual correlation value of Rho Spearman of ρ = 0.3204. Based on the data generation obtained using Monte Carlo simulation, the results of the VaR were -0.027883; -0.01886425; -0.01403 with confidence level at 99%, 95%, and 90% respectively.

Structural Breaks and Volatility Spillovers: The Case of the US and Canadian Stock Markets

This paper investigates the relations of structural breaks and volatility spillovers by using the US and Canadian stock return data. Specifically, applying spillover MGARCH models without and with structural break dummy variables to the two stock returns, this study derives the following interesting evidence. (1) First, we reveal that for both the US and Canadian stock returns, the volatility persistence parameter values in our spillover MGARCH models decline when structural break dummy variables are incorporated. (2) Second, we further clarify that when we do not take structural breaks into account, the spillover effect was unidirectional from Canada to the US. However, when we take structural breaks into consideration, the results from our spillover MGARCH model with structural break dummies demonstrate that the volatility spillover effects between the US and Canada become bidirectional. (3) Third, we furthermore reveal that around the Lehman Brothers bankruptcy in 2008, the time-varying volatilities derived from our spillover MGARCH model with structural break dummy variables show slightly higher values than those volatilities from our spillover MGARCH model with no structural break dummy variable.

Watch Your Neighbor: A Volatility Spillover in ASEAN-5 Stock Exchange

In the process of financial markets integration, this research was conducted to investigate the phenomenon of the transmission of stock return volatility among stock market in five ASEAN countries. Those were Indonesia, Singapore, Malaysia, Philippines, and Thailand. The research was important because when the interdependence of financial markets had increased, changes in asset prices in the market were not only influenced by the shock in the market but also by its response to asset price volatility that occurred in other countries. Information about the volatility spillover between markets was important for investors to the portfolio selection process. Exponential Generalized Autoregressive Conditional Heteroskedasticity (EGARCH) method was used on a daily time series stock return data obtained by accessing www.bloomberg.com. The result indicates that the shock in Singapore, Malaysia, Thailand, and the Philippines stock market will be transmitted to the Indonesia Stock Market with an asymmetric pattern. It has increased intensity after the implementation of the ASEAN Economic Community in December 2015.

A Multivariate Analysis of the Effects of Structural Breaks on Stock Return Volatility Persistence: The Case of the US and Japan

This paper quantitatively inspects the effects of structural breaks in stock returns on their volatility persistence by using the stock return data of the US and Japan. More concretely, applying the diagonal BEKK-MGARCH model with and without structural break dummies to the returns of S&P 500 and TOPIX, we reveal the following interesting findings. (1) First, we clarify that for both the US and Japanese stock returns, the values of the GARCH parameters, namely, the values of the volatility persistence parameters in the diagonal BEKK-MGARCH models decrease when we include the structural break dummies in the models. (2) Second, we further find that interestingly, during the Lehman crisis in 2008, the estimated time-varying volatilities from the diagonal BEKK-MGARCH model with structural break dummies are slightly higher than those from the no structural break dummy model. (3) Third, we furthermore reveal that also very interestingly, the estimated time-varying correlations from the diagonal BEKK-MGARCH model with no structural break dummy are slightly higher than those from the structural break dummy model.

High-dimensional Markowitz portfolio optimization problem: empirical comparison of covariance matrix estimators

ABSTRACTWe compare the performance of recently developed regularized covariance matrix estimators for Markowitz's portfolio optimization and of the minimum variance portfolio (MVP) problem in particular. We focus on seven estimators that are applied to the MVP problem in the literature; three regularize the eigenvalues of the sample covariance matrix, and the other four assume the sparsity of the true covariance matrix or its inverse. Comparisons are made with two sets of long-term S&P 500 stock return data that represent two extreme scenarios of active and passive management. The results show that the MVPs with sparse covariance estimators have high Sharpe ratios but that the naive diversification (also known as the ‘uniform (on market share) portfolio’) still performs well in terms of wealth growth.

Portfolio optimization and model predictive control: A kinetic approach

In this paper, we introduce a large system of interacting financial agents in which all agents are faced with the decision of how to allocate their capital between a risky stock or a risk-less bond. The investment decision of investors, derived through an optimization, drives the stock price. The model has been inspired by the econophysical Levy-Levy-Solomon model [ 30 ]. The goal of this work is to gain insights into the stock price and wealth distribution. We especially want to discover the causes for the appearance of power-laws in financial data. We follow a kinetic approach similar to [ 33 ] and derive the mean field limit of the microscopic agent dynamics. The novelty in our approach is that the financial agents apply model predictive control (MPC) to approximate and solve the optimization of their utility function. Interestingly, the MPC approach gives a mathematical connection between the two opposing economic concepts of modeling financial agents to be rational or boundedly rational. Furthermore, this is to our knowledge the first kinetic portfolio model which considers a wealth and stock price distribution simultaneously. Due to the kinetic approach, we can study the wealth and price distribution on a mesoscopic level. The wealth distribution is characterized by a log-normal law. For the stock price distribution, we can either observe a log-normal behavior in the case of long-term investors or a power-law in the case of high-frequency trader. Furthermore, the stock return data exhibit a fat-tail, which is a well known characteristic of real financial data.

The Idiosyncratic Risk in Chinese Stock Market

Using daily stock return data of all listed firms in Chinese stock market from 1998 to 2018, we disaggregate the volatility of common stocks at the market, industry and firm levels. We find market volatility, on average, is the highest while firm volatility tends to lead to market and industry volatility series. None long-term trend time series behaviour exists for all three volatility series and firm volatility is best described by an autoregressive process with regime shifts associated with the structural market reforms or volatile market movements. We further proceed to identify the source of volatility at the industry level and find the idiosyncratic volatility in the largest manufacturing industry not only accounts for the largest proportion in the aggregate firm volatility but also is the lead indicator for the idiosyncratic volatility of other industries. Finally, unlike Brandt et al. [Review of Financial Studies 23(2): 863-899 (2010)], we find the idiosyncratic volatility in Chinese stock market is associated with high stock trading activities by institutional investors, the result of which is also robust when using other measures of idiosyncratic volatility.

고유변동성과 수익률 이분산성에 관한 논고

고유변동성과 수익률 이분산성에 관한 논고

금융업권간 상호연계성 및 부실전이위험과 예금보험기금 체계에 관한 연구(Interconnectedness and Contagion Risk in the Korean Financial Industry and Its Implication for the Deposit Insurance Fund)

Korean Abstract: 우리나라의 금융산업이 금융지주체제 위주로 진전되며 업권간 겸업이나 복합상품 등의 확대로 상호연계성이나 부실전이 위험에 대한 우려가 확대되고 있다. 본고에서 개별 업권의 주가수익률 자료를 이용하여 주성분분석 방법으로 살펴본 결과 우리 금융산업의 업권간 연계성 정도가 상당히 큰 것으로 분석되었다. 상호연계도나 부실전이 위험이 큰 대형복합금융회사 등의 대규모 부실사태가 재발할 경우 현행 예보기금체계로 대응하는데 한계가 있다. 이미 저축은행계정과 특별계정이 적자인 상태이고, 기금 전반적으로 적립금 규모가 크지 않아 대규모 부실을 감당하기에는 어려운 현실이다. 따라서, 본고에서는 영국의 FSCS 기금과 같이 사후 분담 방식의 공동계정 설치를 통하여 대규모 부실에 금융업권 전체가 공동으로 대응할 것을 제안한다. 다만, 특별계정이 2026년까지 한시적으로 운영되는 점을 감안하여 그 이후부터는 공동계정의 목표기금 규모를 설정하여 사전적립방식으로 전환운영하는 것이 바람직하다고 제안한다. English Abstract: As the Korean financial companies expand their operation into the complex financial products, concerns over the contagion risk and spillover effect of financial companies' failure are increasing. This paper employs the Principal Component Analysis (PCA) methodology to empirically investigate and confirm the high degree of interconnectedness of the Korean financial companies. In the analysis, the stock return data of financial sectors and financial companies over the sample periods of 1997-2017 are used. Current Deposit Insurance Fund (DIF) is in severe deficit, and the size of Savings Banks’ and Special are not adequate to cope with the multiple failures of complex financial companies, in particular. Introducing a new account, so called Account in the DIF, following the example of the Financial Services Compensation Scheme (FSCS) in the U.K., which the KDIC can use to resolve the insured financial companies, is proposed. A funding scheme of the General to be ex-post until 2026, the year in which the term of Special expires, is also proposed. After that, it can be switched into the ex-ante basis funding scheme again.

ESTIMASI VALUE AT RISK PORTOFOLIO SAHAM MENGGUNAKAN METODE GARCH-COPULA (Studi Kasus : Harga Penutupan Saham Harian Unilever Indonesia dan Kimia Farma Periode 1 Januari 2013- 31 Desember 2016)

Any investment in the stock market will earn returns accompanied by risks. Return and risk has a mutual correlation that equilibrium. The formation of a portfolio is intended to provide a lower risk or with the same risk but provide a higher return. Value at Risk (VaR) is a instrument to analyze risk management. Time series model used in stock return data that it has not normal distribution and heteroscedastisicity is Generalized Autoregressive Conditional Heteroscedasticity (GARCH). GARCH-Copula is a combined method of GARCH and Copula. The Copula method is used in joint distribution modeling because it does not require the assumption of normality of the data and can capture tail dependence between each variable. This research uses return data from stock closing prices of Unilever Indonesia and Kimia Farma period January 1, 2013 until December 31, 2016. Copula model is selected based on the highest likelihood log value is Copula Clayton. Value at Risk estimates of Unilever Indonesia and Kimia Farma's stock portfolio on the same weight were performed using Monte Carlo simulation with backtesting of 30 days period data at 95% confidence level. Keywords : Stock, Risk, Generalized Autoregressive Conditional Heteroscedasticity (GARCH), Copula, Value at Risk

Modeling Stock Return Data Using Asymmetric Volatility Models: A Performance Comparison Based On the Akaike Information Criterion and Schwarz Criterion

The Generalized Autoregressive Conditional Heteroscedasticity (GARCH) model has been widely used in time series forecasting especially with asymmetric volatility data. As the generalization of autoregressive conditional heteroscedasticity model, GARCH is known to be more flexible to lag structures. Some enhancements of GARCH models were introduced in literatures, among them are Exponential GARCH (EGARCH), Threshold GARCH (TGARCH) and Asymmetric Power GARCH (APGARCH) models. This paper aims to compare the performance of the three enhancements of the asymmetric volatility models by means of applying the three models to estimate real daily stock return volatility data. The presence of leverage effects in empirical series is investigated. Based on the value of Akaike information and Schwarz criterions, the result showed that the best forecasting model for our daily stock return data is the APARCH model.

The Dynamic and Dependence of Takaful and Conventional Stock Return Behaviours: Evidence from the Insurance Industry in Saudi Arabia

This paper investigates the dynamics of volatility in the stock market using competing univariate GARCH specifications. Moreover, it provides a study of the pairwise correlation pattern of stock returns for a wide range of Saudi Arabian insurance business lines by using a dynamic DCC-GARCH model. Our results show that volatility responds asymmetrically to shocks with a persistence of variance in the stock return data, supporting the presence of irrational behaviour as well as the effectiveness of a cross-market diversification strategy. Finally, we reach a point at which, between every two-business line stock returns, there is a dynamic conditional correlation.

PENGUJIAN EFISIEN PASAR MODAL BENTUK LEMAH DI PASAR MODAL SYARIAH

The purpose of this study to examine whether the Islamic capital market in Indonesia is efficient in a weak form. The efficient capital market weak form states that the capital market is said to be efficient if the price formed reflects past information including previous price information. With these conditions, the stock price will move randomly and past price data cannot be used to predict prices in the future. The sample in this study uses Islamic stocks that listed in the Jakarta Islam Index (JII) in 2018. Sharia stocks that consistently enter for 2 periods in 2018 into the JII are 27 shares. The test method is done by testing Run Test. Run Test is used to see whether the price movements of Islamic stocks move randomly or not. The variables tested were daily stock return data from January to June 2018. The results showed stock price movements during the period of the study were not random. This means that the Islamic capital market in Indonesia has not been efficient in a weak form.

The analysis of data errors in financial information databases: New evidence from the Korean financial markets

Background: As financial professionals including policy-makers tend to base decisions on research performed using large machine-readable financial databases, the accuracy of the financial data provided by database companies has a direct impact on the quality of their decisions. Objectives: The objective of this study was to examine data errors in the DataGuide and KisValue databases which are both primary sources of stock prices and return data for Korea Exchange securities in Korea. This article also discussed the methodological implications of erroneous data on monthly stock returns in empirical studies on Korean financial markets. Methods: A cross-checking technique was used in this study. Results: The results suggest that there are material discrepancies between the DataGuide and KisValue databases in monthly stock returns, most of which are attributable to the mishandling of split events and of missing values. The results also indicate that DataGuide provides a more reliable service than KisValue in terms of monthly stock returns. Conclusion: The results show that extreme monthly returns resulting from serious data errors in the DataGuide and KisValue databases may be enough to sharply change the properties of monthly stock return distributions and to over- or underestimate long-term abnormal stock returns.

Macroeconomic forecasting with mixed data sampling frequencies: Evidence from a small open economy

AbstractThe aim of this study was to forecast the Singapore gross domestic product (GDP) growth rate by employing the mixed‐data sampling (MIDAS) approach using mixed and high‐frequency financial market data from Singapore, and to examine whether the high‐frequency financial variables could better predict the macroeconomic variables. We adopt different time‐aggregating methods to handle the high‐frequency data in order to match the sampling rate of lower‐frequency data in our regression models. Our results showed that MIDAS regression using high‐frequency stock return data produced a better forecast of GDP growth rate than the other models, and the best forecasting performance was achieved by using weekly stock returns. The forecasting result was further improved by performing intra‐period forecasting.

Pemodelan Data Return Saham PT. Bank Republik Indonesia dengan Self-Exciting Threshold Autoregressive dan Algoritma Genetika

Nonlinear time series model is a time series model applied to data that has the nonlinear pattern. One of the nonlinear time series models is Self-Exciting Threshold Autoregressive (SETAR). The SETAR model is a time series model that data modeling is done by dividing data into multiple regimes, whereas each regime following an autoregressive (AR) model. The division of the regime based on the score of the delay and threshold of the data itself. The number of SETAR model parameters not only resulted from the best model search process but also resulted in a SETAR model that is not yet optimum. Based on these findings, this study used Genetic Algorithm (GA) to produce the best and optimum SETAR model. In this research, using SETAR simulation data modeling and return data of Bank Rakyat Indonesia (BRI) were performed. The method used to model the data is Grid Search (GS) and Genetic Algorithm (GA). The result of analysis of SETAR simulation data shows that GA method gives better modeling result than GS method. The GA motive AIC value for the amount of 200 data is -3.976178 which is smaller than the AIC GS method of 1.361723. For the amount of data of 500 AIC values, GA method is also smaller than AIC GS method. In BRI stock return data, GA method also gives better modeling result compared to GS. It is marked by the GA AIC method value of -11147.66 less than -11146.26 which is the AIC method of GS. Thus, the result of analysis of SETAR model simulation data and BRI stock return shows that GA method gives better modeling result compared to GS method based on generated AIC value.

Modelling financial time series based on heavy-tailed market microstructure models with scale mixtures of normal distributions

ABSTRACTThis paper presents a type of heavy-tailed market microstructure models with the scale mixtures of normal distributions (MM-SMN), which include two specific sub-classes, viz. the slash and the Student-t distributions. Under a Bayesian perspective, the Markov Chain Monte Carlo (MCMC) method is constructed to estimate all the parameters and latent variables in the proposed MM-SMN models. Two evaluating indices, namely the deviance information criterion (DIC) and the test of white noise hypothesis on the standardised residual, are used to compare the MM-SMN models with the classic normal market microstructure (MM-N) model and the stochastic volatility models with the scale mixtures of normal distributions (SV-SMN). Empirical studies on daily stock return data show that the MM-SMN models can accommodate possible outliers in the observed returns by use of the mixing latent variable. These results also indicate that the heavy-tailed MM-SMN models have better model fitting than the MM-N model, and the market microstructure model with slash distribution (MM-s) has the best model fitting. Finally, the two evaluating indices indicate that the market microstructure models with three different distributions are superior to the corresponding stochastic volatility models.

Robust precision matrix estimation via weighted median regression with regularization

AbstractA precision matrix is an important parameter of interests because its elements describe useful association information among multiple variables, which has a wide variety of applications. For example, it is used for inferring gene regulation networks in genomic studies and stock association networks in financial studies. However, in many cases, the precision matrix needs to be robustly estimated due to the presence of outliers. We propose estimating a sparse scaled precision matrix via weighted median regression with regularization. Our weighted median regression approach is consistent under various distributional assumptions including multivariate t‐ or contaminated Gaussian distributions. This fact is illustrated with simulation studies and a real data analysis with monthly stock return data. The Canadian Journal of Statistics 46: 265–278; 2018 © 2018 Statistical Society of Canada

Labor unemployment insurance and firms’ future performance

PurposeThe purpose of this paper is to investigate the association between unemployment insurance (UI) benefits and firms’ future performance as well as the association between UI benefits and volatility of firms’ future performance.Design/methodology/approachQuantitative analyses are used to perform empirical testing, and the variables in this study have been selected from previous literature. Empirical data consists of UI benefits data published from 2003 to 2012 on the US Department of Labor website, accounting data from Compustat, and stock return data from CRSP.FindingsUnemployment benefits are positively associated with firms’ future earnings and cash flows. Also, unemployment benefits are negatively associated with volatility of firms’ future earnings and cash flows. Finally, the positive association between unemployment benefits and firms’ future performance is more pronounced for firms with larger changes in labor force, and the negative association between unemployment benefits and volatility of firms’ future performance is more pronounced for firms with higher labor force volatility and capital structure volatility.Research limitations/implicationsTo the extent that other correlated omitted variables exist, the readers are asked to interpret the findings in this paper with caution.Originality/valueThis study contributes to prior literature on labor economics, finance, and accounting. The findings may be of interest to academic researchers and policy makers.