Rolling Window Method Research Articles

Identifying crucial financial markets in the flows of cross-border capital – evidence from China's financial risk network

With the increasing openness of China's financial markets, it is important to address cross-border capital risks. This paper first calculates the stress indicators of financial markets by 24 variables, and then utilizes the Diebold-Yilmaz connectedness approach to examine the spillover effects among the volatility of cross-border capital and the stress indicators of various financial markets. We show both the real estate and stock market are crucial for cross-border capital flow. Using the rolling window method, we find significant time-varying spillovers between cross-border capital and financial markets, which peak during the periods with significant events such as the global financial crisis, the COVID-19 epidemic, and the shift in currency regime. This paper further applies the Markov-switching autoregressive model to identify three different states for the synthetic financial stress. After re-analyzing the subsample data, we observe that stock and real estate markets play significant roles in the low-stress state, foreign exchange and real estate markets in the medium-stress state, and stock and money markets in the high-stress state.

Time-varying effects of structural oil price shocks on financial market uncertainty

This study employed the structural oil price decomposition method proposed by Ready (2018) to decompose oil price shocks into oil risk shocks, demand shocks, and supply shocks. By using the Diebold and Yilmaz (DY) spillover index and rolling window methods, the static and dynamic spillovers of structural oil price shocks on financial market uncertainty were examined. The findings suggest that oil risk shocks exhibited the strongest spillover effects on financial market uncertainty (except for South Africa), followed by oil demand shocks, while oil supply shocks had virtually no impact. Second, the effects of structural oil price shocks on financial market uncertainty were time-varying. Third, significant differences in the spillover effects of structural oil price shocks on financial market uncertainty were found across countries, and the spillover effect of oil risk shocks on the financial market uncertainty in the United States was the largest in all periods. Fourth, the spillover effects of oil demand shocks on financial market uncertainty were larger in the high than in the low oil price period (except for Japan). Finally, during the COVID-19 (coronavirus disease) pandemic compared with the pre-epidemic period, the spillover effects of oil risk shocks on the financial market uncertainty in China significantly decreased, while simultaneously, the spillover effects of oil supply shocks on the financial market uncertainty in Australia substantially increased.

Portfolio Optimization Based on Rolling Window Using 5 Stocks

This paper aims to explore a method of constructing dynamically adjusted investment portfolios through the combination of rolling windows and mean-variance models. The construction of investment portfolios plays a crucial role in financial markets by effectively diversifying risks and achieving stable investment returns. This study analyzed adjusted closing price data from five stocks (AAPL, JPM, JNJ, XOM, and PG), sourced from Yahoo Finance. The rolling window method was employed to predict future stock prices and construct investment portfolios based on these predictions. This study calculated annualized average return and covariance matrix for each window. The mean-variance model and optimization algorithms were then used to determine the optimal weights for daily portfolio composition. The results demonstrate the high accuracy of the rolling window method in predicting short-term stock prices. Notably, Procter & Gamble (PG) and Johnson & Johnson (JNJ) exhibited the lowest prediction errors. Investment portfolios based on rolling window predictions performed well over a certain period. Nevertheless, the S&P 500 index did not show a substantial disadvantage compared to their long-term performance. This research provides dynamic portfolio optimization methods of practical value for investors in financial markets.

Does Islamic Mutual Fund Bear Higher Risk than Conventional Mutual Funds? An Empirical Analysis from Bangladesh

This study aims to identify whether Islamic mutual funds bear higher risk exposure than conventional mutual funds due to implementing their shariah screening criteria to select assets on the portfolio. For this purpose, monthly closing price data of Islamic and conventional funds operated in Bangladesh are collected from January 2016 to August 2023. A total of 2320 observations of each risk measure (e.g., standard deviation, semi-standard deviation, semi-standard deviation, and beta) are computed using a 12-month rolling window method to compare risk exposure between Islamic and conventional funds using univariable and multivariate analysis. The univariate analysis is conducted by performing an independent samples t-test, which confirms that overall, Islamic funds bear lower risk exposure than conventional funds. In multivariate analysis, the Feasible Generalized Least Square (FGLS) method, a dynamic panel data analysis model, is applied where the effects of macroeconomic variables such as deposit rate, GDP growth rate, exports, imports, broad money, and remittances are controlled. The results of the multivariate analysis also confirm that Islamic mutual fund risk exposure is lower than that of conventional mutual funds. This study will be helpful for practitioners and institutional investors in decision-making.

Effect of Macroeconomic Factors on Mutual Funds Risk and Return: An Empirical Study from Bangladesh

This study aims to identify the influence of macroeconomic factors on the risk and return of mutual funds in Bangladesh. Monthly closing price data of 27 mutual funds from Bangladesh are collected from December 2015 to December 2022. Additionally, monthly data of 6 macroeconomic variables, i.e., deposit rate, export, import payments, remittance, broad money (M2) and GDP growth rate, are gathered for this study. This study utilized standard deviation and beta as risk measures, and the Sharpe and Treynor ratios are applied as risk-adjusted return (RAR) measures. All the risk and risk-adjusted return measures are computed using 12-months rolling window method. The random effect model of panel data analysis is applied to find the influence of macroeconomic variables on the risk and return of mutual funds. Overall findings indicate that macroeconomic factors significantly influence mutual fund risk exposure. On the other hand, risk-adjusted return (RAR) is also significantly influenced by the macroeconomic variables. This empirical evidence helps practitioners and institutional investors in their decision-making in the situation of market asymmetric. Keywords: Risk-Adjusted Return, Bangladesh, Mutual Fund, Standard Deviation, Beta, Sharpe Ratio, Treynor Ratio

Demand forecasting for platelet usage: From univariate time series to multivariable models.

Platelet products are both expensive and have very short shelf lives. As usage rates for platelets are highly variable, the effective management of platelet demand and supply is very important yet challenging. The primary goal of this paper is to present an efficient forecasting model for platelet demand at Canadian Blood Services (CBS). To accomplish this goal, five different demand forecasting methods, ARIMA (Auto Regressive Integrated Moving Average), Prophet, lasso regression (least absolute shrinkage and selection operator), random forest, and LSTM (Long Short-Term Memory) networks are utilized and evaluated via a rolling window method. We use a large clinical dataset for a centralized blood distribution centre for four hospitals in Hamilton, Ontario, spanning from 2010 to 2018 and consisting of daily platelet transfusions along with information such as the product specifications, the recipients' characteristics, and the recipients' laboratory test results. This study is the first to utilize different methods from statistical time series models to data-driven regression and machine learning techniques for platelet transfusion using clinical predictors and with different amounts of data. We find that the multivariable approaches have the highest accuracy in general, however, if sufficient data are available, a simpler time series approach appears to be sufficient. We also comment on the approach to choose predictors for the multivariable models.

Research on AUV dynamic obstacle avoidance planning based on rolling speed obstacle method

In this paper, aiming at the problem of poor path planning and obstacle avoidance effect of autonomous underwater vehicle (AUV) in a dynamic environment, a feasible rolling speed obstacle method is proposed. This method combines the rolling window method with the speed obstacle method, and designs a suitable three-dimensional model predictive controller based on the rolling window method under a hybrid obstacle avoidance structure, and achieves stable tracking of the reference path by optimizing the objective function. A three-dimensional collision cone and speed obstacle cone model is constructed while the window is rolling. If the collision avoidance condition is met, the critical collision point is calculated, and the AUV is guided to avoid obstacles safely by tracking the critical collision point; if collision avoidance ends, guide AUV trajectory recovery. The final simulation and experimental results show that the performance of the rolling speed obstacle method in avoiding dynamic obstacles is 30% higher than the rolling window method and 40% higher than the speed obstacle method. The method used in this paper can effectively improve the dynamic obstacle avoidance ability of AUV in real-time path planning.

Hedging Bitcoin with commodity futures: An analysis with copper, gas, gold, and crude oil futures

There is increased interest in the dynamic relationships between cryptocurrency and commodity futures. This study examines the hedging performance of four well-known commodity futures against fluctuations in Bitcoin prices. Furthermore, this study used the DCC- and ADCC-MGARCH models to estimate conditional correlations and time-varying optimal hedge ratios between the returns of copper, gas, gold, and crude oil futures, and Bitcoin. We use a rolling window method to calculate one-step-ahead time-varying optimal hedge ratios and evaluate hedging performance. The empirical results show that gas and gold have hedge benefits to Bitcoin. However, crude oil shows poor hedge performance. From the results of one-step-ahead hedge ratios, for copper and oil, we find that hedge ratios increased and hedge effectiveness improved since the COVID-19 outbreak.

The role of green energy stock market in forecasting China's crude oil market: An application of IIS approach and sparse regression models

This study investigates the effectiveness of sparse regression models with their diverse specifications and the impulse indicator saturation (IIS) method in forecasting crude oil prices and their returns in China. The empirical findings showed that the IIS approach and sparse regression models are more effective than the benchmark of the no-change model. The IIS approach consistently outperformed the competing models and produced reliable results in terms of both ROS2 statistics and success ratio, as it is invariant to window size and time horizon. The results suggest that sparse regression models exhibit a notable decline in accuracy compared to the IIS approach over the long horizon. However, the selection of window size in the rolling window method plays a crucial role. Meanwhile, the sparse regression models are quite sensitive to window size; with a long horizon forecast and a small window size, the accuracy of the results is far less than with a broader window size. In contrast, the IIS method provides quite accurate forecasts regardless of window size and time horizon. The elastic smoothly clipped absolute deviation (E-SCAD) and elastic minimax concave penalty (E-MCP) remained more successful across the sparse models, possibly as a result of the high correlation among the set of predictors.

Quantile connectedness between cryptocurrency and commodity futures

This study investigates the quantile dependence and spillovers for return and volatility of Bitcoin and futures of crude oil, copper, natural gas, and gold. We apply quantile vector autoregression and quantile connectedness approaches using a rolling-window method to examine spillover dynamics. The empirical results reveal that return spillovers increase when asset returns deviate from normal market conditions, and volatility spillovers are particularly increased during bullish market conditions. Moreover, the study finds that under bearish and normal market conditions, Bitcoin is a major recipient of return spillovers from all futures, and crude oil and copper are major transmitters of return spillovers to natural gas and gold, respectively. However, during bullish market states, Bitcoin becomes a major transmitter of return spillovers to other futures. Under unstable market conditions, gold is a major transmitter of volatility spillover to crude oil and natural gas. Furthermore, the directional link from Bitcoin to other futures is stronger when market issues exist.

Enhancing the Predictive Power of Google Trends Data Through Network Analysis: Infodemiology Study of COVID-19.

The COVID-19 outbreak has revealed a high demand for timely surveillance of pandemic developments. Google Trends (GT), which provides freely available search volume data, has been proven to be a reliable forecast and nowcast measure for public health issues. Previous studies have tended to use relative search volumes from GT directly to analyze associations and predict the progression of pandemic. However, GT's normalization of the search volumes data and data retrieval restrictions affect the data resolution in reflecting the actual search behaviors, thus limiting the potential for using GT data to predict disease outbreaks. This study aimed to introduce a merged algorithm that helps recover the resolution and accuracy of the search volume data extracted from GT over long observation periods. In addition, this study also aimed to demonstrate the extended application of merged search volumes (MSVs) in combination of network analysis, via tracking the COVID-19 pandemic risk. We collected relative search volumes from GT and transformed them into MSVs using our proposed merged algorithm. The MSVs of the selected coronavirus-related keywords were compiled using the rolling window method. The correlations between the MSVs were calculated to form a dynamic network. The network statistics, including network density and the global clustering coefficients between the MSVs, were also calculated. Our research findings suggested that although GT restricts the search data retrieval into weekly data points over a long period, our proposed approach could recover the daily search volume over the same investigation period to facilitate subsequent research analyses. In addition, the dynamic time warping diagrams show that the dynamic networks were capable of predicting the COVID-19 pandemic trends, in terms of the number of COVID-19 confirmed cases and severity risk scores. The innovative method for handling GT search data and the application of MSVs and network analysis to broaden the potential for GT data are useful for predicting the pandemic risk. Further investigation of the GT dynamic network can focus on noncommunicable diseases, health-related behaviors, and misinformation on the internet.

Age-dependent association of high urinary iodine concentration with major depression in adults: NHANES 2007–2020

Excessive iodine exposure can have detrimental effects on thyroid function and overall health. This study aimed to investigate the age-dependent association between high urinary iodine concentration (UIC) and major depression symptoms in adults, using data from the National Health and Nutrition Examination Survey (NHANES) from 2007 to 2020. To perform stratified analysis by age, we utilized a rolling window method with a 15-year window width to examine the trend of the odds ratios (ORs) of UIC on depression symptoms with age. Full-factor and one-factor multinomial logistic regression models were employed to calculate the ORs, and violin plots were utilized to depict the ORs of UIC on major depression. The LASSO regression was applied to select variables for one-factor models. The bootstrap method was utilized to ensure the robustness of the results, and the Games-Howell test was applied to compare the differences in the bootstrapped ORs of different UIC groups. Our results indicate that, after age 46, the ORs of high UIC (≥ 300 μg/L) on major depression are significantly higher than those of normal UIC (100–199 μg/L). The bootstrapped ORs of high UIC on major depression calculated by the full-factor and one-factor multinomial logistic regression models are 1.9 (1.28, 2.82) and 1.42 (1.02, 1.93) among participants aged 46 and older, respectively. Based on these findings, we conclude that major depressive symptoms are significantly associated with high UIC among older individuals aged 46 and above.

The instability of U.S. economic policy: A hindrance or a stimulus to green financing?

This article aims to evaluate whether green bonds (GB) can hedge the policy uncertainty risk and enhance the stability of the U.S. economic environment. Existing research provides sufficient theoretical support for GB to diversify economic risks and optimise investment portfolios. Against this background, we adopt the bootstrap rolling-window method to detect the causality between GB and economic policy uncertainty (EPU). The findings evidence that GB is positively influenced by EPU, suggesting that policy uncertainty risk stimulates the growth of green financing. Therefore, GB can be considered a valid hedge against uncertainty shocks. This outcome is supported by the general equilibrium model, which indicates that EPU has specific influences on GB. The adverse impact of GB on EPU demonstrates that GB can improve U.S. policy stability. Moreover, the GB market has an early warning effect on the economic situation, which can be a barometer reflecting EPU fluctuations. GB has become an essential asset for investors in the ongoing global economy and financial market turbulence. Hence, when formulating economic policies, the government should consider the impact of policy changes on the GB market and offset the negative influences of policy fluctuations.

Estimating contagion mechanism in global equity market with time‐zone effect

AbstractThis paper proposes a time‐zone vector autoregressive (VAR) model to investigate comovements in the global financial market. Analyzing daily data from 36 national equity markets, we explore the subprime and European debt crises using static analysis and the COVID‐19 crisis through a rolling window method. Our study of comovements using VAR coefficients reveals a resonance effect in the global system. Findings on densities and assortativities suggest the existence of the transmission mechanism in all periods and abnormal structural changes during the crises. Strength analysis uncovers the information transmission mechanism across continents over normal and turmoil periods and emphasizes specific stock markets' unique roles. We examine dynamic continent strengths to demonstrate the contagion mechanism in the global equity market over an extended period. Incorporating the time‐zone effect significantly enhances the VAR model's interpretability. Signed networks provide more information on global equity markets and better identify critical contagion patterns than unsigned networks.

Testing Okun's Law Over the Business Cycle: The Case of South Africa

ABSTRACT: Understanding the relationship between output and unemployment (Okun's law) is important for policymakers, particularly during crises. One of the aspects of Okun's law that is commonly examined during crises is the structural stability and behavior of Okun's law over the business cycle. While this issue has been addressed empirically in developed countries, little is known about it in developing countries such as South Africa. Hence, this study examines the structural stability and behavior of Okun's law over the business cycle in South Africa. This study adopts both the difference and gap methods of formalizing Okun's law to implement its objectives. The recursive rolling window method was used to test the structural stability of Okun's law over time. The behavior of Okun's law over the business cycle is examined using the Markov-switching regression method. This study was conducted using the data from 1994Q1 to 2021Q1. The results of this study show that Okun's law varies over the business cycle because the response of unemployment to economic expansion is quite different from that of economic contraction. Okun's law holds during economic expansion but fails to hold during an economic recession. Evidence from this study also reveals that the coefficients of Okun's law vary over time. For instance, in the case of the difference method, Okun's coefficients range from 0.063 to 1.221 in absolute terms. For the gap method, especially when the H-P filtering method is applied, Okun's coefficients range from 0.509 to 9.412 in absolute terms. In summary, the findings from this study suggest that cyclical unemployment responds more significantly to cyclical output growth than the response of changes in unemployment to changes in output. In addition, this study proves that Okun's law is unstable over time in South Africa. These findings imply a high degree of variability between the labor and goods markets in the country. Hence, policies must be designed to harmonize the divergence between the two markets. This will require the implementation of macroeconomic policies such as fiscal and monetary policies. From a fiscal policy perspective, the government should reduce taxes or provide tax holidays to firms. The interest rate should be set low in the case of monetary policy.

Impact of the Local and Global Crisis on Stock Market Efficiency

The study examines the evolution of the stock market efficiency of Indian banks during the period from 1 January 2007 to 30 June 2022. The study also seeks to investigate the degree of the impact of the different crises on the stock market efficiency in response to three major events: the global financial crisis, the local banking crisis and the pandemic crisis. For this, the wild bootstrap automatic variance ratio (WBAVR) test is applied using the rolling window method to account for the implications of the adaptive market hypothesis (AMH). For the robustness of the analysis, the study applies the automatic portmanteau (AQ) test, which is also based on a data-driven procedure. The findings show that the market efficiency of Indian banks is not an all-or-nothing phenomenon; rather, both efficiency and inefficiency co-exist simultaneously, with the Central Bank of India noted to be the most ‘inefficient’ bank. The findings demonstrate that market efficiency is ‘context-dependent’, that is, the stock market efficiency significantly alters in response to black-swan events happening in the economy. The study sheds light on the degree of the impact of different events on market efficiency, and it is shown that the internal crisis of the industry of high NPAs has a far greater impact on market efficiency compared to the global financial and pandemic crises. This research may assist policymakers in developing a comprehensive strategy to enhance the stock market efficiency of Indian banks in the face of such local and global crises.

The intertemporal substitution effect of energy consumption under climate policy changes

Based on the intertemporal substitution effect, the high inflation expectations can stimulate agents to consume now rather than in the future. However, under the background of global climate policy changes, how inflation expectations affect energy consumption? Using the bootstrap Granger full-sample causality test and sub-sample rolling window tests, this study examines the intertemporal substitution effect of energy consumption in the U.S. The results based on the full-sample data indicate no causality between inflation expectations and energy consumption, which suggests that the intertemporal substitution effect of energy consumption does not exist. Nevertheless, the rolling window method which estimates a time-varying causality identifies a short-lived positive effects of inflation expectations on energy consumption in a distinct sub-period before the global Paris agreement, but disappears since then. Therefore, the intertemporal substitution effect regarding energy consumption does not exist under the background of pressing carbon targets. The effects of energy consumption on inflation expectations can be positive or negative, which tells a cautionary tale about climate policies aiming at engineering lower carbon emissions.

On the efficiency of the gold returns: An econometric exploration for India, USA and Brazil

As a precious metal and investment commodity, gold has been signified to be important for risk management, diversification, and hedging. The gold market has undergone considerable structural changes in the facet of the pandemic and other geopolitical developments, attracting the interest of investors. Thus, it is crucial to look into how these structural changes affect the efficiency of the market. Accordingly, the study examines and compares the evolution of the gold market efficiency in three major economies from January 1, 2018, to August 31, 2022: India, USA, and Brazil. For this, we first decompose the time series using Loess Smoother's Seasonal and Trend Decomposition and then employ a multifractal detrended fluctuation analysis approach. The estimates are strengthened by the alternative approach of the rolling window method of wild bootstrap automatic variance ratio. The findings indicate a considerable decline in the efficiency of the gold returns across three economies, with the highest decline in India, followed by USA and Brazil. Notably, during covid and post covid periods, India and USA show persistence in small fluctuations, while Brazil displays persistent behavior in large fluctuations. Thereby, the market panic makes the gold market unstable, and its use as a safe haven is “erratic”.

Disentangling the impact of economic and health crises on financial markets

This paper explores the impact of different crises on the informational efficiency of financial assets. The study covers stock markets indices (ASX200, DAX30, EuroStoxx50, S&P500 and Nikkei), commodities (gold and oil) and volatility (VIX). The study analyzes, using a rolling window method, the long memory profile and the multifractality of the time series by means of the DFA and generalized Hurst exponents. This dynamic analysis is important as it uncovers the time-varying behavior of returns characteristics, affecting the investment decisions and trading strategies at different moments of time. The paper extends the current literature on informational efficiency, providing evidence of the distinct impact on the long memory and on the multifractality of the time series, depending on the nature of the crisis and the market. The results could be of interest for investors as well as for academics, regarding the hedging limits of the models during calm or turbulent times.

Does technology innovation help to achieve carbon neutrality?

Technological innovation (TI) can optimise energy structure and achieve green development, notably by reducing carbon dioxide (CO2) emissions. In the context of global warming, testing whether TI can reduce CO2 emissions is essential to achieve carbon neutrality. Therefore, the rolling-window method is used to overcome the issue of non-constant parameters in VAR systems and time series and further examines the role of TI in mitigating carbon pollution. The findings reveal that TI has both positive and negative effects on CO2. The negative impact suggests that TI is an efficient way to reduce CO2 emissions. This outcome is consistent with the energy-environment model, implying that TI has prominent potential to decrease climate change risks and accomplish net-zero emissions. Nevertheless, the positive effect indicates that the rebound effect of TI will increase energy consumption and cause more pollution. Conversely, the negative link of CO2 on TI means governments tend to make greener policies to reduce carbon pollution under intense environmental pressure. Thus, governments should accelerate the process of energy structure transformation and encourage ecological innovation development related to environmental protection. Besides, financial institutions must provide ample funds to launch low-carbon development strategies, mitigate climate change and promote sustainable economic growth.