Vector Autoregression Research Articles

Statistical analysis of gold production in South Africa using ARIMA, VAR and ARNN modelling techniques: Extrapolating future gold production, Resources–Reserves depletion, and Implication on South Africa's gold exploration

South African gold mining is one of the main contributors to the country's economic growth and employment creation. Assessment of future gold production is pivotal for positioning the country's supply security and contribution to the projected global demand. In this study, we modelled and forecasted South African and global gold production trends (1990–2022) using the Autoregressive Integrated Moving Average (ARIMA), Vector Autoregressive (VAR), and Autoregressive Neural Network (ARNN) techniques. The study also evaluated the impact of annual productions on the collated reserves (2008–2021) and the contribution of resource–reserve conversion in sustaining gold reserves within the South African goldfields. The ARIMA (1,1,0) model, based on root mean square error (RMSE), mean absolute error (MAE), and mean absolute percentage error (MAPE), outperformed both ARNN (1,1) and VAR (2) methods. The forecast of the ARIMA model showed an increase in South Africa's gold production, with a compounded annual growth rate (CAGR) of ∼0.6%. The model also predicted an increase in global gold production, with CAGR of ∼2.2%. The analyses of reserves–production trends showed that most South African mining companies have been depleting their gold reserves due to production and were minimally converting resources to reserves, averaging at ∼2%/year from 2017 till present. The minimal conversion may also reflect the challenging mining conditions (such as mining depths and underground flooding) and the mining industry's socio-political dynamics. We demonstrated that, if the resource–reserve conversion factor is maintained (at ∼2%/year and above), the forecasted production may sustain the current reserves (at > 2000 t Au excluding tailings) but deplete ∼27 % of the resources to reserves by 2040. However, if the conversion factor continues to decline (to <1 %), the forecasted gold production will reduce the reserves to < 500 t Au with ∼3% of the resources converted to reserves.

The effect of structural oil shocks on stock returns of Indian renewable energy companies across market conditions

Purpose This study aims to evaluate the structural oil shocks effect on stock returns of Indian renewable energy companies across market conditions. Design/methodology/approach This study applies the structural vector autoregression model to estimate sources of oil shocks such as oil supply shock, aggregate demand shock and oil price-specific demand shock. In the next step, the panel quantile regression model estimates the effect of these oil shocks on stock return across market conditions. Monthly data are collected from January 2009 to December 2019. All renewable energy companies listed on the National Stock Exchange of India are considered for the analysis. Findings In the whole sample analysis, this study finds that oil shocks negatively affect stock returns in most of the market conditions except oil price-specific demand shock. In sub-groups, oil shocks driven by supply and aggregate demand also negatively affect stock return in most market conditions. This study finds the positive interaction of oil price-specific demand shock. A majority of these positive interactions happen in bearish market conditions. In the whole sample, the asymmetric effects of shocks driven from oil supply and oil price-specific demand are seen in most quantiles or market conditions. At the same time, aggregate demand shock does not affect asymmetrically. In the sub-group analysis, standalone renewable energy companies stock returns are least asymmetrically affected by these oil shocks. The asymmetries of oil supply-driven shock on stock returns of the renewable energy sub-group companies are found in most quantiles. Originality/value First, this is a company-level study of the stock returns response to the structural oil shocks in the renewable energy sector. Second, to the best of the authors’ knowledge, this type of study is the first in the Indian context. Third using panel quantile regression model along with capital asset pricing model framework, the authors investigate these effects across market conditions.

The role of environmental tax on the environmental quality in EU counties: evidence from panel vector autoregression approach.

This study intends to analyze the influence of environmental taxes on pollution in EU-27 nations. Furthermore, energy from renewable sources consumption and urbanization are employed to clarify CO2 emissions in this study that tests the EKC hypothesis. According to the findings, an increase in environmental taxes reduces CO2 emissions by 0.14%. Also, the data supported the validity of the EKC concept. The findings of the causality test demonstrated that there is a bidirectional causal link between CO2 emissions and environmental taxes. These results reflect that environmental tax revenues contribute to sustainability as an effective policy tool in EU countries. Policies regarding environmental tax enforcement come to the fore in terms of both keeping the balance in economic activities and serving sustainability.

Systematic evaluation of integration between China's digital economy and sports industry: Two-stage grey relational analysis and vector autoregressive model.

The development of the digital economy constitutes a key component of China's endeavors to advance towards "Digital China." The sports industry functions as a new catalyst for high-quality economic growth. This study systematically evaluated the integration between these two sectors. First, we conducted two levels of grey relational analysis to assess their integration between 2016 and 2021. Second, we conducted a VAR analysis to determine whether their integration between 2009 and 2021 represents a causal relationship. At the macro level, the grey relational analysis reveals that the sports industry (grade = 0.770) ranked second among China's eight key economic sectors in terms of digital economy integration. At the meso level, a wide variation (ranging from 0.606 to 0.789) existed in the grade of integration between the digital economy and the sub-sectors of the sports industry. According to the VAR model, the digital economy does not Granger cause (p = 0.344) the growth of the sports industry. This study yielded two added values to the existing literature: First, there exists a sectoral imbalance in the digitization process; second, the explosive growth of the sports industry was not primarily caused by the digital economy. Accordingly, the "sports + digital" complex is still in the first wave of technological integration. We propose three policy recommendations, namely, sectoral synergistic development, overtaking via esports IP, and new economy and new regulation. Collectively, these findings provide updated insights for the digital transformation towards "building a leading sports nation" and "Digital China."

Semantic Segmentation for Change Detection in Satellite Imaging

Change detection is a common and actual problem in the field of remote sensing. The classical approaches using raw pixel information are very sensitive to noise. In this study we propose the usage of additional semantic information for change detection. We use the semantic segmentation methods like geospatial Segment Anything Model and encoder based U-Net to evaluate the predictions and tracing the semantic information as well as raw information in change detection. Later the multidimensional time series data is used via the Vector Autoregression model to predict the future changes in the landscape. The observations which fall out of the prediction interval are considered as the changes in the landscape. The proposed method is evaluated on the dataset of the random locations across the Baltic region. The research is accompanied by the data and reproducible code at Github repository.

Revisiting the role of climate change on crop production: evidence from Mediterranean countries

AbstractThe Mediterranean region is an important agricultural center and is expected to be most affected by climate change due to its location. In this study, the role of climate change on agriculture is examined for eight South European countries on the Mediterranean coast for the period of 1996–2016. Carbon dioxide emissions, temperature and precipitation values are used as the indicators of climate change while cereal production is taken as a proxy for agricultural production. Results of the panel vector autoregression approach reveal that an increase in the carbon dioxide emissions and temperature have a negative impact on the cereal production. However, this effect is statistically significant only in the initial periods. On the other hand, an increase in rainfall has a statistically significant positive effect on crop production only in one period. However, eventually this effect turns to negative as expected, since excessive rainfall has a negative effect on agriculture as much as drought. In conclusion, the importance of bringing the policies and strategies to the forefront in ensuring the sustainability of agriculture and minimizing the negative effects of climate change in the region are discussed.

Exploring inflation dynamics in Canada: A threshold vector autoregressive approach

Given the pivotal role of inflation expectations in contemporary monetary policy, we posit that if monetary policy has effectively influenced inflation expectations, thereby altering the trajectory of total inflation, a structural break in the path of total inflation should be observable. Conversely, if inflation expectations have remained stable and monetary policy has had limited impact, a stable vector autoregressive (VAR) model should adequately describe the path of total inflation. To address these hypotheses, a non-linear specification of a threshold vector autoregressive (TVAR) model is employed, offering a comprehensive analytical framework for the examination of these dynamics.

Machine learning-enabled weather forecasting for real-time radioactive transport and contamination prediction

Effective responses to nuclear accidents require accurate and fast predictions of radionuclide transport in the atmosphere. However, real-time forecasting has been challenging, since predicting the transport requires meteorological forecasting, which relies on computationally intensive numerical weather simulations. To address this challenge, we have developed statistical emulators for the Weather Research and Forecasting model (WRF) to forecast wind and temperature fields around the source location. The emulator is constructed based on pre-computed WRF simulation results and their boundary conditions from global circulation models (GCM), enabling the rapid prediction of local-scale wind/temperature fields by ingesting the GCM-predicted boundary conditions available online for the next several days. We have explored two methods: (1) deep neural network and (2) a vector autoregressive model with exogenous variables (VARX). A Gaussian plume model is then used to take these field as input and to predict the distribution of radioactive material/dose in the environment. The results show that both emulators are capable of forecasting the wind field for several days in the future in real-time, while not compromising accuracy. The autoregressive model has shown a strong performance of predicting the temperature field, owing to the strong temporal autocorrelations in the temperature data. This framework offers a powerful tool for informed decision-making during emergencies such as enabling meteorology-informed timing of containment venting, and real-time guidance of evacuation strategies.

Optimal Gasoline Price Predictions: Leveraging the ANFIS Regression Model

This study presents an in-depth analysis of gasoline price forecasting using the adaptive network-based fuzzy inference system (ANFIS), with an emphasis on its implications for policy-making and strategic decisions in the energy sector. The model leverages a comprehensive dataset from the U.S. Energy Information Administration, spanning over 30 years of historical price data from 1993 to 2023, along with relevant temporal features. By combining the strengths of fuzzy logic and neural networks, the ANFIS approach can effectively capture the complex, nonlinear relationships present in the data, enabling reliable price predictions. The dataset’s preprocessing involved decomposing the date into year, month, and day components to enhance the model’s input features. Our methodology entailed a systematic approach to ANFIS regression, including data preparation, model training with the inclusion of the previous week’s prices as an additional feature, and rigorous performance evaluation using MSE, RMSE, and correlation coefficients. The results indicate that incorporating previous prices significantly enhances the model’s accuracy, as reflected by improved scores and correlation metrics. The findings have significant implications for the energy sector, where stakeholders can leverage the ANFIS model’s insights for strategic decision-making. Accurate gasoline price forecasts are instrumental in devising pricing strategies, managing risks associated with price volatility, and guiding policy formulation. The model’s predictive capability enables energy companies to optimize resource allocation, plan for future investments, and maintain competitive advantage in a market influenced by fluctuating prices. Moreover, policymakers can utilize these predictions to assess the impact of energy policies on market prices and consumer behavior, ensuring that regulatory measures align with market dynamics and sustainability goals. In addition to the ANFIS model, we also employed Vector Autoregression (VAR) and Autoregressive Integrated Moving Average (ARIMA) models to validate our approach and provide a comprehensive understanding of time series forecasting within the energy sector. Notably, the ANFIS model achieves a score of 0.9970 and a robust correlation of 0.9985, demonstrating its ability to accurately forecast gasoline prices based on historical data and features. The integration of these traditional techniques with advanced ANFIS modeling offers a robust framework for accurate and reliable gasoline price prediction, which is vital for informed policy-making and strategic planning in the energy industry.

Effectiveness of hierarchical medical system and economic growth: based on China’s urban vs. rural health perspectives

BackgroundThe hierarchical medical system is an important measure to promote equitable healthcare and sustain economic development. As the population’s consumption level rises, the demand for healthcare services also increases. Based on urban and rural perspectives in China, this study aims to investigate the effectiveness of the hierarchical medical system and its relationship with economic development in China.Materials and methodsThe study analyses panel data collected from Chinese government authorities, covering the period from 2009 to 2022. According to China’s regional development policy, China is divided into the following regions: Eastern, Middle, Western, and Northeastern. Urban and rural component factors were downscaled using principal component analysis (PCA). The factor score formula combined with Urban–rural disparity rate (ΔD) were utilized to construct models for evaluating the effectiveness of the hierarchical medical system from an urban–rural perspective. A Vector Autoregression model is then constructed to analyze the dynamic relationship between the effects of the hierarchical medical system and economic growth, and to predict potential future changes.ResultsThree principal factors were extracted. The contributions of the three principal factors were 38.132, 27.662, and 23.028%. In 2021, the hierarchical medical systems worked well in Henan (F = 47245.887), Shandong (F = 45999.640), and Guangdong (F = 42856.163). The Northeast (ΔDmax = 18.77%) and Eastern region (ΔDmax = 26.04%) had smaller disparities than the Middle (ΔDmax = 49.25%) and Western region (ΔDmax = 56.70%). Vector autoregression model reveals a long-term cointegration relationship between economic development and the healthcare burden for both urban and rural residents (βurban = 3.09, βrural = 3.66), as well as the number of individuals receiving health education (β = −0.3492). Both the Granger causality test and impulse response analysis validate the existence of a substantial time lag between the impact of the hierarchical medical system and economic growth.ConclusionResidents in urban areas are more affected by economic factors, while those in rural areas are more influenced by time considerations. The urban rural disparity in the hierarchical medical system is associated with the level of economic development of the region. When formulating policies for economically relevant hierarchical medical systems, it is important to consider the impact of longer lags.

Volatility Spillover Benefits of the Hang Seng Index and Shanghai Composite Index: A Vector Autoregressive (VAR) Model and Granger Causality Test Analysis

This study aims to explore the volatility spillover benefits between two major stock markets in Hong Kong and Shanghai, namely the Hang Seng Index and the Shanghai Composite Index. Empirical analysis is conducted using a Vector Autoregressive (VAR) model and Granger causality test based on daily return data from 2013 to 2023. The research finds a significant volatility interaction between the Hang Seng Index and the Shanghai Composite Index, which is more pronounced during periods of global economic instability. Impulse response analysis reveals that positive shocks in Hang Seng Index lead to increased volatility in the short term for the Shanghai Composite Index but gradually weaken to a weak negative effect in the long term. Conversely, positive shocks in the Shanghai Composite Index have a short-term inhibitory effect on the Hang Seng Index but transform into a weak promoting effect in the long term. These findings have important implications for investors and policymakers in risk management, forecasting future stock market trends, and capital allocation.

Trends and Triggers: Analyzing the Co-Movement of Cryptocurrency and NFT Prices

This paper aims to explore the complex interrelationships between the prices of cryptocurrency, specifically Ethereum (ETH), and five top Non-Fungible Token (NFT) collections: Bored Ape Yacht Club, Mutant Ape Yacht Club, Azuki, Moonbirds, and Otherdeed. Motivated by the intertwining dynamics of these digital assets and the unexplored nature of their interdependencies, this study employs a Vector Autoregressive (VAR) model and utilizes Granger Causality to dissect the multifaceted interactions. The analysis period ranges from April 2021 to January 2023, a critical window of exponential growth and fluctuation in the digital asset market. The results demonstrate a statistically significant impact of ETH prices on NFT collection prices, but not vice versa, revealing the strong dependence of the NFT market on cryptocurrency volatility. Specifically, the research finds that changes in ETHs value are predictive of shifts in NFT prices, whereas NFT price fluctuations lack predictive power for ETH prices. In conclusion, this research represents an advancement in understanding price dynamics in the rapidly evolving digital economy. By innovatively analyzing the co-movement of cryptocurrencies and NFTs, it not only enriches existing knowledge but also paves the way for further exploration, offering practical insights for diverse stakeholders navigating this exciting, ever-changing field.

Machine Learning for Economic Forecast Based on Past 30 Years and Covid-19 Pandemic Data

Along the time, there are many forecasting techniques applied by researchers in various topics in Economics. Traditionally, some of the most popular time-series analysis model like Vector-autoregressive (VAR) are still widely applied in Economics forecasting topics since they can capture sufficient information for a dataset to predict. On the other hands, machining learning and deep-learning algorithm also shades a way for forecasting. In particular, algorithm like Gradient boosting, learning algorithm Long-short-term memory (LSTM) shows their tremendous accuracy when applying to Economic data. Covid-19 leads to one of the largest economic recessions in history in terms of intensity and time. In this article, some of the popular forecasting methods are applied to forecasting GDP data with the record from Covid-19. The empirical analysis is conducted for data in United states to compare the accuracy and divergency for various prediction algorithms. It turns out that machine learning algorithms are well performed in US cases where they generate relatively low forecasting error.

The time-varying dynamic impact of US renewable energy prices on agricultural prices in China: the case of fuel ethanol.

This paper intends to look into the time-varying dynamic impact of US fuel ethanol, one of the renewable energy sources, on the prices of agricultural products (specifically corn, soybeans, rice, and wheat) in China based on monthly price data from January 2000 to January 2023. To achieve this, a time-varying parameter vector autoregressive (TVP-VAR) model is employed, which takes into account structural changes in emergencies through time-varying parameters. The empirical results show that the equal-interval impulse responses of price fluctuations in agricultural commodities are primarily positive to variations in fuel ethanol prices and production. And the intensity and direction of the effects vary at distinct time lags. Additionally, the magnitude of these responses is most pronounced in the short term for all agricultural commodities except for corn, and the duration of the impulse responses at different time points is generally longer for corn prices compared to other commodities. The study also reveals that the influence of US fuel ethanol on Chinese agricultural commodity prices is not substantial on the whole. Therefore, there is a necessity to advance the growth of biofuels and provide policy support and financial subsidies for agricultural products earmarked for food production. These actions could shed insights into the progression of Chinese renewable energy and food policies, ensuring the stability of the market in the long run.

On the Validity of Granger Causality for Ecological Count Time Series

Knowledge of causal relationships is fundamental for understanding the dynamic mechanisms of ecological systems. To detect such relationships from multivariate time series, Granger causality, an idea first developed in econometrics, has been formulated in terms of vector autoregressive (VAR) models. Granger causality for count time series, often seen in ecology, has rarely been explored, and this may be due to the difficulty in estimating autoregressive models on multivariate count time series. The present research investigates the appropriateness of VAR-based Granger causality for ecological count time series by conducting a simulation study using several systems of different numbers of variables and time series lengths. VAR-based Granger causality for count time series (DVAR) seems to be estimated efficiently even for two counts in long time series. For all the studied time series lengths, DVAR for more than eight counts matches the Granger causality effects obtained by VAR on the continuous-valued time series well. The positive results, also in two ecological time series, suggest the use of VAR-based Granger causality for assessing causal relationships in real-world count time series even with few distinct integer values or many zeros.

Fiscal Policy, Government Ideology, and Economic Activity: Evidence from OECD Countries

AbstractThis study explores the role played by a country's political environment in the origin and effect of government spending. Using a rich data set that contains time‐varying ideological party positions, I show that both government ideology and the timing of elections are key determinants of government spending shocks and Granger‐cause government spending shocks estimated from traditional structural vector autoregressive (SVAR) models that ignore political considerations. I find that the magnitude of the spending multiplier depends on the political context: highly polarized countries have smaller multipliers relative to countries with a low degree of polarization, and established democracies have smaller multipliers than younger democracies.

The impact of fiscal shocks on economic growth and income inequality in Ghana: is there a trade-off?

PurposeThe study examines the impact of fiscal policy shocks on economic growth and income inequality in Ghana. This has become necessary because of the interdependence between growth and income inequality and the role fiscal policy plays in this relationship in the development process of a country. Thus, a study that investigates how government expenditure shock and tax revenue shock influence the relationship between economic growth and income inequality could assist policymakers to adopt the best policy mix to ensure income equity and sustained economic growth in Ghana.Design/methodology/approachIt employs sacrifice ratio from structural VAR model using quarterly time series data from 1996 to 2019 on Ghana.FindingsOur results show that government expenditure shock impacts economic growth, exchange rate and education positively and significantly in the long run. Also, tax revenue shock has a positive impact on income inequality, economic growth and education. The findings further show that there exists a trade-off between economic growth and income inequality in the long run.Originality/valueThe relationships between fiscal policy shocks, economic growth and income inequality have been extensively discussed among scholars. Understanding how these three macroeconomic variables are determined and their interrelationships are crucial for policymakers. This is because fiscal policy aids in both economic growth and income inequality. In the empirical literature, the emphasis has been on independently estimating the growth effects of fiscal policy or the distribution effects of fiscal policy, leaving out the existence of possible trade-off between economic growth and income inequality following a fiscal shock. To the best of our knowledge, no empirical study has been done on Ghana to empirically examine the trade-off between economic growth and income inequality as we do in this paper.

A new sample-size planning approach for person-specific VAR(1) studies: Predictive accuracy analysis.

Researchers increasingly study short-term dynamic processes that evolve within single individuals using N = 1 studies. The processes of interest are typically captured by fitting a VAR(1) model to the resulting data. A crucial question is how to perform sample-size planning and thus decide on the number of measurement occasions that are needed. The most popular approach is to perform a power analysis, which focuses on detecting the effects of interest. We argue that performing sample-size planning based on out-of-sample predictive accuracy yields additional important information regarding potential overfitting of the model. Predictive accuracy quantifies how well the estimated VAR(1) model will allow predicting unseen data from the same individual. We propose a new simulation-based sample-size planning method called predictive accuracy analysis (PAA), and an associated Shiny app. This approach makes use of a novel predictive accuracy metric that accounts for the multivariate nature of the prediction problem. We showcase how the values of the different VAR(1) model parameters impact power and predictive accuracy-based sample-size recommendations using simulated data sets and real data applications. The range of recommended sample sizes is smaller for predictive accuracy analysis than for power analysis.

Connectedness of cryptocurrency markets to crude oil and gold: an analysis of the effect of COVID-19 pandemic

The notion that investors shift to gold during economic market crises remains unverified for many cryptocurrency markets. This paper investigates the connectedness between the 10 most traded cryptocurrencies and gold as well as crude oil markets pre-COVID-19 and during COVID-19. Through the application of various statistical techniques, including cointegration tests, vector autoregressive models, vector error correction models, autoregressive distributed lag models, and Granger causality analyses, we explore the relationship between these markets and assess the safe-haven properties of gold and crude oil for cryptocurrencies. Our findings reveal that during the COVID-19 pandemic, gold is a strong safe-haven for Bitcoin, Litecoin, and Monero while demonstrating a weaker safe-haven potential for Bitcoin Cash, EOS, Chainlink, and Cardano. In contrast, gold only exhibits a strong safe-haven characteristic before the pandemic for Litecoin and Monero. Additionally, Brent crude oil emerges as a strong safe-haven for Bitcoin during COVID-19, while West Texas Intermediate and Brent crude oils demonstrate weaker safe-haven properties for Ether, Bitcoin Cash, EOS, and Monero. Furthermore, the Granger causality analysis indicates that before the COVID-19 pandemic, the causal relationship predominantly flowed from gold and crude oil toward the cryptocurrency markets; however, during the COVID-19 period, the direction of causality shifted, with cryptocurrencies exerting influence on the gold and crude oil markets. These findings provide subtle implications for policymakers, hedge fund managers, and individual or institutional cryptocurrency investors. Our results highlight the need to adapt risk exposure strategies during financial turmoil, such as the crisis precipitated by the COVID-19 pandemic.

Macroeconomic Impacts of Oil Price Shocks: Evidence from Iraq by Using Vector Autoregressive Model

Based on a VAR framework, Granger Causality Tests, Impulse Response Function and Variance Decomposition analysis on the annual data from 1970 to 2021, This study aims to demonstrate the effect of oil price fluctuations on GDP, imports, international reserves, and exports in Iraq. The Granger causality results demonstrated a unidirectional connection moving from oil price to imports, exports, international reserves, and GDP, this is an inevitable result because oil prices are determined in the international markets according to specific factors that do not include local economic variables. The variance decomposition result indicated that oil price changes are an important source of variation in the studied variables. Finally, the results of the impulse response function indicated that fluctuations in oil prices significantly impact GDP, exports, imports, and international reserves in Iraq. Therefore, we suggest that economic policymakers work seriously to develop practical plans to diversify the Iraqi economy instead of relying too heavily on oil revenues, which are characterized by sharp and continuous volatility, to avoid the negative effects of these fluctuations on the main macroeconomic variables in Iraq.