Vector Autoregression Research Articles

The role of uncertainty and sentiment for intraday volatility connectedness between oil and financial markets

We quantify intraday volatility connectedness between oil and key financial assets and assess how it is related to uncertainty and sentiment measures. For that purpose, we integrate the well-known spillover methodology with a TVP VAR model estimated on a unique, vast dataset of roughly 300 thousand 5 min quotations for most heavily traded financial assets: crude oil, the US dollar, S&P 500 index, gold and US treasury bonds. This distinguishes our investigation from previous studies, which usually employ relatively short samples of daily or weekly data and focus on connectedness between two asset classes. We contribute to the literature across three margins. First, we document that market connectedness at intraday frequency presents a different picture on markets co-movement compared to the estimates obtained using daily data. Second, we show that at 5 min frequency volatility is mostly transmitted from the stock market and absorbed by the bond and dollar markets, with oil and gold markets being occasionally important for volatility transmission. Third, we present evidence that daily averages of intraday connectedness measures respond to changes in sentiment and market-specific uncertainty. Interestingly, our results contrast with earlier findings, as they show that connectedness among markets decreases in periods of high volatility owing to market-specific factors. Our study points to the importance of using high-frequency data in order to better understand financial and commodity markets dynamics.

The dynamic effects of oil supply shock on China: Evidence from the TVP-Proxy-VAR approach

This study examines how changes in oil supply impact oil prices and China's macroeconomy. We developed an estimator that uses OPEC's institutional characteristics and high-frequency data to identify an oil supply surprise shock. This oil supply surprise is then incorporated as an exogenous variable into a TVP Proxy VAR model to analyze the effects of oil supply shocks on China's economy. Our findings indicate that negative oil supply shocks lead to higher oil prices, which in turn cause increases in China's interest rates and inflation, a decline in stock prices, a short-term rise in exports, and a long-term decrease in industrial output. When considering time-varying model parameters, we found that periods with larger oil supply shocks have a more pronounced impact on the macroeconomy. Our research provides empirical evidence for a better understanding of the effects of energy supply fluctuations.

Exchange Rate in Emerging Markets: Shock Absorber or Source of Shock?

This paper examines the stabilization role of flexible exchange rates for emerging economies within the Latin America and Asia regions. Based on a structural VAR model, we utilize zero, sign and exchange rate pass-through restrictions to identify structural macroeconomic shocks. Overall, we find that exogenous exchange rate shocks drive around half of total exchange rate fluctuations in emerging economies. Despite this predominant role, we find evidence that exchange rates do not act as a source of shocks to the real economy, but they instead absorb and reduce output growth and inflation volatilities. Based on counterfactual analyses, we further find that this shock-insulation property is highly shock-dependent, where the benefits of flexible exchange rates are sizable for demand and global monetary policy shocks, but are overall small in the face of supply shocks. Results also differ across time horizons, where the shock stabilization benefits are mainly limited to the short run for output, but also extend to the medium term for inflation. We also find that the net benefits of flexible exchange rates as a shock absorber are in general larger for emerging economies in Latin America than in Asia, particularly during crises periods. Finally, while we find that the stabilization role of exchange rates hinges upon the nature of underlying structural shocks, there is also a positive association with structural determinants such as a country's degree of exchange rate flexibility and trade openness.

China's monetary policy framework and global commodity prices

This paper examines the effects of China's monetary policy on global commodity prices over the quarterly period 1996:Q1–2021:Q4. Using a Bayesian Structural VAR model, we evaluate the impact of interest rate shocks (as a price rule) and shocks to the monetary aggregate (M2) (as a quantity rule) on those commodity prices. Our main findings are fourfold. First, a positive interest rate shock has a negative and persistent effect on commodity prices, with beverages and metals commodity prices falling the most in response to such shock. Second, a positive shock to the growth rate of M2 has a strong impact on the prices of non-fuel commodities, agricultural raw materials, and metals. Still, the highly volatile food and fuel (energy) commodity prices are less affected. Third, while both the growth rate of M2 and the interest rate seem relevant macroeconomic stabilizers, the quantity instrument appears more effective than the price instrument in explaining commodity prices. Finally, while interest rate hikes are linked with a persistent rise in world uncertainty, monetary expansions lead to a long-lived fall in this variable. All in all, our study provides new evidence about the impact of China's monetary policy on global commodity prices using a rich dataset and an econometric setup that accounts for uncertainty.

The efficiency assessment of using hybrid neural networks for the detection of forged audio data in socially oriented systems

The subject of the research is the problem of detecting falsified data, in particular in audio format, in socially oriented systems. The goal of the work is to develop an effective model based on recurrent and convolutional neural networks for determining the fact of forgery of sound data, using MapReduce technology for parallelization. The article addresses the following tasks: determining the features of audio in socially-oriented systems, conducting an analysis of algorithms for processing audio information both in the form of text and in the form of a signal, forming a list of target architectures of neural networks and revealing the features of their implementation, conducting an experimental test of effectiveness selected approaches. The following methods used are – analytical and inductive method for determining the target set of neural network architectures; expert assessment for the formation of the most influential efficiency factors; experimental, multi-criteria evaluation and statistical methods of data augmentation to determine the most effective model. The following results were obtained: an audio data reprocessing algorithm was developed for the possibility of using recurrent and convolutional networks. Several approaches to data classification using augmentation based on vector autoregression and MapReduce parallelization technology have been implemented. It was determined that the most effective model for the multi-criteria selection problem is a combination of a bidirectional recurrent neural network with support for short- and long-term memory with several convolutional networks. The advantages of using MapReduce technology to optimize training time and data processing are shown, and a set of open questions for further research and applied implementation is defined. Conclusions: he application of an analytical and inductive approach followed by experimental verification made it possible to develop an effective (with an accuracy of more than 96%) a mechanism for detecting fabricated data both in the form of a signal and in text form. The obtained result makes it possible to assert the feasibility of implementing the proposed approach, and, accordingly, makes it possible to reduce the influence of such information in socially oriented systems, especially during crisis events.

Economic Policy Uncertainty (EPU) in emerging countries: The case of Tunisia

Purpose: I aim to develop the first Economic Policy Uncertainty (EPU) indices for Tunisia covering the period from 2012 to 2022, using a methodology adapted from Baker et al. (2016). These indices assess the frequency of relevant terms in major Tunisian newspapers to gauge the level of economic policy uncertainty. Additionally, I investigate the impact of EPU on economic activity. Design/Methodology/Approach: This study employs a textual analysis methodology and a Web-scraping algorithm to compute the news-based EPU indices. Additionally, using a VAR (Vector Autoregression) methodology and impulse response functions, the study examines the dynamic relationship between EPU and key macroeconomic variables, including GDP, consumption, industrial production, and the unemployment rate. Findings: The results reveal that increases in EPU significantly predict declines in GDP, consumption, and industrial production, while positively correlating with the unemployment rate. Furthermore, monetary policy uncertainty emerges as the most influential factor contributing to EPU. Implications/Originality/Value: These findings underscore the importance of clear and consistent policy frameworks in mitigate uncertainty and enhancing economic performance in emerging economies like Tunisia.

PRICE DYNAMICS OF FOSSIL FUEL COMMODITIES IN THE PERIOD 2014 - 2024

Over the last decade, the dependence on fossil fuels and their prices has been increasingly discussed. This paper aimed to assess the development of fossil fuel prices and their relationship to GDP in the Czech Republic. To achieve this objective, a VAR model and Granger causality test were used. All fossil fuel prices peaked in 2022. The causal relationship with GDP in the Czech Republic was confirmed for natural gas and coal prices. On the other hand, the causal relationship between oil and GDP in the Czech Republic was not confirmed during the period under study. Weak correlations were found with the Covid-19 pandemic, inflation, and unemployment in the EU. The only exception is the correlation between coal and inflation in the EU, which was moderately strong. A limitation of the paper is the length of the period studied, with data collection taking place only once a month.

The short-term effects of changes in capital regulations in Poland

In this study I attempt to address two questions. First, how to adequately measure capital regulations. Second, once they are adequately measured, what their effects are in Poland. As the starting point, I illustrate the threats of measuring capital regulations by actual regulatory capital ratios. Then, I analyse the effects of the transition to higher actual regulatory capital ratios due to the tightening of capital regulations. As a measure of capital regulations, I directly use minimum regulatory capital ratios. I apply Bayesian panel vector autoregressive models and local projections to bank-level data. I find that the tightening of capital regulations lowers bank lending for at least one out of two analysed minimum regulatory capital ratios. This implies that capital regulations could be an effective prudential policy tool in limiting excessive bank lending in Poland. I also attempt to identify whether the effects of changes in capital regulations depend on whether they are tightened or loosened.

Economic Resilience: Evidence for African Economies Application of a Panel Var Model

A panel VAR model was applied to analyse the economic resilience of 54 African countries from 1990-2022. Realising how exogenous shocks influence countries’ ability to respond from the outset is naturally the aim of the study. Thus, the results suggest that there is a significant presence of economies based on international market expectations, which are significantly explained by the presence of exogenous shocks. On the other hand, the Impulse Response Functions help to explain the fact that 90% of African countries have economies controlled by international market expectations, which, in the presence of exogenous international market shocks, end up determining the path and behaviour of economies in the medium term. On the other hand, the results show that countries such as Botswana, South Africa, Namibia and Ghana have a greater capacity to respond in a context of uncertainty, and there are strong reasons to suggest that these countries are able to control their economies, unlike, for example, the results for Angola in a context of uncertainty, Democratic Congo and Brazzaville, Equatorial Guinea and Sierra Leone, the evidence nevertheless shows that in a context of uncertainty, exogenous shocks control and determine the economic path in the long term. These results also suggest that these economies should be characterised as economies without control by the authorities. Thus, as exogenous shocks increase, there are significant increases in the destructive capacity of these economies.

Impact of tax changes on the risk premium of the WIG index

The presented article provides an empirical analysis of changes in the risk premium of stocks on the Warsaw Stock Exchange in response to changes in tax rates. The analysis uses a structural VAR model, identified with sign restrictions. This method turns out simple to use and proves to be effective in overcoming the problem of predictability of fiscal policy, which is especially important in studies using variables from financial markets. The results show an increase in the risk premium following a sudden tax hike, accompanied only by a temporary reduction in GDP growth. Meanwhile, an anticipated tax hike seems to lower risk premia while being more harmful to GDP dynamics.

Bayesian varying‐effects vector autoregressive models for inference of brain connectivity networks and covariate effects in pediatric traumatic brain injury

AbstractIn this article, we develop an analytical approach for estimating brain connectivity networks that accounts for subject heterogeneity. More specifically, we consider a novel extension of a multi‐subject Bayesian vector autoregressive model that estimates group‐specific directed brain connectivity networks and accounts for the effects of covariates on the network edges. We adopt a flexible approach, allowing for (possibly) nonlinear effects of the covariates on edge strength via a novel Bayesian nonparametric prior that employs a weighted mixture of Gaussian processes. For posterior inference, we achieve computational scalability by implementing a variational Bayes scheme. Our approach enables simultaneous estimation of group‐specific networks and selection of relevant covariate effects. We show improved performance over competing two‐stage approaches on simulated data. We apply our method on resting‐state functional magnetic resonance imaging data from children with a history of traumatic brain injury (TBI) and healthy controls to estimate the effects of age and sex on the group‐level connectivities. Our results highlight differences in the distribution of parent nodes. They also suggest alteration in the relation of age, with peak edge strength in children with TBI, and differences in effective connectivity strength between males and females.

Maintaining Sustainable Public Finances: The Role of Fiscal Consolidation

Maintaining Sustainable Public Finances: The Role of Fiscal Consolidation

Green horizons: Enabling the energy transition through climate change policies

In response to the goals set by the COP21 Summit, the challenges brought about by the COVID-19 pandemic, and the ongoing conflict between Russia and Ukraine, this study aims to develop an effective policy framework to support the transition to sustainable energy. This framework considers key elements such as managing energy risks, leveraging green finance, navigating carbon markets, and evaluating three climate change policy indicators: the impact of climate change summits (CCS), government climate programs (CCGP), and climate change taxation (CCT). Utilizing the Quantile Vector Autoregressive (QVAR) approach and analyzing monthly data from the United States from August 1, 2014, to August 30, 2022, our research examines the influential role of these climate policy indicators. The results show that climate summits, governmental initiatives, and climate taxes are significant influencers, affecting both renewable and conventional energy sectors, carbon market movements, and green finance. The study underscores the importance of government initiatives and climate policies in driving the transition to renewable energy and fostering environmentally sustainable financial activities. Focused on advancing Sustainable Development Goals 7 (Affordable and Clean Energy) and 13 (Climate Action), this research contributes to shaping effective policy frameworks and enriching policy debates on sustainable energy transition.

Volatility and returns connectedness between cryptocurrency and China’s financial markets: A TVP-VAR extended joint connectedness approach

We employ a time-varying parameter vector autoregression (TVP-VAR) joint connectedness approach to study the dynamic risk spillover effects between cryptocurrencies and China’s financial market, further exploring the impact of cryptocurrencies on China’s financial market. Our results show that there is asymmetric risk transmission between cryptocurrencies and China’s financial market, and the risk spillover effect is very weak. Specifically, the spillover of cryptocurrencies to China’s financial market is significantly stronger than the spillover of China’s financial market to cryptocurrencies. Cryptocurrencies have a stronger spillover effect to China’s exchange rate and gold. The net spillover effect of cryptocurrencies is weakening over time. Overall, the return spillover impact of cryptocurrencies on China’s financial market is greater than the volatility spillover impact, and the degree of impact of different cryptocurrencies is heterogeneous. The findings of this study have several implications for policymakers and investors.

Offshoring, firm-level adjustment and labor market outcomes

This paper studies how the China shock affects unemployment rates and wage inequality across high-skilled and low-skilled workers in the United States, with particular emphasis on the dynamic and general equilibrium channels of firms' production locations and entry decisions. To shed light on the subject, I build a two-country trade-in-task model with firm heterogeneity, search-and-matching labor market frictions, and firms' endogenous selections into entry and offshoring. The model, consistent with evidence from vector autoregression analyses, uncovers important dynamics with implications for the impact of the China shock on U.S. worker inequality. Namely, it shows association between a decrease in offshoring costs and a short-lived increase in low-skilled unemployment in the source country, a longer-term decline in high-skilled unemployment, a transient expansion of the wage gap between high- and low-skilled workers, and an increase in firm entry.

Risk Premium and Fear of Investors in Crisis’ Periods: An Empirical Approach Based on Fama–French and Carhart Factor Models

This study aims to answer the question about the interactions between “investors’ fear”, two factors proposed by Fama & French, the Carhart momentum factor, andthe risk premium, and how these interactions were affected by two financial crises, the Dot-Com and Sub-Prime crises. This paper is the first empirical study that considers the effects of these financial crises. It is of critical importance as it changes the specificity of the empirical models for different periods, significantly affecting the results compared to previous research work. The main findings include a general negative change in fear over all of the sub-periods. Secondly, no consistent positive trend was observed in any of the risk premiums over time. After each crisis, the relationships between the endogenous variables had significant changes. More specifically, investors’ fear, on the first day of the week, appears to be systematically higher across all sub-periods except during the Sub-Prime crisis. Finally, after the Sub-Prime financial crisis, there is an almost complete loss of the explanatory power of the VAR models. Although fear does not seem to affect risk premiums or momentum, it was nevertheless found that the results are sensitive to the specification of the models.

Traffic flows time series in a flood-prone area: modeling and clustering on extreme values with a spatial constraint

AbstractTime series of traffic flows, extracted from mobile phone origin–destination data, are employed for monitoring people crowding and mobility in areas subject to flooding risk. By applying a vector autoregressive model with exogenous covariates combined with dynamic harmonic regression to such time series, we detected the presence of many extreme events in the residuals, which exhibit heavy-tailed distribution. For this reason, we propose a time series clustering procedure based on tail dependence which is suitable for data characterized by a spatial dimension, since objects’ geographical proximity is taken into account. The final aim is to obtain clusters of areas characterized by the common tendency to the manifestation of extreme events, that in this case study are represented by extremely high incoming traffic flows. The proposed method is applied to the Mandolossa, a strongly urbanized area located on the western outskirts of Brescia (northern Italy) which is subject to frequent flooding.

Effect of fuel prices on sailing speeds in short-sea shipping

ABSTRACT In this paper, we estimate fuel price elasticities of sailing speed for general cargo vessels using data covering the Baltic Sea and Norwegian coastal areas during the years 2007–2018. To disentangle the correlation between fuel prices and freight rates arising from changes in global demand, we instrument fuel prices on price changes triggered by supply shocks. The shocks are derived from the structural vector autoregressive (SVAR) model proposed by Kilian (2009). In a sensitivity analysis, we use unanticipated oil supply shocks derived from oil supply outages as an alternative instrument for fuel prices. We find that disregarding the correlation between fuel prices and freight rates yields biased parameter estimates, which can partly explain the mixed results in the previous literature. Our preferred estimate for the fuel price elasticity of speed is −0.08.

Implementation of the Vector Autoregressive (VAR) Model in Electricity Supplier Companies

The government's policy regarding setting special prices for coal as fuel for power plants is a dilemma for investors because if the policy is implemented there is a possibility that it will affect the company's profitability and impact the company's share price. Scientific forecasting of a company's future based on share price volatility with various considerations including political, social and economic aspects of the country are things that must be taken into account when making decisions. The method that will be used in this research is quantitative descriptive through the application of the VAR model to be able to describe the causal relationship between variables. The result is a VAR model for each variable that is used as a forecasting model for the daily share price volatility of companies supplying coal to PLN, so that investors can make strategic steps in investing.

Did COVID‐19 induce a reallocation wave?

AbstractWe critically examine the hypothesis that COVID‐19 has ushered in a large reallocation shock in the USA, beyond typical business cycle patterns. We take a broad perspective, and first consider data from the CPS and JOLTS; there is no noticeable uptick in occupation or sector switches, either at the aggregate level or in the cross‐section. The dispersion of sectoral growth rates over the three years before the pandemic was similar to the previous period. The recovery from the initial shock was characterized by very high quits and low layoffs, patterns indicative of a strong labour market, not excessively high reallocation relative to previous business cycles. High growth of small employers in the recovery, and larger ones once the labour market tightened, is also a common cyclical pattern. We then examine whether mismatch unemployment rose as a result of the pandemic; using an off‐the‐shelf multisector search and matching model, there is little evidence for an important role for mismatch in driving the unemployment rate during the pandemic. Finally, we employ a novel Bayesian Structural Vector Autoregression framework with sign restrictions to identify a reallocation shock; we find that it has played a relatively minor role in explaining labour market patterns in the pandemic, at least relative to earlier episodes.