Cointegrated Vector Autoregression Research Articles

Exploring price level trajectory in India: Does it validate the fiscal theory of price level?

The fiscal policy’s impact on the price level is theorized as the Fiscal Theory of Price Level (FTPL) and has been popularized since the 1980 s. Developing countries often face the problem of prolonged deficits in fiscal management and depend on public debt. Studies on the FTPL in these countries are pertinent but scarce. This paper explores the price level trajectory in the Indian economy for 1985–2019 on the premise of FTPL. Empirical assessment involves both fiscal variables (deficit, debt, public spending) and money supply. The results of the cointegrated vector autoregression model followed by an impulse response analysis reveal that fiscal deficit stimulates the price level, while public spending has a stabilizing impact. Public debt is rather inflationary, but its impact is not robust. Besides, the money supply amplifies the price level. In the price level trajectory, neither the fiscal dominance nor the monetary dominance, that is, indeterminacy, is ascertained. The proactive role of fiscal and monetary policies in the price level trajectory suggests that if the Reserve Bank of India’s stance on price-level stabilization is abreast, the fiscal authority might accomplish the appropriate strategy.

Price discovery and long‐memory property: Simulation and empirical evidence from the bitcoin market

AbstractPrice discovery studies of a single asset traded in multiple markets have traditionally focused on assessing the relative price discovery contribution of each market. However, in this paper, we demonstrate that the overall price discovery across all markets can undergo changes even when the relative price discovery of each market remains constant. We propose that this overall change in price discovery can be effectively captured by the fractional parameter in the fractionally cointegrated vector autoregressive (FCVAR) model. In contrast, the widely used cointegrated vector autoregressive (CVAR) model fails to account for this dynamic in overall price discovery. Through a combination of simulation exercises and empirical applications, we show that the FCVAR approach outperforms the CVAR model not only in evaluating the relative price discovery contributions but also, more importantly, in providing a comprehensive measurement of overall price discovery.

Investigating the Long-Run Sectoral Growth Linkages in Ethiopia: Is Agriculture or Service an Engine of Growth?

This paper investigates the long run relationship between agriculture, industry and service using cointegrated vector autoregressive (CVAR) methodology for the period 1981-2011. Using this approach, the article provides a fresh evidence for Ethiopia that has not been deployed by the previous researches in the country. The paper finds that service is a driving force of the growth of agriculture and itself, an evidence obtained from analysis of the long run impact matrix C. From the fully identified long run structure, growth in service has positive and significant impacts on agriculture and industry. It deeply investigates the effects on agriculture by disaggregating service into other service and distributive service whereas industry comprises manufacturing and non-manufacturing. Concerning the impacts of disaggregated service, other service sub-sector is found to be a pushing force for the growth of agriculture, non-manufacturing and service itself. A variable comprising transportation and communication is vital for the long term growth of agriculture. These results are robust to changes in sample size and sample source. The policy prescription is that government should invest on this small sub-sector as the returns to the whole economy are tremendous.
 The paper finds positive and strong effects from non-manufacturing to manufacturing reflecting that improved access to electricity, gas and water triggers unprecedented growth in manufacturing productivity. Finally, a shock to agriculture has little impacts on the growth of entire economy as the variable is purely adjusting in most of the models considered in the paper while aggregate service is weakly exogenous.

Energy price volatility affects decisions to purchase energy using capital: Motor vehicles

I investigate how energy price volatility affects consumer decisions to purchase durable, energy using capital, motor vehicles. A cointegrating vector autoregression (CVAR) model indicates that; (1) high price volatility reduces the negative effect of motor gasoline prices on monthly purchases of motor vehicles, (2) consumers consider passenger cars to be an inferior good and this drives the substitution of light trucks for passenger cars, (3) the own price elasticity of demand for vehicles is about −0.3, which is consistent with estimates used to justify The Safer Affordable Fuel-Efficient (SAFE) Vehicles Rule for Models Years 2021–2026 Passenger Cars and Light Trucks. Simulating the CVAR model indicates that implementing an energy tax rapidly or during a period of low price volatility has a greater effect on motor vehicle sales than implementing the same tax slowly or during a period of high price volatility. Together these results suggest that more research should focus on how energy price volatility affects consumer decisions to purchase energy using capital.

More Accurate Climate Trend Attribution by Using Cointegrating Vector Time Series Models

Adapting to human-induced climate change is becoming an increasingly important aspect of sustainable development. To be able to do this effectively, it is important to know how much human influence has contributed to observed climate trends. Climate detection and attribution (D&A) studies achieve this by estimating scaling factors usually obtained by performing a least squares regression of the observed trending climate variable on the equivalent variable simulated by a climate model. This study proposed instead to estimate scaling factors by using the econometric approach of dynamically modelling the time series as a cointegrating Vector Auto-Regressive (VAR) time series process. It is shown that a 2nd-order cointegrating VAR(2) model is theoretically justified if the observed and simulated variables can be represented as a one-box AR(1) response to a common integrated forcing. The VAR(2) model can be expressed as a Vector Error-Correction Model (VECM) and then fitted to the data to obtain the cointegration relationship, the stationary linear combination of the two variables, from which the scaling factor is then easily obtained. Estimates of the scaling factor from the VAR(2) model are critically compared to those from Ordinary Least Squares (OLS) and Total Least Squares (TLS) for annual Global Mean Surface Temperature (GMST) data simulated by a simple stochastic model of the carbon–climate system and for historical simulations from 16 climate models in the Coupled Model Intercomparison Project 5 (CMIP5) experiment. Results from the toy model simulations show that the slope estimates from OLS are negatively biased, TLS estimates are less biased but have high variance, and the VAR(2) estimates are unbiased and have lower variance and provide the most accurate estimates with smallest mean squared error. Similar behaviour is noted in the CMIP5 data. Hypothesis tests on the VAR(2) fits found strong evidence of a cointegrating relationship with the observations for all the CMIP5 simulations.

A learning by doing multiplier accelerates the transition to photovoltaic cells

Abating emissions of carbon dioxide depends in part on how quickly the levelized cost of electricity (LCOE) from photovoltaic cells (PV) achieves grid parity without policy interventions. Reaching this threshold is accelerated by learning by doing, which reduces the LCOE generated by PV. The resultant cost reduction generates a positive feedback loop and increases the demand for PV; but previous analyses ignore this feedback and therefore overlook a critical learning by doing multiplier effect, in which increasing the cumulative production of PV modules lowers their price, and lower PV module prices increase purchases of PV modules, which increases cumulative production of PV modules, and so on. We quantify the learning by doing multiplier effect with a cointegrating vector autoregression (CVAR) model that captures the simultaneous relation between the price for and cumulative production of PV modules. The learning by doing multiplier effect amplifies the static effects of learning by nearly a factor of ten and eliminates the simultaneous equation bias in previous estimates of unidirectional learning curves. This multiplier effect enhances the ability of policies, such as a carbon tax, to lower the costs of PV, increase cumulative production, and lower carbon emissions. Together, these results suggest that grid parity is closer than indicated by unidirectional learning curves.

Price Analysis in the European Food Supply Chain

The paper assesses the degree of price cooperation between the main agricultural supply chain stakeholders in EU-27. The price transmission mechanism between producers and retailers is used for assessing cooperation. Cereals prices of EU-27 are used for the empirical analysis (January 1995 - April 2022). The price mechanism is modeled via the Co-Integrated Vector AutoRegressive (VAR) representation. The empirical analysis follows the usual drill of stationarity and co-integration tests followed by Granger Causality tests, Impulse Responses and Forecasts of Error Decomposition. The results show restricted cooperation between supply chain stakeholders.
 
 JEL Classifications: Q13, Q18
 
 Keywords: Price analysis, European Union - 27, supply chain management

A memory in the bond: Green bond and sectoral investment interdependence in a fractionally cointegrated VAR framework

The urgency surrounding environmental sustainability has triggered an innovation of financing channels for climate and environmental projects. Green bond as one such channel has garnered immense interest from investors, with an implicit view that this fixed-income instrument is a relatively safer choice as an investment portfolio. Yet, the uncomfortable spread of greenwashing as a marketing spin has subjected green bonds to significant market volatility, at least as much as other financial assets or sectoral indices if not more. Whether green bonds as a financial instrument may incur losses to the extent of the loss in various sector indices, can be gauged by studying the nature of their contemporaneous growth. In this paper, we use daily data on green bonds and several S&P sectoral indices and a fractionally cointegrated vector autoregression framework (FCVAR) to study the extent to which green bonds dynamically co-move with various sectoral indices. Such a co-movement, if any, would elicit the extent to which a variation of uncertainty would determine an investor’s inclination to the diversification of a portfolio between an investment in a sectoral index and a green bond. The identifying mechanism is the shock-dissipation speed, which also informs a policymaker before choosing the right instrument to stabilise the system. We show that the system-wide shocks indeed dissipate slower than could be predicted by a conventional cointegrated VAR system. Further, the property of the slow error correction within the dynamic system of Green Bond and sectoral S&P indices, for instance, may demonstrate the speed of adjustment of the global economy to sudden shocks. Rigorous predictions exercises complement our baseline conclusions.

Impact of Internationalization on Human Development: A Comparative Analysis of Mexico and France, 2000–2019

The objective is to determine the relationship between the openness of markets and human development in Mexico and France for the period 2000–2019. A comparative analysis is carried out by looking at the effect of migration (measured by the inflow of remittances) and the opening of capital markets and trade on the Human Development Index in both countries. Estimations are based on a Cointegrated Vector Autoregressive model. Results show that Foreign Direct Investments has a positive influence on HDI in both countries, but remittances seem to contribute more to human development, in Mexico, than trade and capital liberalization do.

The power of investors’ optimism and pessimism in oil market forecasting

By modelling dynamism in the global oil market by three essential market-centric observables (viz., Market Expansion, Market Regime, and Market Liquidity), we study forecasting potential of the future oil markets within a memory-driven interdependence setting. We combine spot prices with our derived market proxies to produce representative global market proxies. The latter are used to quantify the extent of static and dynamic persistence within the system. Our extensive empirical investigation exploits the rich features of fractionally cointegrated vector autoregression, where the rate of disequilibrium error correction within the system is modelled to be slow, approximating real life system dynamics. An advantage is that it explains why we often experience a slow response of a policy intervention. We present robust evidence of both system-wide long-memory and a long-memory in the market-centric observables. We introduce a memory of memory estimation to discern the magnitude of the relative rate of acceleration/deceleration of shocks within each observable, which reflects on the overall stability of the system. Our results show significant degree of non-linear error dissipation and high degree of informational inefficiency. Rigorous out-of-sample forecasting exercise produces robust predictions and demonstrate superiority of our approach.

Fractional cointegration and price discovery in Canadian commodities

Using as a unifying theme commodities important to the Canadian economy, recently developed tools are applied to studying price discovery in the spot and futures markets. For each commodity the fractionally cointegrated vector autoregression (FCVAR) model of Johansen and Neilsen is estimated and tested against the special case of the conventional cointegrated vector autoregression (CVAR). These models characterize the fundamental value of a commodity as the common stochastic trend shared by its cointegrated spot and futures prices, and so price discovery can be analyzed using the permanent-transitory decomposition of Gonzalo and Granger. Model forecasts are evaluated and compared using a distributional result due to Clark and West. The generalization to fractional cointegration is found to be statistically significant. However the economic significance of this generalization—in terms of forecast accuracy and the profitability of mean–variance dynamic trading strategies—is more fragile than may have been appreciated.

Do Chilean imports lead prices in the EU mussel market?

The impact that added competition of imported mussels from Chile might have had on market prices is one of the main reasons given to explain the decrease in the economic performance of the mussel aquaculture sector in the European Union (EU) in the last two decades. This hypothesis has not yet been tested. In this article we test empirically for price leadership and market integration in the EU mussel market. We estimate a cointegrated vector autoregressive (CVAR) model for the French, Italian, and Spanish mussel import markets and test for price leadership. The results indicate that the import prices of Chile, Belgium, Spain, Ireland, Italy and the Netherlands are determined within a fully integrated market, so prices are proportional over time. All countries follow the lead of Chilean mussel prices in the French market, which are on average among the lowest of the main importers in this market. These results support the opinion that added competition from Chilean mussels may have contributed to the low prices in the EU market.

Trajectories to high income: Comparing the growth dynamics in China, South Korea, and Japan with cointegrated VAR models

We analyze and compare the patterns of economic growth and development in China, South Korea, and Japan in the post-war period. The geographical proximity and cultural affinity between the three countries, as well as the key role of the development state in their economies, suggest that an analytical comparison would be a meaningful and valuable exercise. Furthermore, South Korea and Japan are two of the few economies that have jumped from middle income to high income in a short period and thus offer potentially valuable lessons for China. We use Cobb–Douglas production functions to assess the long-run equilibrium relationships between per capita GDP, capital, and labor by means of cointegrated vector autoregressive (CVAR) models. We show that such equilibrium relationships cannot be rejected for all three countries, while the evidence is stronger for China and South Korea than for Japan. Our hypothesis tests show that the estimated Cobb–Douglas production functions display coefficients of capital and employment that sum up to 1 and broken linear trends that can be attributed to structural breaks and (changes in) total factor productivity (TFP) growth. We observe a striking similarity between the experience in South Korean and China, which gives some optimism that the China may be capable of graduating to high income, like South Korea.

Escape underway: Malthusian pressures in late imperial Moscow

Did late Imperial Russia suffer from Malthusian pressures? At first glance, with its rising levels of population and per capita income, it seems Russia was in a transition away from Malthusian equilibrium. However, the joint increase in population and per capita income could also have been the result of Russia’s high land-to-labor ratio. Which of the two is it? Such a problem is a frequent one in economic history, as many frontier economies have high land-to-labor ratios, which foil the researcher’s ability to determine whether an economy was transitioning or whether it was growing because of weak land constraints. In this paper, we use quarterly demographic and economic data from Moscow (which we take as a proxy for Russia) in conjunction with a Cointegrated Vector Autoregression approach to determine whether the Russian economy was transitioning away from a Malthusian equilibrium. We find signs of Malthusian pressures still operating while wages had stopped responding to changes in death and birth rates. This combination suggests that a vulnerable transition was truly underway even though a Malthusian shadow remained.

Trade friction and price discovery in the USD–CAD spot and forward markets

This paper examines the impact of trade friction on price discovery in the USD–CAD spot and forward markets. Using the recently developed fractionally cointegrated vector autoregressive (FCVAR) model, we investigate how the foreign exchange spot and forward markets respond to trade friction. We consider two major trade friction events: the United States–Mexico–Canada Agreement and the recent trade friction between Canada and China. Both events show that the forward market plays a dominant role in price discovery, and the influence of the forward market increases as trade tension increases. By comparing the fractional and non-fractional models, we find that the fractional model fits the data better and has superior forecasting performance to the cointegrated vector autoregressive (CVAR) model.

Fractional cointegration between gold price and inflation rate: Implication for inflation rate persistence

In this study, we employ a recently developed Fractional Cointegrating Vector Autoregressive (FCVAR) model to analyze the relationship between gold price and inflation rate, to determine the responsiveness of inflation rate persistence of the selected countries to gold price shocks. Our analyses cover two decades; ranging from January 2001 to December 2019. We also account for country heterogeneity; specifically, due to variation in countries’ level of development, income level, and monetary policy framework. Our results suggest that the effect of gold price shock lingers for a long time on inflation rate persistence of developing countries, and for a short time on inflation rate persistence of developed countries. We also find that a higher level of income is associated with lower gold price – inflation rate cointegrating persistence, but the possibility of high-income countries having higher gold price – inflation rate cointegrating persistence than low-income countries cannot be dispelled. We also find that adoption of inflation targeting monetary policy reduces gold price – inflation rate cointegrating persistence and that gold price – inflation rate cointegrating persistence is higher under limited or intermediate floating exchange rate arrangement than under free-floating and currency peg arrangement.

Did OPEC change its behaviour after the November 2014 meeting?

We analyse the behaviour of OPEC as a group by formulating a theoretical model that encompasses the perfect competition model and various forms of the imperfect competition model. By confronting the theoretical model with quarterly data for the period from 1992 to 2013 within the context of a cointegrated vector autoregressive (CVAR) model, we find support for the imperfect competition hypothesis regarding the output decisions of OPEC. We also find that a dynamic equilibrium correction model with imperfect competition is stable in-sample. However, a forecasting exercise for the period from 2014 to 2018 reveals that the model breaks down following the November 2014 meeting at which OPEC decided to keep its supply unchanged despite the huge oil price drop in advance. The model systematically underpredicts OPEC production over the forecast period and by as much as 2.5 million barrels per day at the end of 2016. During 2018, however, the model forecasts OPEC production quite well. Our findings suggest that the behaviour of OPEC did indeed change significantly after the November 2014 meeting.

Gold and silver prices, their stocks and market fear gauges: Testing fractional cointegration using a robust approach

The present paper investigates the long-run relationships between daily prices, stocks and fear gauges of gold and silver by employing an updated fractional cointegrating framework, that is, the Fractional Cointegrating Vector Autoregression (FCVAR). The initial unit root tests results indicate that the series are I(d)s with values of d around 1 in all cases, and these are homogenous in the paired cointegrating series. Evidence of cointegration is found in the three pairs (prices, stocks and market gauge indices), while these cointegrations are only time-varying in the case of market gauge indices for the commodities. The fact that cointegration exists in prices and stocks of gold and silver implies the possibility that gold and silver prices and stocks can interchangeably be used to access the performances of the commodity markets, with the recommendation that the two commodities are not to be traded in the same portfolio.

Revealing unnoticed properties of super exogeneity in a cointegrated vector autoregression

This study provides a basis for super exogeneity possessing further valuable implications which have not been clarified yet in preceding research. The relevance of super exogeneity to S-ancillary statistics is reexamined from a theoretical viewpoint, and it is then argued that the small-sample precision of statistical inference for cointegrating parameters can be improved by conditioning on a class of super exogenous variables. Monte Carlo experiments are conducted to verify the theoretical argument. An empirical analysis is also performed as a demonstration of the practicality of the argument.

The environmental consequences of blockchain technology: A Bayesian quantile cointegration analysis for Bitcoin

AbstractIn recent years, there is a widespread belief among researchers and academicians that Bitcoin usage is imposing an additional burden on the environment inducing climate change. Although several studies have focussed on issues related to the energy consumption of the basic cryptocurrencies, an open question remains regarding the environmental depiction of Bitcoin. By resorting to Bayesian analysis and quantile cointegrated vector autoregression (CQVAR), this study seeks to disentangle the driving forces that shape the carbon footprint of Bitcoin. The sample used in the empirical analysis consists of a daily panel dataset covering 50 countries over the period 2016–2018. The empirical findings corroborate a causal effect between the use of Bitcoin and its underlying carbon dioxide emissions generated by the increasing energy load. The CQVAR is associated with positive marginal posterior means for most of the covariates of the model across all the estimated quantiles. In contrast, there is a negative and statistically significant relationship between Bitcoin miner's revenue and carbon emissions, uncovering a multimodal distribution pattern of the marginal posterior densities which is stronger at higher than in lower quantiles. This finding suggests that the lower (higher) miner's Bitcoin revenues, the more abrupt (gradual) the effect on environmental degradation. Therefore, a sustainable energy strategy focussing on the penetration of renewable energy sources along with the use of energy‐efficient mining hardware will alleviate the carbon footprint of Bitcoin.