Standard VAR Research Articles

Revisiting the Nexus Between Oil Prices and Economic Activity for Asian Economies Using MIDAS

The objective of this paper is to re-examine the causal relationship between oil prices and economic activity for five Asian economies. We apply the unrestricted MIDAS (U-MIDAS) model using monthly data for real oil prices and quarterly data for real GDP for the period from 1998Q1 to 2019Q4. The causal nexus between oil prices and economic activity is also studied by means of wavelet analysis to investigate whether the relationship between the variables changes over different time scales. The key empirical results under the MIDAS approach show that there is a clear significant causal link from oil prices to economic activity, which is not as clearly found under the standard VAR approach. In addition, our results using impulse response functions suggest that the five Asian economies respond, in general, positively in economic activity to an oil price shock at shorter time horizons (less than two years), while the positive responses switch to mostly negative ones at longer time horizons (from two to four years). Our results, in general, support that the (theoretically) expected negative causal nexus between oil price fluctuations and economic activity for oil importers is dominant over longer time horizons for our dataset. An exception to this pattern is China, which has a dissimilar country profile in terms of its oil market and production structure from the profiles of the other Asian economies in the study. JEL Classification: C32, E32, O53, Q43

Nonlinear network connectedness: Assessing financial risk transmission in MENA and influence of external financial conditions

This study investigates the influence of global financial market conditions on financial risk connectedness and transmission among the Middle East and North Africa (MENA) economies. Utilizing weekly realized stock market volatilities as a measure of risk and employing a smooth transition threshold vector autoregressive (STVAR) model to analyze risk transmission under varying levels of financial stress, the authors also examine the impact of external macroeconomic conditions on the risk connectedness of MENA economies. The results indicate that the overall connectedness, based on a standard VAR model, is moderate at 48.34%. However, in the low financial stress regime, overall connectedness increases to 52.79%, and in the high financial stress regime, it rises to 72.94%, indicating stronger risk interdependency among MENA countries during times of high stress. In the high financial stress regime, Kuwait, Oman, Qatar, Saudi Arabia, Turkey, and the United Arab Emirates are identified as net risk transmitters among MENA countries. The study also reveals that risk transmission across MENA is more pronounced in the regime-dependent model compared to the overall mean-based VAR model.

Real estate uncertainty and financial conditions over the business cycle

We investigate the nonlinear effects of real estate uncertainty shocks and the role of financial conditions in the U.S. over the business cycle. We employ a logistic smooth transition vector autoregressive (LSTVAR) model and identify uncertainty shocks through short-run restrictions. The results illustrate that real estate uncertainty shocks negatively affect the housing market, reducing housing prices, housing starts, and employment in the construction sector. The influence of these shocks is notably more pronounced during recessions when compared to results from a standard linear VAR model in terms of the magnitude and persistence of the responses of the housing market-related variables. Additionally, favorable financial conditions dampen the dynamic responses of both macroeconomic indicators and the housing market to real estate uncertainty.

Macroeconomic uncertainty and vector autoregressions

A procedure to estimate measures of macroeconomic uncertainty and compute the effects of uncertainty shocks based on standard VARs is proposed. Uncertainty and its effects are estimated using a single model so to ensure internal consistency. Under suitable assumptions, the procedure is equivalent to using the square of the VAR forecast error as an external instrument in a proxy SVAR. The procedure allows to add orthogonality constraints to the standard proxy SVAR identification scheme. The method is applied to a US data set; results show that macroeconomic uncertainty is responsible of a large fraction of business-cycle fluctuations while financial uncertainty plays a modest role.

Identifying structural VARs from sparse narrative instruments: Dynamic effects of US macroprudential policies

SummaryWe study identification in Bayesian proxy VARs for instruments that consist of sparse qualitative observations indicating the signs of shocks in specific periods. We propose the Fisher discriminant regression and a non‐parametric sign concordance criterion as two alternative methods for achieving correct inference in this case. The former represents a minor deviation from a standard proxy VAR, whereas the non‐parametric approach builds on set identification. Our application to US macroprudential policies finds persistent declines in credit volumes and house prices together with moderate declines in GDP and inflation and a widening of corporate bond spreads after a tightening of capital requirements or mortgage underwriting standards.

The shale oil revolution and the global oil supply curve

SummaryWe focus on the implications of the shale oil boom for the global supply of oil. In order to derive testable implications, we introduce a simple stylized model with two producers, one facing low production costs and one higher production costs but potentially lower adjustment costs, competing à la Stackelberg. We find that the supply function is flatter for the high cost producer and that the supply function for shale oil producers becomes more responsive to demand shocks when adjustment costs decline. On the empirical side, we apply an instrumental variable approach using estimates of demand‐driven oil price changes derived from a standard structural VAR of the oil market. A main finding is that global oil supply is rather vertical, with a short‐term elasticity around 0.05. A rolling sample reveals that the shale oil boom does not appear to have fundamentally changed the contours of global oil production, but there is evidence for the oil supply curve to become more vertical in Saudi Arabia and more price responsive in the United States.

Do remittances affect output? Evidence from Lebanon

ABSTRACT This paper examines the effects of remittances on output for Lebanon, a case with a unique setting: remittances to Lebanon are primarily from workers located in oil-producing Gulf States and thus influenced by oil prices. This setting enables us to estimate a structural VAR model using the price of oil as an instrument. We estimate the model with and without the instrument and compare the impulse response of remittances. Our key results are as follows: without the instrument, we find that a one-standard deviation shock in remittances increases industrial production by about 0.10% to 0.20%, a small and weakly estimated effect. In the instrumental variable setting, the magnitude increases by a factor of at least 5.8: the increase in output ranges from 0.72% to 1.11%. Our results imply that remittance effects on output computed using standard VARs are likely underestimated. Moreover, they suggest that the adoption of policies that facilitate remittance flows should be encouraged as they likely stimulate economic growth by more than previously detected.

Oceans Apart? China and Other Systemically Important Economies

ABSTRACT China has been considered a systemically important economy for at least a decade. As policymakers worldwide grapple with sluggish growth there is relatively little evidence about whether the G4, which consists of the US, the Eurozone, Japan, and includes China, as a block contributes to global economic performance in a manner that is not possible when China is left out or treated exogenously. We estimate a series of panel factor and standard VARs because these are well suited to exploit cross-country links. We estimate the relative impact of domestic and global factors on these four economies. First, it is essential to treat China in a model of the G4, on a level playing field with the US, the Eurozone, and Japan to better understand how shocks among these economies interact with each other. Second, we find that domestic and global shocks can reinforce each other. Indeed, global monetary shocks explain up to 60% of variation in commodity demand and real economic conditions. We also report that there is a trade-off between domestic monetary and financial conditions. We recommend that policymakers to reexamine the potential benefits from greater policy cooperation.

Effects of COVID-19 on cryptocurrency and emerging market connectedness: Empirical evidence from quantile, frequency, and lasso networks

We use time and frequency connectedness approaches based on network analysis to investigate the volatility connectedness among 27 emerging equity markets and seven high-capitalized cryptocurrencies. We estimate the network connectedness using the standard, quantile, frequency, and lasso VAR models for the pre- and post-COVID-19 pandemic periods and daily data over the period from October 2, 2017 to May 20, 2022. The network connectedness estimates based on the several models used in this study indicate a growing risk spillover among and within the emerging market equities and the cryptocurrencies after the COVID-19 pandemic hit the world. The frequency connectedness analysis shows that cryptocurrencies cannot be used as diversifiers for emerging stock markets in both the short and long-run. The empirical findings from the quantile VAR model reveal that the volatility connectedness in the tails is much stronger compared to the center of the distribution. It is also evident that Saudi Arabia, Thailand’s stock markets, and USDT are the main risk transmitters at the 0.95-th quantile during the post-COVID period. Time-varying connectedness estimates confirm the substantial effect of COVID-19. Our study also shows that the spread of risk among these financial markets is global rather than regional, supporting cross-border structure and worldwide financial market integration. The findings suggest cryptocurrency and emerging market equity portfolios should be closely monitored during financial turmoil.

Causal Linkages Among Cryptocurrency and Emerging Market Indices: An Empirical Investigation

The possibility of including financial instruments, such as equity, debt, derivative and market-based funds, in a portfolio varies with their market sensitivity. Cryptocurrency (crypto) has been of recent origin and interest to investors and policymakers. The study has attempted to explore opportunities for Indian and international investors in equity and crypto markets. Bivariate analysis between the crypto index and Indian market indices revealed few causal linkages between crypto and other indices. Standard VAR and Granger causality have been used for exploring the association between the variables. DCC-GARCH has been applied for checking further on volatility spillover and the relationship between indices. Granger results indicate the presence of linkages between crypto and energy, media, and oil & gas indices. However, spillover results have shown an absence of such linkages in the short run but a significant presence in the long run except for a few indices.

Large Oil Shocks and Economic Growth: Evidence from Saudi Arabia

This paper aims to analyze the impact of large oil shocks on economic growth in Saudi Arabia, using a standard VAR model and a Markov-switching heteroscedastic regime, by using a quarterly data from 1981Q1 to 2019Q4. The results indicated that there were three large negative oil shocks, 1986Q1, 2008Q4, and 2014Q4, but there was only one large positive shock in 1990Q3. The impulse response and variance decomposition analysis show that both large negative and positive oil shocks have positive impacts on economic growth in Saudi Arabia, although only large negative shocks are statistically significant. Furthermore, large oil shocks only have a significant positive impact on economic growth comparing with normal oil shocks.

The links between gold, oil prices and Islamic stock markets in a regime switching environment

This paper investigates the linkages between gold, oil prices and Islamic stock market for the turbulent period 1996–2020 which covers the recent COVID-19 pandemic crisis. The paper applies standard VAR and Markov switching VAR models. Empirical results can be summarized as follows: (i) There are some significant relationships between the considered markets. (ii) The sign of the links varies significantly according to markets and regimes. (iii) There is a significant and positive link between oil and Islamic stock markets namely during turbulent periods suggesting the financialization of the crude oil market. (iv) The negative or the absence of relationships between gold market and both oil and Islamic stock markets indicate that gold can act as a hedge and safe haven during extreme market conditions. These findings have several practical implications for risk-management and portfolio diversification strategies.

Is there news in inventories?

We identify total factor productivity (TFP) news shocks using standard VAR methodology and document a new stylized fact: in response to news about future increases in TFP, inventories rise and comove positively with other major macroeconomic aggregates. We show that the standard theoretical model used to capture the effects of news shocks cannot replicate this fact when extended to include inventories. We derive the conditions required to generate a procyclical inventory response by using a wedges approach. To explain the empirical inventory behavior, we consider two mechanisms: sticky wages and the presence of knowledge capital accumulated through learning-by-doing. Only the latter moves the wedges to qualitatively match the empirical behavior. The desire to take advantage of higher future TFP through knowledge capital drives output and hours choices on the arrival of news and leads to inventory accumulation alongside the other macroeconomic variables. The broad-based comovement a model with knowledge capital can generate, supports the view that news shocks are an important driver of aggregate fluctuations.

COVID-19 and cryptocurrency market: Evidence from quantile connectedness

ABSTRACT This study quantifies the spillover effects among seven cryptocurrencies to explore the spillover characteristics of seven cryptocurrencies, namely, Bitcoin, Ethereum, Ripple, Litecoin, Monero, Stellar, and NEM. The connectedness networks of returns are based on standard VAR and quantile VAR spillovers. In addition, the framework focuses on intact, pre-, and post-COVID-19 crisis sub-sample periods. Our results highlight that Bitcoin, Litecoin, and Ripple are the dominant transmitters to return spillover. The strongest interconnection is found for Bitcoin/Litecoin and Ripple/Sellar pair. Interestingly, Ethereum is the unvarying recipient in the system and is influenced by most of the cryptocurrencies. Further, NEM exhibits no connection with any of the cryptocurrency in the network acting as a potential diversifier. The quantile spillovers suggest increased intensity of connectedness at right and left tails. The sub-sample analysis confirms the low network integration across the cryptocurrencies during pre-COVID period. Finally, the post-COVID period indicates tangled clusters across the cryptocurrencies. The analysis provides contrasting results as obtained in the pre-analysis phase. Implications for investors and policymakers are highlighted in the study.

A state‐dependent linear recurrent formula with application to time series with structural breaks

AbstractAn underlying assumption in Multivariate Singular Spectrum Analysis (MSSA) is that the time series are governed by a linear recurrent continuation. However, in the presence of a structural break, multiple series can be transferred from one homogeneous state to another over a comparatively short time breaking this assumption. As a consequence, forecasting performance can degrade significantly. In this paper, we propose a state‐dependent model to incorporate the movement of states in the linear recurrent formula called a State‐Dependent Multivariate SSA (SD‐MSSA) model. The proposed model is examined for its reliability in the presence of a structural break by conducting an empirical analysis covering both synthetic and real data. Comparison with standard MSSA, BVAR, VAR and VECM models shows the proposed model outperforms all three models significantly.

Practical Methods for Modeling Weak VARMA Processes: Identification, Estimation and Specification With a Macroeconomic Application

We consider the problem of developing practical methods for modelling weak VARMA processes. We first propose new identified VARMA representations, the diagonal MA equation form and the final MA equation form, where the MA operator is either diagonal or scalar. Both these representations have the important feature that they constitute relatively simple modifications of a VAR model (in contrast with the echelon representation). Second, for estimating VARMA models, we develop computationally simple methods which only require linear regressions. The asymptotic properties of the estimator are derived under weak hypotheses on the innovations (uncorrelated and strong mixing), in order to broaden the class of models to which it can be applied. Third, we present a modified information criterion which yields consistent estimates of the orders under the proposed representations. The estimation methods are studied by simulation. To demonstrate the importance of using VARMA models to study multivariate time series, we compare the impulse-response functions and the out-of-sample forecasts generated by VARMA and VAR models. The proposed methodology is applied to a six-variable macroeconomic model of monetary policy, based on the U.S. monthly data over the period 1962–1996. The results demonstrate the advantages of using the VARMA methodology for impulse response estimation and forecasting, in contrast with standard VAR models.

Comparison of Local Projection Estimators for Proxy Vector Autoregressions

Different local projection (LP) estimators for structural impulse responses of proxy vector autoregressions are reviewed and compared algebraically and with respect to their small sample suitability for inference. Conditions for numerical equivalence and similarities of some estimators are provided. A new LP type estimator is also proposed which is very easy to compute. Two generalized least squares (GLS) projection estimators are found to be more accurate than the other LP estimators in small samples. In particular, a lag-augmented GLS estimator tends to be superior to its competitors and to perform as well as a standard VAR estimator for sufficiently large samples.

Addressing COVID-19 Outliers in BVARs with Stochastic Volatility

The COVID-19 pandemic has led to enormous movements in economic data that strongly affect parameters and forecasts obtained from standard VARs. One way to address these issues is to model extreme observations as random shifts in the stochastic volatility (SV) of VAR residuals. Specifically, we propose VAR models with outlier-augmented SV that combine transitory and persistent changes in volatility. The resulting density forecasts for the COVID-19 period are much less sensitive to outliers in the data than standard VARs. Evaluating forecast performance over the last few decades, we find that outlier-augmented SV schemes do at least as well as a conventional SV model. Predictive Bayes factors indicate that our outlier-augmented SV model provides the best data fit for the period since the pandemic’s outbreak, as well as for earlier subsamples of relatively high volatility.

Tail Forecasting with Multivariate Bayesian Additive Regression Trees

We develop novel multivariate time series models using Bayesian additive regression trees that posit nonlinear relationships among macroeconomic variables, their lags, and possibly the lags of the errors. The variance of the errors can be stable, driven by stochastic volatility (SV), or follow a novel nonparametric specification. Estimation is carried out using scalable Markov chain Monte Carlo estimation algorithms for each specification. We evaluate the real-time density and tail forecasting performance of the various models for a set of US macroeconomic and financial indicators. Our results suggest that using nonparametric models generally leads to improved forecast accuracy. In particular, when interest centers on the tails of the posterior predictive, flexible models improve upon standard VAR models with SV. Another key finding is that if we allow for nonlinearities in the conditional mean, allowing for heteroskedasticity becomes less important. A scenario analysis reveals highly nonlinear relations between the predictive distribution and financial conditions.

Comparison of Local Projection Estimators for Proxy Vector Autoregressions

Different local projection (LP) estimators for structural impulse responses of proxy vector autoregressions are reviewed and compared algebraically and with respect to their small sample suitability for inference. Conditions for numerical equivalence and similarities of some estimators are provided. A new LP type estimator is also proposed which is very easy to compute. Two generalized least squares (GLS) projection estimators are found to be more accurate than the other LP estimators in small samples. In particular, a lag-augmented GLS estimator tends to be superior to its competitors and to perform as well as a standard VAR estimator for sufficiently large samples.