Bayesian VAR Research Articles

Investment Funds, Monetary Policy, and the Global Financial Cycle

This paper studies the role of international investment funds in the transmission of global financial conditions to the euro area using structural Bayesian vector auto regressions. While cross-border banking sector capital flows receded significantly in the aftermath of the global financial crisis, portfolio flows of investors actively searching for yield on financial markets world-wide gained importance during the post-crisis “second phase of global liquidity” (Shin, 2013). The analysis presented in this paper shows that a loosening of US monetary policy leads to higher investment fund inflows to equities and debt globally. Focussing on the euro area, these inflows do not only imply elevated asset prices, but also coincide with increased debt and equity issuance. The findings demonstrate the growing importance of non-bank financial intermediation over the last decade and have important policy implications for monetary and financial stability. JEL Classification: F32, F42, G15, G23

The Macroeconomic Effects of Fiscal Policy Shock in Ethiopia: Evidence from a Bayesian VAR Approach

This paper investigated the macroeconomic effects of fiscal policy shocks in Ethiopia using a Bayesian Vector Auto Regression model. We examined the dynamic responses of output, inflation, interest rate and exchange rate to fiscal policy shocks employing quarterly data from 2000/01Q1 to 2015/16Q4. The empirical evidence suggests that government spending shock had a positive impact on output and inflation but the effect was too small. Initially the interest rate responded negatively to government spending shocks and was positive with small effect and the nominal exchange rate showed deterioration. In addition, government revenue shocks had positive effect on real GDP and exchange rate and then they responded negatively. The inflation response to the net tax was medium and negative whereas its effect on interest rate was positive, and persistent. Furthermore, positive shocks to recurrent expenditure had a persistent positive impact on real output. Recurrent expenditure appeared not to be responsible for inflationary pressure. Interest rate picked up slightly as a result of recurrent spending shocks in the short run. The response of exchange rate to recurrent expenditure was small and remained negative. In contrast, capital expenditure was found to have an insignificant effect on output. The reasons could be the administrative lag and contractual bottleneck that are sometimes involved in executing capital projects and that appeared to be responsible for inflationary pressure. In the short term, the interest rate responded negatively and the estimated impact on exchange rate was insignificant. Following indirect tax revenue shocks the rise in output and inflation was very persistent. Regarding the effects of indirect taxes on interest rate and exchange rate our results show a clear and negative impact- whereas direct taxes were found to affect output and inflation very little and were insignificant. Initially, interest and exchange rates responded positively to direct tax shock later interest rate and exchange rate become insignificant and negative respectively. The results support the idea of a ‘crowding-in’ effect and when we take into account the feedback from government debt, the results suggest that the effects of fiscal shocks on the majority of macro variables is too small except for the real GDP for government revenue shock. Therefore, empirical evidence shows that it is important to consider government debt dynamics in the model

Nowcasting with Large Bayesian Vector Autoregressions

Nowcasting with Large Bayesian Vector Autoregressions

The Effects of Asset Securitization on Banks' Performances (Case Study: Bank Saderat Iran 2005-2015)

The purpose of this study is to investigate the effects of Securitization on banks' performances. Asset securitization is generally defined as the financial process by which an owner of an asset, such as a portfolio of loans, receives cash upfront in exchange for the future cash flows from the asset without selling the asset in a normal contractual sales agreement. (Menzi et al., 2018). Asset securitization has not been applied in Iranian banks so far. Therefore, we have devised an approach to examine the variation in performance in the presence or the absence of a securitized portfolio by using a Propensity Score Matching method. In this study, the effect of Securitization is hypothetically assessed for Bank Saderat Iran. To show the meaningfulness of the difference between two states, variance equality F-test as well as couplet-test is used. The results show that Securitization has a positive and meaningful effect on the net profit of the Bank Saderat Iran. Moreover, to study the relationship between profitability and non-performing loans, the Bayesian Vector Autoregressive model is applied, and the results show that non-performing loans harm the bank's profitability.

Real-time Forecasting of the Australian Macroeconomy Using Flexible Bayesian VARs

This paper evaluates the real-time forecast performance of alternative Bayesian Vector Autoregressive (VAR) models for the Australian macroeconomy. To this end, we construct an updated vintage database and estimate a set of model specifications with different covariance structures. The results suggest that a large VAR model with 20 variables tends to outperform a small VAR model when forecasting GDP growth, CPI inflation and unemployment rate. We find consistent evidence that the models with more flexible error covariance structures forecast GDP growth and inflation better than the standard VAR, while the standard VAR does better than its counterparts for unemployment rate. The results are robust under alternative priors and when the data includes the early stage of the COVID-19 crisis.

Partial Pooling with Cross-Country Priors: An Application to House Price Shocks

A structural Bayesian vector autoregression model predicts that - when accompanied by a decline in consumer confidence - a one-percent decrease in house prices is associated with a contraction of economic activity by 0.2 to 1.2 percent after one year. Results point to important second-round effects and additional exercises highlight the amplifying role of (i ) the mortgage rate and (ii ) consumers' expectations. A novel econometric approach exploits information available from the cross section. Shrinkage towards a cross-country average model helps to compensate for small country samples and reduces estimation uncertainty. As a by-product, the method delivers measures of cross-country heterogeneity.

Measuring the Effects of U.S. Uncertainty and Monetary Conditions on EMEs’ Macroeconomic Dynamics

We explore empirically the transmission of U.S. financial and macroeconomic uncertainty to emerging market economies (EMEs). We start by assuming that there are crucial differences between volatility and uncertainty, and between the latter and its shocks. With the help of Bayesian vector auto-regressions, we first identify two measures of U.S. uncertainty shocks, which appear to explain the dynamics of output developments better than conventional volatility measures. Next, we find evidence that adverse shocks to U.S. aggregate uncertainty are associated with marked contractions in some EMEs’ business cycles. However, we detect significant cross-country heterogeneity in the responses of EMEs’ business cycles to U.S uncertainty shocks. We also find generalized declines in stock market values, which supports the so-called Global Financial Cycle hypothesis.

Measuring Global Financial Market Stresses

We propose measures of financial market stress for forty-six countries and regions across the world. Our measures indicate that worldwide financial market stresses rose significantly in March following the widespread economic shutdowns in the wake of the COVID-19 pandemic. However, hardly anywhere in the world did these March peaks in financial stresses reach those seen during the trough of the 2007-09 Global Financial Crisis. Since March, financial market conditions normalized rapidly with financial market stresses around average levels. We also show that our financial stress measures have predictive power for the near-term economic outlook across most parts of the world, with the exception of China. A structural Bayesian VAR analysis indicates that historically, financial stress shocks, irrespective of the source of the shock, have significant impact on global economic activity, but in particular that emerging market economies are usually hit more severely than advanced economies.

Do Non-Performing Loans Matter for Bank Lending and the Business Cycle in Euro Area Countries?

We contribute to the empirical literature on the impact of non-performing loan (NPL) ratios on aggregate banking sector variables and the macroeconomy by estimating a panel Bayesian VAR model for twelve euro area countries. The model is estimated assuming a hierarchical prior that allows for country-specific coefficients. The VAR includes a large set of variables and is identified via Choleski factorisation. We estimate the impact of exogenous shocks to the change in NPL ratios across countries. The main findings of the paper are as follows: i ) An impulse response analysis shows that an exogenous increase in the change in NPL ratios tends to depress bank lending volumes, widens bank lending spreads and leads to a fall in real GDP growth and residential real estate prices; ii ) A forecast error variance decomposition shows that shocks to the change in NPL ratios explain a relatively large share of the variance of the variables in the VAR, particularly for countries that experienced a large increase in NPL ratios during the recent crises; and iii ) A three-year structural out-of-sample scenario analysis provides quantitative evidence that reducing banks' NPL ratios can produce significant benefits in euro area countries in terms of improved macroeconomic and financial conditions. JEL Classification: G21, C32, C11

Nowcasting the Output Gap

We propose a way to directly nowcast the output gap using the Beveridge-Nelson decomposition based on a mixed-frequency Bayesian VAR. The mixed-frequency approach produces similar but more timely estimates of the U.S. output gap compared to those based on a quarterly model, the CBO measure of potential, or the HP filter. We find that within-quarter nowcasts for the output gap are more reliable than for output growth, with monthly indicators for a credit risk spread, consumer sentiment, and the unemployment rate providing particularly useful new information about the final estimate of the output gap. An out-of-sample analysis of the COVID-19 crisis anticipates the exceptionally large negative output gap of -8.3% in 2020Q2 before the release of real GDP data for the quarter, with both conditional and scenario nowcasts tracking a dramatic decline in the output gap given the April data.

Weigh(T)Ing the Basket: Aggregate and Component-Based Inflation Forecasts for the Euro Area

We compare direct forecasts of HICP and HICP excluding energy and food in the euro area and five member countries to aggregated forecasts of their main components from large Bayesian VARs with a shared set of predictors. We focus on conditional point and density forecasts, in line with forecasting practices at many policy institutions. Our main findings are that point forecasts perform similarly using both approaches, whereas directly forecasting aggregate indices tends to yield better density forecasts. In the aftermath of the Great Financial Crisis, relative forecasting performance was typically only affected temporarily. Inflation forecasts made by Eurosystem/ECB staff perform similarly or slightly better than those from our models for the euro area. JEL Classification: C11, C32, C53, E37

Fiscal Policy Shocks and International Spillovers

The domestic and international transmission mechanism of fiscal policy shocks are analysed in large developed economies. Using a Bayesian VAR approach, we find that fiscal expansions are associated with increases in output, private consumption and, in many cases, with an increase in private investment. The terms of trade, which affect the international transmission of fiscal policy shocks, are found to depreciate in response to a fiscal expansion, thus transferring some of the increased domestic purchasing power abroad. A US government spending shock is expansionary for all non-US G7 members. A German government spending shock is expansionary for most, but not all European economies, both within and outside the Euro Area. The dynamics of the BVAR are rationalise using a dynamics stochastic general equilibrium model where heterogeneous households and firms face borrowing constraints.

Shock Dependence of Exchange Rate Pass-through: A Comparative Analysis of BVARs and DSGEs

In this paper, we make use of the results from Structural Bayesian VARs taken from several studies for the euro area, which apply the idea of a shock-dependent Exchange Rate Pass-Through, drawing a comparison across models and also with respect to available DSGEs. On impact, the results are similar across Structural Bayesian VARs. At longer horizons, the magnitude in DSGEs increases because of the endogenous response of monetary policy and other variables. In BVARs particularly, shocks contribute relatively little to observed changes in the exchange rate and in HICP. This points to a key role of systematic factors, which are not captured by the historical shock decomposition. However, in the APP announcement period, we do see demand and exogenous exchange rate shocks countribute significantly to variations in exchange rates. Nonetheless, it is difficult to find a robust characterization across models. Moreover, the modelling challenges increase when looking at individual countries, because exchange rate and monetary policy shocks (also taken relative to the US) are common to the whole euro area. Hence, we provide a local projection exercise with common euro area shocks, identified in euro area-specific Structural Bayesian VARs and in DSGE, extrapolated and used as regressors. For common exchange rate shocks, the impact on consumer prices is the largest in some new member states, but there are a wide range of estimates across models. For core consumer prices, the coefficients are smaller. Regarding common relative monetary policy shocks, the impact is larger than for exchange rate shocks in any case. Generally, euro area monetary policy plays a big role for consumer prices, and this is especially so for new member states and the euro area periphery.

Fast and Accurate Variational Inference for Large Bayesian VARs with Stochastic Volatility

We propose a new variational approximation of the joint posterior distribution of the log-volatility in the context of large Bayesian VARs. In contrast to existing approaches that are based on local approximations, the new proposal provides a global approximation that takes into account the entire support of the joint distribution. In a Monte Carlo study we show that the new global approximation is over an order of magnitude more accurate than existing alternatives. We illustrate the proposed methodology with an application of a 96-variable VAR with stochastic volatility to measure global bank network connectedness.

Measuring the Systemic Importance of Banks

We provide a new metric for the systemic importance of banks based on the intensity of spillovers of daily CDS movements. We denote this a bank’s Individual Systemic Risk (ISR). Our novel empirical tool uses Bayesian VAR to address the dimensionality problem in large networks of banks and maps for every pair of banks in the system the shocks that they exchange. We apply this tool to all banks that issue publicly traded CDS contracts among the world’s biggest 150 and identify which of these may trigger instability in the global financial system. Our methodology provides measures that are relatively stable across time, contain persistent information, have strong explanatory power for standard variables of systemic risk, and provided early warning signals in the case study of Deutsche Bank in mid-2016. Using our measure, ISR, we demonstrate which bank- and country-specific characteristics are related to bank systemic importance. We find higher systemic importance for banks that are relatively larger, less profitable, have G-SIB status, and are headquartered in economies with fiscally strong sovereigns. We also show that there is a negative relationship between concentration in the domestic banking sector and the systemic importance of a bank. We examine the relationship of ISR to alternative systemic risk metrics.

Public Opinion on Central Banks when Economic Policy is Uncertain

This paper investigates whether uncertainty about economic policy plays a role in shaping the credibility and reputation of the central bank in the eyes of the public. In particular, we look at the effect of policy uncertainty for the dynamics of citizens’ opinion, being trust, satisfaction or confidence, in the European Central Bank, the Bank of England and the Bank of Japan. Estimating Bayesian VARs for the period 1999-2014, we find that shocks to economic policy uncertainty induce economic contractions and relatively sharp deterioration in trust or satisfaction measures, which in general take longer than economic growth to rebuild.

베이지안 패널 VAR모형을 이용한 거시경제변수가 지역 주택가격에 미치는 영향

베이지안 패널 VAR모형을 이용한 거시경제변수가 지역 주택가격에 미치는 영향

Scenario Design for Macro-Financial Stress Testing

The goal of this paper is to provide a possible empirical approach to ScenarioDesign for selecting a stress scenario on international Macro-Financial variables. TheScenario Design framework belongs to the class of Second Generation Stress Tests andis composed of a few building blocks. First, multiple scenarios on the risk factorsare generated simulating a Multi-country large Bayesian VAR. Second, we take theperspective of a representative investor who aims to select a severe yet plausible scenarioon a set of systematic risk factors following a factor investing strategy. Moreover, wecompare the stress scenarios selected under different approaches to measure plausibility(the Mahalanobis distance and Entropy pooling under subjective views with a cleareconomic narrative). Finally, we compare our Scenario Design approach to an historicalscenario approach in terms of its ability to select a stress scenario in the eve of a rareadverse event like the COVID-19 pandemics. We give evidence that our frameworkis suitable for the selection of a proper forward-looking severe yet plausible Macro-Financial stress scenario.

The relation between the corporate bond-yield spread and the real economy: Stable or time-varying?

In this paper we assess whether the relation between the corporate bond-yield spread and the real economy has been stable over time. Using quarterly US data from 1953Q1 to 2018Q2, we estimate Bayesian VAR models which allow for drifting parameters and/or stochastic volatility and conduct formal model selection in a Bayesian setting. Our results indicate that the relation between the variables has been stable; we do, however, find strong support for stochastic volatility. We conclude that the corporate bond-yield spread’s usefulness for predicting real economic activity has not changed to a relevant extent after the Great Recession.

The Impact of Emerging Asia´s Demand on the Pacific Alliance Countries

ABSTRACT This article presents new evidence on the economic links between Asia and Latin America. Estimates from a Bayesian vector autoregression model show that key macroeconomic variables of the Pacific Alliance countries (Mexico, Peru, Chile, and Colombia) have a significant response to shocks on Emerging Asia’s demand. The spillover effects show that Peru is the country that is most vulnerable to income shocks in Emerging Asia. Nevertheless, developed economies’ shocks are still significant when it comes to explain the macroeconomic performances of Colombia, Chile, and especially, Mexico.