Factor-augmented Vector Autoregression Research Articles

Forecasting core inflation: the case of South Africa

ABSTRACT Underlying, or core, inflation is likely the most important variable for monetary policy. It is considered to be the optimal nominal anchor as it is stable, excludes relative price shocks, and reflects underlying trends in the behaviour of price-setters and demand conditions in the economy. Despite its importance, there is sparse literature on estimating and forecasting core inflation in South Africa, with the focus still on measuring it. This paper emphasizes predicting core inflation from time-varying parameter vector autoregressive models (TVP-VARs), factor-augmented VARs (FAVAR), and structural break models using quarterly data from 1981Q1 to 2013Q4. We use mean squared forecast errors (MSFE) and predictive likelihoods to evaluate the forecasts. In general, we find that (i) time-varying parameter models consistently outperform constant coefficient models (ii) small TVP-VARs outperform all other models; (iii) models with heteroscedastic errors do better than models with homoscedastic errors; and (iv) allowing for structural breaks does not improve the predictability of core inflation. Overall, our results imply that additional information on the growth rate of the economy and the interest rate is sufficient to forecast core inflation accurately, but the relationship between these three variables needs to be modelled in a time-varying fashion.

A Factor-Augmented Vector Autoregressive Approach to Analyze the Transmission of Monetary Policy

Using the factor-augmented vector autoregressive (FAVAR) model proposed by Bernanke et al. (2005), this study explores the effect of monetary policy on a wide range of macroeconomic and financial variables for the US, Canada and the UK. The study makes use of financial data from 1990 to 2016, comprising 55-70 variables of the three major nations to show (1) that factors come with additional informational capability, which summarizes the performance of key macroeconomic variables and (2) the manner in which these variables are affected by contractionary monetary policies. Our findings confirm that monetary policy tightening results in decrease in industrial production, employment, share prices, housing starts and inflation; however, it leads to increase in the three-month treasury bill rate, long-term interest rates and unemployment. Overall, the impact of standardized monetary tightening is similar across the countries studied. These results from the major economies and the inclusion of larger data sets containing more variables would be relevant for policy theorists and practitioners from other countries.

The Effectiveness Of Monetary Policy In South Africa Under Inflation Targeting: Evidence from a Time-Varying Factor-Augmented Vector Autoregressive Model

In the 1970s and 1980s, the economies of several developed and developing countries witnessed much volatility in output growth, inflation and other macroeconomic variables. Thereafter, these became considerably low and more stable. This latter development has been named the "great moderation" with first observation in the US and comparable evidence for other developed and developing economies including South Africa. However, the 2007/2009 economic and financial crisis resulted into heightened uncertainty and volatility. This brings to question the role of monetary policy and its effectiveness in the economy. This paper examines the transmission mechanism of shocks to monetary policy in South Africa using quarterly data from 1980:1 to 2012:4. We also in addition identify demand and supply shocks. Our analyses are based on a factor-augmented vector autoregression with time-varying coefficients and stochastic volatility (TVP-FAVAR), which allows us to simultaneously analyze the changing impulse responses of a set of 177 macroeconomic variables covering the inflation, real activity, asset prices and monetary series. We also have intangible variables, such as confidence indices, and survey variables. These data capture the broad trends in the South African economy. Our results based on the impulse response functions, are consistent with economic theory as we observe no price puzzle that is often associated with the standard VAR models. We find evidence of modest time variation in the transmission of shocks. Overall, the macroeconomic variables seemed to have responded slightly more to the monetary policy shocks in the post -2000 (inflation targeting) sub-period than the pre-2000 period, albeit the differences in the effects are statistically insignificant. The forecast error variance decomposition results show the changes in the macroeconomic variables are largely determined by the demand shock relative to the monetary policy shock although the contribution of the latter increased slightly over time. Our results suggest the need for a more efficient role of the monetary authority as this will both improve its credibility and greater economic stability. As inflation still remains within the upper portion of the 3–6% target range, appropriate mix of supply and demand side policies could be explored alongside monetary policy to reduce inflationary pressures.

Forecasting the GDP of a small open developing economy: an application of FAVAR models

ABSTRACTGDP forecasting remains a challenge for a small open developing economy. Faced with insufficient and low-frequency data, central bank forecasters cannot project GDP reliably for the purpose of monetary policy decision-making. An attempt is made to forecast GDP using a factor-augmented vector autoregressive (FAVAR) model for a small open developing economy. The forecasting accuracy of the FAVAR model is examined through sequential forecasts and benchmarked against a Bayesian vector autoregressive (BVAR) model. The main finding of this study is that a FAVAR model can generate consistent GDP projections for a small open developing economy despite data inadequacy.

Is the exchange rate a shock absorber or a source of shocks? Evidence from the U.S.

We examine the stabilization role of the exchange rate in the U.S. economy using a factor augmented vector autoregression model. We find that exchange rate shock explains a large fraction of the variation in exchange rate and transmits major disturbances to the real economy. Further, we find that demand and supply shocks explain less than a quarter of the exchange rate movement. We provide robust evidence that although the exchange rate plays some role as a shock absorber, its role as an independent source of shocks is more dominant for the U.S. economy. The foreign exchange market breeds its own shocks which are destabilizing not only to the value of the dollar but to the overall economy as well. Our results suggest that policymakers need to take foreign exchange market fluctuations into account when making macroeconomic policy decisions.

Large time‐varying parameter VARs: A nonparametric approach

SummaryIn this paper we introduce a nonparametric estimation method for a large Vector Autoregression (VAR) with time‐varying parameters. The estimators and their asymptotic distributions are available in closed form. This makes the method computationally efficient and capable of handling information sets as large as those typically handled by factor models and Factor Augmented VARs. When applied to the problem of forecasting key macroeconomic variables, the method outperforms constant parameter benchmarks and compares well with large (parametric) Bayesian VARs with time‐varying parameters. The tool can also be used for structural analysis. As an example, we study the time‐varying effects of oil price shocks on sectoral U.S. industrial output. According to our results, the increased role of global demand in shaping oil price fluctuations largely explains the diminished recessionary effects of global energy price increases.

Variance risk premium in a small open economy with volatile capital flows: The case of Korea

This paper extends the research on the variance risk premium by considering a small open economy with volatile capital flows—the Korean economy. The empirical analysis in this paper finds that as in the US, the variance risk premium in Korea has a predictive power for the Korea Composite Stock Price Index (KOSPI) 200 stock returns over one-month and three-month horizons, indicating that it reflects the level of risk aversion in the Korean economy. The short-term forecasting ability of the variance risk premium is comparable to that of other popular predictor variables, such as the dividend yield and output gap. Moreover, a factor-augmented vector autoregression (FAVAR) analysis shows that the global liquidity sector is more important than the domestic macroeconomic sector in determining the variance risk premium. An increase in global liquidity significantly reduces both the variance risk premium and economic uncertainty.

Energy price shocks and dynamics of current account in Turkey: a FAVAR Approach

Purpose- In this article, we examine the linkages between current account and energy prices, namely crude oil, coal and natural gas in Turkey the years between 2005 and 2016. Methodology- This article investigates how the changes in the energy prices affect the current account in Turkey. For this purpose, a Factor-Augmented Vector Auto Regression (FAVAR) model is used with economic data from the Turkish economy and world commodity price indexes to obtain empirical results for current account dynamics in the Turkish economy. The impact of various factors that include crude oil prices, coal prices, natural gas prices and fuel (Energy) index (Crude oil, natural gas, and coal price indices) data have been studied by obtaining impulse response functions. Findings- Natural gas prices gradually affect the current account. The impact is permanent after a period indicating a very limited elasticity. Oil prices have an immediate The current on the current account. Cycles, in the long run, indicate some degree of elasticity. The negative effect of coal price on the current account deficit occurs with a significant delay. Crude oil price index shocks graphs and fuel index, which includes oil price, coal price and natural gas, and crude oil price shocks graphs are very similar. Conclusion- In this comprehensive study, we can conclude that crude oil prices, coal prices, natural gas prices deteriorate current account balance. From all of the energy indices, the crude oil price is the most effective on the current account.

Inflation expectations and the recovery from the Great Depression in Germany

A regime shift toward increased inflation expectations is credited with jump-starting the recovery from the Great Depression in the United States. What role did inflation expectations play in Germany that experienced a similarly successful economic upturn in the 1930s? We study inflation expectations in the German recovery across several methods: we conduct a narrative study of media sources; we estimate inflation expectations from a factor-augmented vector autoregression model, real interest rate forecasts, and quantitative news series. Consistently across these approaches, we do not find a shift to increased expected inflation. This recovery was different, and its causes lie elsewhere.

The credit supply channel of monetary policy: evidence from a FAVAR model with sign restrictions

We test whether the credit channel of the monetary policy was present in the United States’ economy from January 2001 to April 2016. To this end, we use a factor-augmented vector autoregression, and we impose sensible theoretical sign restrictions in our structural identification scheme. We use the expected substitution effect between bank commercial loans and commercial papers to identify the credit supply channel. We found that the credit channel appears to have operated in the US economy during the sample period. However, when we split the sample, we found that the credit channel did not operate after the subprime crisis (close to the Zero Lower Bound of the interest rate). This result is robust to changing the sign restriction horizons. It supports current views in the literature regarding the ineffectiveness of the credit channel as a means to foster real economic activity during crises episodes.

Spillover Effects of Regional Apartment Business Cycles Using Factor-Augmented VAR Model

구는 FAVAR 모형을 이용하여 지역별 아파트 경기지수를 작성하고, 아파트 경기지 수의 적정성을 검증하고, 작성된 아파트 경기지수를 이용하여 지역별 아파트 경기의 전이 효과를 분석하였다. 실증분석결과, FAVAR 모형을 이용하여 작성한 전국아파트 경기지수와 통계청에서 발표 하는 경기동행지수 순환변동과 유사한 움직임을 보이며, 특히 2008년 금융위기와 그 이후의 경제 충격을 전국 아파트 경기지수가 잘 트레이싱(tracing)하는 것으로 분석되었으며, 전국 아파트 경기지수는 경기동행 순환변동을 약 4-5개월 정도 선행하는 것으로 나타났다. 지역별 아파트 경기지수 분석결과, 2008년 세계금융위기의 영향을 공통적으로 받은 것을 확인되었지만, 금융위기 이후에는 지역별 아파트 경기지수가 차이를 보이는 것으로 분석되었다. 이러한 결과는 중앙정부에서 시행한 부동산 정책에 대한 효과가 지역별로 다르게 나타날 수 있다는 것이며, 이는 부동산 정책을 시행할 때, 지역별 특성과 영향을 고려해야 함을 시사하는 것이다. 지역별 경기지수 전이효과를 종합하면, 아파트 경기지수는 서울과 수도권이 상호 영향을 주고 받으며, 부산에도 상당한 영향을 미치는 것을 확인할 수 있지만, 부산에서 서울과 수도권에 미치는 영향은 상대적으로 미미하다고 할 수 있다.We used the FAVAR model in order to estimate the regional apartment business cycles. We also analyzed the regional spillover effects by using the methodology suggested by Diebold and Yilmaz (2009, 2012). Based on this analysis, a similarity was found between the national apartment business cycle and the coincident composite index. In addition, the national apartment business cycle can be traced back to the 2008 financial crisis and subsequent economic shocks. The national apartment business cycle also led the coincident composite index by about 4-5 months. The analysis of the regional apartment business cycles showed that the regional apartment business cycles were commonly affected by the 2008 global financial crisis. However, the regional apartment business cycles varied after the financial crisis. These results indicate that the real estate policies of the government should be differentiated by region. Moreover, there is a difference between the economic environment of each region. We conclude that when implementing real estate policies, regional characteristics and impacts need to be considered. The analysis result of the transition effect of regional economic indexes showed that the apartment business cycles have a significant influence on both Busan and Seoul. However, Busan has a relatively small impact on Seoul and the metropolitan area.We estimate that the variation in Seoul’s apartment business cycle is only about 0.291 due to the change within Seoul, and that 0.709 of the transition effect is explained by the change in the other regions. Meanwhile, the transfer effect of Incheon to the other regions was 0.819.

The quantitative effects of tax foresight: Not all states are equal

This paper explores the effect of federal tax news on state economic activity. We estimate a factor-augmented vector autoregression (FAVAR) model, which allows us to consider the possibility that unobserved factors – such as credit and fiscal conditions – might be relevant for modeling the dynamic response of aggregate and state-level economic activity. We identify tax foresight as a shock to the implicit tax rate, measured by the yield spread between the one-year tax-exempt municipal bond and the one-year taxable Treasury bond. Our results suggest that an increase in the implicit tax rate raises national output over much of the anticipation period. In addition, anticipated tax increases give rise to expansions in state personal income and employment. We find that the variation in the responsiveness of economic activity across states is mostly explained by differences in industrial composition and income distribution, as well as by some demographic characteristics such as median income and education. Finally, using a proxy for exogenous changes in federal tax revenues, we investigate the dynamics of state-level personal income and employment. Our results point to considerable heterogeneity in the response across U.S. states. Moreover, they reveal that the long-run multiplier for an anticipated increase in tax revenues is about a tenth of the short-run multiplier for an unanticipated increase in taxes.

The Quantitative Effects of Tax Foresight: Not All States Are Equal

This paper explores the effect of tax news on state economic activity. We estimate a factor-augmented vector autoregression (FAVAR) model, which allows us to consider the possibility that unobserved regional factors — such as credit and fiscal conditions — might be relevant for modelling the dynamic response of aggregate and state-level economic activity. We identify tax foresight as a shock to the implicit tax rate, measured by the yield spread between the one year tax-exempt municipal bond and the one-year taxable Treasury bond. Our results suggest that an increase in the implicit tax rate raises national output over much of the anticipation period. In addition, anticipated tax increases give rise to expansions in state personal income and employment. We find that the variation in the responsiveness of economic activity across states is mostly explained by differences in industrial composition and income distribution, as well as by some demographic characteristics such as median income and education.

The effects of electricity price changes on prices of other goods and services – evidence from Turkey

ABSTRACT This article employs a Factor-Augmented Vector Autoregressive model to assess the effects of electricity price innovations on prices of other goods and services. Using monthly series from Turkish Domestic Producer Price Index (D-PPI) and Harmonized Index of Consumer Prices (HICP) components, the results from the analyses on D-PPI components suggest that (i) Machinery & Equipment (not elsewhere classified); Electrical Equipment; and Rubber & Plastic Products increase the most, while (ii) Tobacco Products; Crude Petroleum & Natural Gas; and Water Supply, Sewerage, Waste Management & Remediation Services increase the least. In addition, the results from the analyses on HICP components suggest that (iii) Housing, Water, Electricity, Gas & Other Fuels; Furnishings, Household Equipment & Maintenance; and Restaurants & Hotels increase the most, while (iv) Communications; Alcoholic Beverages, Tobacco & Narcotics; and Education increase the least.

Energy price shocks and dynamics of current account in Turkey: is this time different

Purpose- In this article, we examine the link between current account and energy prices, namely crude oil, coal and natural gas in Turkey the years between 2005 and 2016 . Methodology- This article investigates how the changes in the energy prices affect the current account in Turkey. For this purpose, a Factor-Augmented Vector Auto Regression (FAVAR) model is used with economic data from the Turkish economy and world commodity price indexes to obtain empirical results for current account dynamics in the Turkish economy. The impact of various factors that include crude oil prices, coal prices, natural gas prices data have been studied by obtaining impulse response functions. Findings- Natural gas prices gradually affect the current account. The impact is permanent after a period indicating a very limited elasticity. Oil prices have an immediate impact on the current account. Swings, in the long run, indicate some degree of elasticity. The negative effect of coal price on the current account deficit occurs with a significant delay. Conclusion- We can conclude that, from all of the energy indices, the crude oil price is the most effective on the current account.

Effectiveness of Macroprudential Policies under Maturity Mismatch

ABSTRACT This paper studies the role of reserve requirements as a macroprudential policy tool in China. In a factor-augmented vector autoregression of China, we find that banking system works as a shock absorber. To explain this “financial attenuator” effect, we extend an otherwise standard New-Keynesian model including (i) a banking sector with financial frictions with households, (ii) a credit in multi-period contracts, (iii) a central bank that conducts monetary policy by adjusting the nominal interest rate in response to the money-growth rate, and (iv) the reserve requirement (RR) as a macroprudential policy instrument. The quantitative analysis of the estimated model shows that the presence of a maturity mismatch makes a bank’s leverage less procyclical, which offsets the effects of financial frictions and makes the bank’s balance sheet function as a shock absorber. Our analysis also suggests that countercyclical RR adjustment can enhance welfare compared to fixed an RR ratio in the presence of a maturity mismatch but faces important implementation challenges. In particular, an RR policy countercyclically responding to bank lending can effectively stabilize the economy but increase financial fragility, as the “credit attenuator” effect stemming from the maturity mismatch will be offset by this policy.

Estimation of FAVAR Models for Incomplete Data with a Kalman Filter for Factors with Observable Components

This article extends the Factor-Augmented Vector Autoregression Model (FAVAR) to mixed-frequency and incomplete panel data. Within the scope of a fully parametric two-step approach, the alternating application of two expectation-maximization algorithms jointly estimates model parameters and missing data. In contrast to the existing literature, we do not require observable factor components to be part of the panel data. For this purpose, we modify the Kalman Filter for factors consisting of latent and observed components, which significantly improves the reconstruction of latent factors according to the performed simulation study. To identify model parameters uniquely, the loadings matrix is constrained. In our empirical application, the presented framework analyzes US data for measuring the effects of the monetary policy on the real economy and financial markets. Here, the consequences for the quarterly Gross Domestic Product (GDP) growth rates are of particular importance.

A Factor-augmented VAR Analysis of Business Cycle and Inflation Synchronizations in GCC Member Countries

A Factor-augmented VAR Analysis of Business Cycle and Inflation Synchronizations in GCC Member Countries 의 이용 수, 등재여부, 발행기관, 저자, 초록, 목차, 참고문헌 등 논문에 관한 다양한 정보 및 관련논문 목록과 논문의 분야별 BEST, NEW 논문 목록을 확인 하실 수 있습니다.

Monetary Policy and Systemic Risk-taking in the Euro Area Banking Sector

Available empirical evidence on the significance of the (micro) risk-taking channel of monetary policy is not sufficient to indicate a threat to financial stability. This research has the objective of determining whether conventional and unconventional monetary policies have resulted in systemic risk-taking. To that end, it uses statistical measures that capture systemic risk in the banking sector of the euro area in all its forms allowing for the time-varying non-linearities and feedback effects typical of financial markets. The methodology is a structural factor-augmented vector autoregressive (FAVAR) model. The main result is that there is systemic risk-taking in the euro area banking sector. It takes the form of an increase in the banking sector’s vulnerability via contagion and interconnectedness. Banks’ balance sheets, however, do not account for the full transmission from (micro) risk taking to systemic risk-taking confirming the importance of accounting for time-varying non-linearities and feedback effects. The main policy implication is that persistently accommodative monetary policy geared toward preserving price stability may face a trade-off with financial stability. In that case, monetary policy will require coordination with macro-prudential policy.

Impact of climate change on food yield in Senegal: FAVAR approach

The main objective of this research is to evaluate the impact of climate change on food crop yields in Senegal using the Factor Augmented Vector Auto Regression (FAVAR) approach. The estimation method used is principal components analysis. We identified two major shocks representative of climate change. The first is an increase of temperature (thermal shock) and the second is a decrease in the quantity of precipitation (rainfall shock). The data covers the period 1970-2014 and each of the shocks is carried out over the prior year. The impact of each shock is observed along a time horizon of 10 years. The results show a positive impact of the thermal shock on the yields of rice, maize and millet, with a much greater impact on rice and maize yield. Rising temperatures are, however, detrimental to sorghum. A decline in rainfall has a negative impact on the yields of all cereals, which is in line with expectations.