Mixed-frequency VAR Research Articles

An Observation-Driven Mixed-Frequency VAR Model With Closed-Form Solution

An Observation-Driven Mixed-Frequency VAR Model With Closed-Form Solution

Climate, geopolitical, and energy market risk interconnectedness: Evidence from a new climate risk index

Using meteorological monitoring data from eight climate disasters across the globe along with financial data from the WTI and BNG energy markets, this study employs the fixed-base extreme difference entropy method to construct a climate risk index (CRI) and investigates the relationship between climate risk, geopolitical risk (GPR), and energy market risk based on the mixed-frequency VAR (MF-VAR) method. The empirical results show that an increase in both GPR and CRI is related to an increase in energy market risk, and that a higher CRI is associated with greater GPR. Moreover, the positive relationship between CRI scores and energy market risk after the Paris Agreement has grown stronger.

Precision-based sampling for state space models that have no measurement error

This article presents a computationally efficient approach to sample from Gaussian state space models. The method is an instance of precision-based sampling methods that operate on the inverse variance-covariance matrix of the states (also known as precision). The novelty is to handle cases where the observables are modeled as a linear combination of the states without measurement error. In this case, the posterior variance of the states is singular and precision is ill-defined. As in other instances of precision-based sampling, computational gains are considerable. Relevant applications include trend-cycle decompositions, (mixed-frequency) VARs with missing variables and DSGE models.

Carbon emissions and economic growth in China: Based on mixed frequency VAR analysis

This study endeavors to examine the association between carbon emissions and economic growth in China spanning the period from 1992 to 2018, employing a mixed frequency vector autoregressive model (MF-VAR). In contrast to the low frequency vector autoregressive model (LF-VAR), the MF-VAR model employed in this research does not involve any filtering procedure; instead, it directly employs variables with distinct frequencies for regression computation. Comparative analysis of the findings reveals that the utilization of the MF-VAR model yields bidirectional causality between carbon emissions and economic growth, a relationship that cannot be validated through employment of the LF-VAR model. Furthermore, the prediction error variance decomposition outcomes of the MF-VAR model exhibit a higher level of explicatory capacity when compared to those of the LF-VAR model. These outcomes carry significant implications for China, as well as other global economies, in the pursuit of the Sustainable Development Goals (SDGs). The analysis outcomes further underscore the necessity of effectively curbing greenhouse gas emissions in China, while simultaneously maintaining a certain level of economic development.

Revisiting economic growth and CO2 emissions nexus in Taiwan using a mixed-frequency VAR model

This study, for the first time in Taiwan, uses the mixed frequency vector autoregressive (MF-VAR) model in the high-frequency dataset to investigate the causal association between economic progress and carbon dioxide emissions over time periods spanning from 1970Q1-2019Q4. This study also includes primary energy consumption as a control variable for analysis since the bias of missing variables could lead to misleading results. In accordance with the forecast error variance decomposition and the Granger causality test, our empirical findings imply that the MF-VAR model has more explanatory power than the traditional VAR model. The empirical LF-VAR model results demonstrate a reciprocal and causal association between economic progress and carbon dioxide (CO2) emissions is supported by evidence; primary energy consumption significantly influences economic progress. Additionally, MF-VAR model results also indicate, in Taiwan, a reciprocal and causal association between economic progress and carbon dioxide emissions as well as between primary energy consumption and economic progress. Based on the finding of the results, this study suggests policy implications to the government that an effective energy strategy should be addressed along with the plan for economic development in Taiwan.

Could Cryptocurrency Policy Uncertainty Facilitate U.S. Carbon Neutrality?

Investigating the essential impact of the cryptocurrency market on carbon emissions is significant for the U.S. to realize carbon neutrality. This exploration employs low-frequency vector auto-regression (LF-VAR) and mixed-frequency VAR (MF-VAR) models to capture the complicated interrelationship between cryptocurrency policy uncertainty (CPU) and carbon emission (CE) and to answer the question of whether cryptocurrency policy uncertainty could facilitate U.S. carbon neutrality. By comparison, the MF-VAR model possesses a higher explanatory power than the LF-VAR model; the former’s impulse response indicates a negative CPU effect on CE, suggesting that cryptocurrency policy uncertainty is a promoter for the U.S. to realize the goal of carbon neutrality. In turn, CE positively impacts CPU, revealing that mass carbon emissions would raise public and national concerns about the environmental damages caused by cryptocurrency transactions and mining. Furthermore, CPU also has a mediation effect on CE; that is, CPU could affect CE through the oil price (OP). In the context of a more uncertain cryptocurrency market, valuable insights for the U.S. could be offered to realize carbon neutrality by reducing the traditional energy consumption and carbon emissions of cryptocurrency trading and mining.

A Mixed Frequency BVAR for the Euro Area Labour Market*

AbstractWe introduce a Bayesian mixed frequency VAR model for the aggregate euro area labour market that features a structural identification via sign restrictions. The purpose of this paper is twofold: we aim at (i) providing reliable and timely forecasts of key labour market variables and (ii) enhancing the economic interpretation of the main movements in the labour market. We find satisfactory results in terms of nowcasting and forecasting, especially for employment growth. Furthermore, we look into the shocks that drove the labour market and macroeconomic dynamics from 2002 to 2022, with an insight also on the COVID‐19 recession. While demand shocks were the main drivers during the Global Financial Crisis, technology and wage bargaining factors, reflecting the degree of lockdown‐related restrictions and job retention schemes, have been important drivers of key labour market variables during the pandemic.

Revisit economic growth and CO2 emission nexus in G7 countries: mixed frequency VAR model.

Applying a mixed frequency vector autoregressive (MF-VAR) approach, we examine relationships between CO2 emissions and economic growth from 1970Q1 to 2019Q4 among G7 countries. We incorporate primary energy consumption as a control variable, to avoid any bias from an omitted variable. Our empirical results, using forecast error variance decomposition and a Granger causality check, suggest that MF-VAR exhibits better explanatory ability over the more commonly used VAR model employing single frequency data. Results from LF-VAR exhibit a feedback loop connecting economic expansion and emissions of CO2 with one-way Granger causality from primary energy consumption to growth of the economies studied. MF-VAR model results also indicate that, in G7 countries, economic expansion exhibits a one-way causal link to CO2 emissions in Canada, UK, and US cases. Interestingly, MF-VAR shows feedback between economic expansion and primary energy use in Germany, while LF-VAR quantifies the link from economic growth to CO2 emissions in Canada and from CO2 to economic growth in the UK. Results raise implications for the G7 samples' policymakers.

On the Relationships among Nurse Staffing, Inpatient Care Quality, and Hospital Competition under the Global Budget Payment Scheme of Taiwan’s National Health Insurance System: Mixed Frequency VAR Analyses

Background: Time series analyses on the relationship between nurse staffing and inpatient care quality are rare due to inconsistent frequencies of data between common observations of nurse-staffing (e.g., monthly) and inpatient care quality indicators (e.g., quarterly). Methods: In order to deal with the issue of mixed frequency data, this research adopted the MF-VAR model to explore causal relationships among nurse staffing, inpatient care quality, and hospital competition under the global budget payment scheme of Taiwan’s healthcare system. Results: Our results identified bi-directional causation between nurse staffing and patient outcomes and one-way Granger causality running between nurse staffing and reimbursement payments for inpatient care services. Impulse-response analyses found positive (negative) effects of the patient-to-nurse ratio on adverse patient outcomes (reimbursement payments) in all types of hospitals and detrimental effects of adverse patient outcomes on the patient-to-nurse ratio in medical centers and regional hospitals across a 12-month period. Conclusions: These findings suggest that nurse staffing is an essential determinant of both patient outcomes and reimbursement payments. Strategic policies such as direct subsidy and hospital accreditation for appropriate nurse staffing levels should be implemented for medical centers and regional hospitals to mitigate the harmful effects of adverse patient outcomes on nurse staffing.

Infant Mortality and Inflation in China: Based on the Mixed Frequency VAR Analyses.

Reducing neonatal mortality is an important goal in the Sustainable Development Goals (SDGs), and with the outbreak of the new crown epidemic and severe global inflation, it is extremely important to explore the relationship between inflation and infant mortality. This paper investigates the causal relationship between inflation and infant mortality using a mixed frequency vector autoregressive model (MF-VAR) without any filtering procedure, along with impulse response analysis and forecast misspecification variance decomposition, and compares it with a low frequency vector autoregressive model (LF-VAR). We find that there is a causal relationship between inflation and infant mortality, specifically, that is inflation increases infant mortality. Moreover, the contribution of CPI to IMR is greater in the forecast error variance decomposition in the MF-VAR model compared to the LF-VAR model, indicating that CPI has stronger explanatory power for IMR in mixed-frequency data. The results of the study have important implications for China and other developing countries in reducing infant mortality and achieving the Sustainable Development Goals (SDGs). Policymakers should focus on inflation as a macroeconomic variable that reduces the potential negative impact of inflation on infant mortality. The results of the analysis further emphasize the importance of price stability in the context of global inflation caused by the outbreak of the coronavirus pandemic outbreak.

Panel data nowcasting

This article promotes the use of panel data methods in nowcasting. This shifts the focus of the literature from national to regional nowcasting of variables like gross domestic product (GDP). We propose a mixed-frequency panel VAR model and a bias-corrected least squares estimator which attenuates the bias in fixed effects dynamic panel settings. Simulations show that panel forecast model selection and combination methods are successfully adapted to the nowcasting setting. Our novel empirical application of nowcasting quarterly U.S. state-level real GDP growth highlights the success of state-level nowcasting, as well as the gains from pooling information across states.

Mixed frequency evidence of the tourism growth relationship in small Island developing states: a case study of Tonga

ABSTRACT In this study, we examine the effect of tourism on economic growth in Tonga. We apply Ghysels Beta-MIDAS approach to estimate the elasticity of tourism, identify breaks with the multiple break test, and test for causality using the mixed frequency VAR approach. We utilize a sample from 1995 quarter 1 to 2018 quarter 4. The results indicate that the long-run effect of tourism is 0.06. Two structural breaks are identified, and both have negative growth effects. Unidirectional causality from tourism to real per-capita GDP is noted. The findings indicate that Tonga’s economic growth can be improved by promoting tourism.

Measuring the effects of expectations shocks

We seek to improve the measurement of the dynamic causal effects of expectation shocks by addressing issues related to data uncertainty. The expectations shocks are estimated in a mixed-frequency VAR model which incorporates monthly and quarterly economic and financial indicators. The VAR is estimated on real-time data to prevent the shocks being confounded with the effects of data uncertainty. But dynamic responses are calculated using a quarterly VAR for revised data, estimated using older vintages as instruments to account for the fact that ‘true values’ of key macroeconomic variables may never be observed. We show that expectations shocks – revisions in GDP expectations unrelated to changes in current economic fundamentals and orthogonalized to other, potentially related shocks – explain 7–8% of the two-year variation of output, investment, consumption and hours. This is similar to the proportion of business-cycle variation explained by monetary shocks, for example.

Systemic risk, real GDP growth, and sentiment

Using a mixed frequency VAR methodology, which can accommodate variables with different frequencies in a VAR framework, we model the relation between monthly systemic risk and real GDP growth. To identify the importance of business and consumer sentiment in this relation, a Kalman filter approach is adopted to extract the systemic risk-driven sentiment expectations. Our contributions are as follows. Systemic risk in the U.S. has a significant and negative impact on real GDP growth, and the channel of this impact is business and consumer sentiment. We illustrate that systemic risk is an important determinant of sentiment and sentiment expectations which, in turn, exercise a significant effect on GDP. These results extend previous evidence on the impact of systemic risk on monthly measures of economic activity, and carry implications for recent research exploring systemic risk and sentiments as factors driving the macro-economy. They also suggest that ‘offsetting’ sentiment-targeting policies may be adopted in order to curtail the detrimental effects of systemic risk on GDP.

Electricity Consumption and Economic Growth in Turkey: A Mixed Frequency Var Approach

This paper investigates the relationship between monthly electricity consumption, quarterly GDP, and quarterly components of GDP using the Mixed Frequency VAR (MF-VAR) model for Turkey for the period from 1987:2Q to 2017:3Q. When the conventional quarterly VAR model is used, any causal relationship between electricity consumption and GDP growth could not be found. However, when we used the MF-VAR specification, we found that electricity consumption does increase GDP growth; this supports to the growth hypothesis but not the conservation hypothesis. Repeating the same exercise by adding other low frequency variables, the empirical evidence still reveals that an increase in electricity consumption increases GDP. However, an increase in electricity consumption increases Private Consumption, Investment, Imports expenditures, Construction, Industrial, Manufacturing, and Service Sector outputs more than it increases GDP. In addition to this, the empirical evidence reveals that an increase in electricity consumption increases Agricultural sector output less than it increases GDP.

Nowcasting in a Pandemic Using Non-Parametric Mixed Frequency VARs

This paper develops Bayesian econometric methods for posterior inference in non-parametric mixed frequency VARs using additive regression trees. We argue that regression tree models are ideally suited for macroeconomic nowcasting in the face of extreme observations, for instance those produced by the COVID-19 pandemic of 2020. This is due to their flexibility and ability to model outliers. In an application involving four major euro area countries, we find substantial improvements in nowcasting performance relative to a linear mixed frequency VAR.

The impact of high-frequency economic policy uncertainty on China’s macroeconomy: evidence from mixed-frequency VAR

We investigate the impact of high-frequency economic policy uncertainty on investments of state-owned and private-owned enterprises (SOEs and POEs), as well as short-, medium- and long-term bank loans in China by employing the mixed-frequency vector autoregression model. Impulse response analysis suggests that monthly economic policy uncertainty is allowed to have heterogeneous effects on investments and bank loans in China. Variance decomposition analysis shows that aggregating monthly economic policy uncertainty into the quarterly level underestimates the influence of economic policy uncertainty in shaping China’s macroeconomy at business cycle frequencies. By further decomposing the SOEs’ investment, we reveal that the effects of economic policy uncertainty on SOEs’ investment are strengthened due to the existence of the injection of the government investment into SOEs. Trade policy uncertainty has a similar impact on China’s investments and bank loans as economic policy uncertainty. The counterfactual analysis shows that the impact of economic policy uncertainty on China’s investments and bank loans is alleviated when the interest rate channel exists. Our major conclusions are insensitive to a series of robustness checks.

Identifying high-frequency shocks with Bayesian mixed-frequency VARs

We contribute to research on mixed-frequency regressions by introducing an innovative Bayesian approach. We impose a Normal-inverse Wishart prior by adding a set of auxiliary dummies in estimating a Mixed-Frequency VAR. Based on this new “high-frequency” identification scheme, we illustrate our method by identifying uncertainty shock for the U.S. economy. As the main findings, we document a “temporal aggregation bias” when we adopt a common low-frequency model instead of estimating a mixed-frequency framework. The bias is amplified in case of a large mismatching between the high-frequency shock and low-frequency business cycle variables.

A Mixed Frequency BVAR for the Euro Area Labour Market

We introduce a Bayesian Mixed-Frequency VAR model for the aggregate euro area labour market that features a structural identification via sign restrictions. The purpose of this paper is twofold: we aim at (i) providing reliable and timely forecasts of key labour market variables and (ii) enhancing the economic interpretation of the main movements in the labour market. We find satisfactory results in terms of forecasting, especially when looking at quarterly variables, such as employment growth and the job finding rate. Furthermore, we look into the shocks that drove the labour market and macroeconomic dynamics from 2002 to early 2020, with a first insight also on the COVID-19 recession. While domestic and foreign demand shocks were the main drivers during the Global Financial Crisis, aggregate supply conditions and labour supply factors reflecting the degree of lockdown-related restrictions have been important drivers of key labour market variables during the pandemic.

Identifying High-Frequency Shocks with Bayesian Mixed-Frequency VARs

We contribute to research on mixed-frequency regressions by introducing an innovative Bayesian approach. Based on a new “high-frequency” identification scheme, we provide novel empirical evidence of identifying uncertainty shock for the US economy. As main findings, we document a “temporal aggregation bias” when we adopt a common low frequency model instead of estimating a mixed-frequency framework. The bias is amplified when we identify a higher frequency shock.