The interaction between oil prices and macroeconomic dynamics has long been a source of interest for economists, policymakers, and industry practitioners. The importance of oil as a key component in production and transportation highlights its importance in economic processes.
In the United States, where oil is an essential component of the industrial and home sectors, changes in oil prices affect not only the energy sector but also a wide range of economic activity. Understanding the informational dynamics surrounding oil supplies is critical in this environment. Announcements and foreknowledge about oil supply frequently predate market reactions, resulting in what are known as oil supply news shocks. These informational variance shockwaves, in turn, engage a plethora of macroeconomic variables in a complicated interplay.
Through detailed research spanning the period from January 1975 to December 2022, this paper goes on an adventurous voyage into the macroeconomic effects of oil supply news shocks in the United States. The empirical basis for this research is a deep dissection of data relevant to oil supply surprises, oil supply news shocks, consumer price index, and industrial production index within the specified timetable.
The process begins with the complete setup of a Vector Autoregression (VAR) model that captures the dynamic interrelations between the relevant economic variables. The earlier phase includes a comprehensive determination of the model’s structure, highlighted by selecting of an appropriate lag length, followed by an estimation of the reduced form VAR using the Akaike Information Criterion (AIC) as a guiding metric. As the investigation progresses, it moves into a sophisticated estimation of the triangular VAR model helped by Cholesky decomposition, revealing the complicated network of causality and interactions among the variables under consideration.
The next stage relates to an intensive assessment of the stability of the results in order to ensure a robust and unassailable analytical framework. This includes a detailed evaluation of the coefficient matrices’ eigenvalues to confirm the model’s stability.The way concludes with an IRF analysis, which gives light on the time-path of variables in reaction to shocks, clarifying the temporary and long-term macroeconomic effects of oil supply news shocks.
This section describes the methodology used to analyse the macroeconomic effects of oil supply news shocks in the United States. The investigation begins with the collection of relevant data, which is then followed by an analytical get via the VAR model, ending in a strong statistical analysis confirming the reliability and validity of the conclusions.
The primary data used in this analysis ranges from January 1975 to December 2022, and includes key variables such as the Oil Supply Surprise series, the Oil Supply News Shock series, the Consumer Price Index (CPI), and the Industrial Production Index (IPI) for the United States. The dataset is carefully selected to assure accuracy and completeness, establishing the basis for the resulting analytical expedition.
Prior to estimating the VAR model, it is critical to determine the right lag duration to ensure the model’s robustness. The lag length is computed using traditional procedures by minimizing the Akaike Information Criterion (AIC). This step is critical because it establishes a structure for further model estimation while ensuring that the model capture the inherent dynamic of the data.
After determining the optimal lag duration, the investigation moves on to the estimate of the reduced-form VAR model. The VAR model is an effective technique for capturing the dynamic interrelationships between system variables. The reduced-form VAR model is estimated, and the parameters are examined to get insight into the temporal interactions between the variables under consideration.
To go deeper into the causal interplay among variables, the research moves on to the estimate of the triangular VAR model using Cholesky decomposition. This stage is critical in determining the causal link and the mechanism by which oil supply news shocks echo across the macroeconomic landscape. The Cholesky decomposition allows the identification of orthogonal shocks, allowing for a clear explanation of the variables’ dynamic responses to the shocks.
The reliability and validity of the findings are critical to the success of this investigation. As a result, a thorough statistical study is initiated, which includes: 1. Eigenvalues of the Coefficient Matrices: A thorough examination of the eigenvalues of the coefficient matrices is conducted to ascertain the stability of the VAR model. 2. Impulse Response Function (IRF): An Impulse Response Function (IRF) analysis is performed to trace the response of the variables to shocks over time, providing a vivid depiction of the transient and long-term effects of oil supply news shocks on the U.S. macroeconomy.
The data used in the study ranges from January 1975 to December 2022, and it includes the oil supply surprise series, oil supply news shock series, Consumer Price Index (CPI), and Industrial Production Index (IPI) in the United States. Over the long time under discussion, the data series provide fertile ground for determining the macroeconomic repercussions of oil supply news shock.
The inquiry began with establishing the best lag duration, which is crucial for estimating the Vector Autoregression (VAR) model accurately. The optimal lag durations, according to the Akaike Information Criterion (AIC) and the Bayesian Information Criterion (BIC), are 20 and 17, respectively. The appropriate lag length must be determined since it highlights the lags that provide the best match for the VAR model. It is critical to find a balance between include enough delays to capture the underlying data structure and avoiding over-parametrization. Because it restricts free parameters more severely, the AIC suggests a more complex model with 20 lags, but the BIC predicts a somewhat simpler model with 17 delays. The difference in optimal lag time between AIC and BIC requests a conservative approach to VAR estimation in order to give a robust analysis free of overfitting or underfitting. According to Känzig’s findings, a comparable sophisticated approach to lag duration selection can increase the model’s anticipated accuracy as well as the veracity of the empirical data. The ideal lag length is used to estimate the reduced form VAR model and the triangle VAR model, which will be described further in the results sections. The following examination of these models attempts to reveal the complicated macroeconomic implications of oil supply news shocks in the United States from 1975 to 2022. Känzig’s precise technique is mirrored in the use of the AIC and BIC in determining the appropriate lag time, ensuring that the essential aspects of the study are anchored in statistical rigor. This careful methodology is essential for producing credible and insightful findings on the macroeconomic consequences of oil supply news shocks, shedding light on the interplay between oil market dynamics and the broader macroeconomic milieu in the United States over the long period under consideration.
The reduced form VAR was estimated using the Akaike Information Criterion (AIC) with a lag order of 20 once the appropriate lag duration was determined. The computed coefficient matrices across the various delays shed light on the time-dependent relationship between the variables of interest. Observing the diagonal elements throughout the delays reveals information about the persistence of shocks to the various variables. The negative coefficients in the third row, third column over multiple lags, for example, illustrate the autoregressive tendency of oil supply news shocks. The magnitude and sign of these coefficients throughout lags demonstrate the varying impact of past values on the current condition of oil supply news shocks. Furthermore, the off-diagonal parts indicate the variables’ intertemporal interdependence. Positive coefficients in the third row and second column across numerous lags, for example, highlight the influence of the oil supply surprise series on the oil supply news shock series. These connections represent the dynamic interactions in the macroeconomic landscape caused by oil supply news shocks. The estimated covariance matrix of residuals gives useful information about the variables’ contemporaneous connections. This matrix’s diagonal elements indicate the variance of the residuals for each variable, indicating the amount of unexplained variability in each series. The off-diagonal elements, on the other hand, disclose the contemporaneous correlations among the residuals of the various variables, indicating the system’s direct interrelationships. The negative correlation between the residuals of the consumer price index and the industrial production index, for example, suggests that these variables have an inverse connection. In comparison, Känzig’s research revealed comparable interrelations and dynamic patterns that underlay the complex macroeconomic ramifications of oil supply news shocks. The application of a comparable empirical paradigm broadens understanding of how such shocks reverberate through many economic aspects throughout time, providing a holistic view of the macroeconomic landscape. This estimate is a first step toward a more refined study using the Triangular VAR model, which aims to provide a structural understanding of the linkages and dynamic interactions that emerge between macroeconomic variables and oil supply news shocks. The following part will go deeper into unraveling the causal pathways and impulse response dynamics inherent in the system through the lens of Cholesky Decomposition.
The triangular VAR model, characterized by Cholesky decomposition, aids in isolating exogenous shocks in a multivariate system, allowing for a more thorough examination of the causal linkages between the variables under consideration. The computed coefficients in the Triangular VAR matrices (B1, B2, B3…, B8) describe immediate impact of one-time shocks on the predefined macroeconomic variables. The coefficients in matrix B1 indicate a complicated dynamic between the variables. A one-unit shock in oil supply news, for example, has a relatively large and negative influence on the third variable in the system, implying a significant inverse link. The magnitude of these coefficients provides insight into the macroeconomic system’s rapid reactions to unanticipated changes in oil supply news. Similarly, the following matrices from B2 to B8 reveal the continuous interactions across various lagged times. These matrices’ developing coefficients show how the system adapts over time after the initial shock. In certain matrices, the substantial negative coefficients associated with oil supply news reflect the assumed adversarial influence on macroeconomic variables. The decreasing magnitude of coefficients with increasing delays could indicate a gradual adaptation or fading shock effect over time, which is consistent with economic theories that propose the dissipation of shocks over long periods of time. Examining the residual covariance matrix is an important element of comprehending the triangular VAR model findings. The diagonal elements indicate the variance of each equation’s residuals, providing a measure of unexplained variability in each series. The off-diagonal elements represent the covariance between the residuals from distinct equations, providing insights into the series’ co-movements. The covariance matrix in this analysis reveals a significant variation in the residuals of the first equation, indicating a significant unexplained variability in the oil supply news shocks. The positive correlation between the first and fourth variables, as well as the negative covariance between the second and fourth variables, suggests that the macroeconomic structure has different directional linkages.
The analysis presents the eigenvalues of the companion matrices A and B over a series of iterations (from 1 to 20). These eigenvalues are complex numbers, although many are real, and their magnitudes are also provided. The eigenvalues for both A (Reduced Form VAR Coefficients) and B (Triangular VAR Coefficients) matrices appear to fluctuate over the iterations. In some iterations, the eigenvalues are real, while in others, they are complex with non-zero imaginary parts. The magnitudes of the eigenvalues also fluctuate, but they seem to stabilize or diminish as the iterations progress, especially for matrix A. The magnitudes of the eigenvalues provide insight into the behavior and stability of the system represented by these matrices. Lower magnitude eigenvalues, particularly those closer to zero, may indicate a more stable system. Matrix A shows a general decrease in the magnitude of its eigenvalues over iterations, possibly indicating a trend towards stabilization. Matrix B, on the other hand, has higher magnitude eigenvalues that do not show a clear decreasing trend. The stability or behavior of the system represented by matrix B might be different from that represented by matrix A. The presence of complex eigenvalues indicates oscillatory behavior in the system, with the frequency of oscillation typically related to the imaginary part of the eigenvalues. Real eigenvalues indicate growth or decay in the system, depending on whether the eigenvalue is positive or negative. The eigenvalues of matrix B tend to have higher magnitudes compared to those of matrix A across most iterations, suggesting that the system represented by matrix B is less stable or has different dynamics compared to the system represented by matrix A. Certain iterations show notable changes in the eigenvalues or their magnitudes. For example, in iteration 17, the eigenvalues of matrix B have significantly higher magnitudes compared to previous iterations. In some iterations, both matrices A and B have eigenvalues with similar magnitudes, such as in iteration 8 and 20.
The IRFs are generated using a Cholesky decomposition for identifying the shocks, and the responses of the variables to these shocks are plotted over time.
This graph shows how the Consumer Price Index (CPI) responds over time to a one-unit shock in the Oil Supply Surprise Series. The pattern of the graph would reveal that the oil supply effect is intense at first and disappears over time. Figure 3 Response of CPI to Oil Supply Surprise Series.
This graph illustrates how the Consumer Price Index (CPI) reacts over time to a one-unit shock in the Oil Supply News Shock. The new information regarding oil supply affect intensively at first and fluctuate over time and then disappear. Figure 4 Response of CPI to Oil Supply News Shock.
This graph delineates how the Industrial Production Index (IPI) evolves over time in response to a one-unit shock in the Oil Supply Surprise Series. It would indicate that a surprise in oil supply has a limited and short-lived effect on IPI Figure 5 Response of IPI to Oil Supply Surprise Series.
This graph depicts the response of the Industrial Production Index (IPI) to a one- unit shock in the Oil Supply News Shock over time. new information regarding oil supply affects industrial production temporally and short-time. Figure 6 Response of IPI to Oil Supply News Shock.
The complex relationship between oil prices and macroeconomic dynamics has long been a major focus of economic discourse, with the effects of oil supply news shocks being a critical aspect of this dialogue. This study set out on an analytical journey to investigate the macroeconomic effects of oil supply news shocks in the United States over a long period of time, from January 1975 to December 2022. This analysis has shed light on the intricate interplay between oil supply news shocks and key macroeconomic variables, particularly the Consumer Price Index (CPI) and the Industrial Production Index (IPI), using a careful analytical methodology. This study’s methodological rigor, which included a Vector Autoregression (VAR) model and a subsequent Triangular VAR model facilitated by Cholesky decomposition, provided a robust lens through which the dynamic interactions among the selected economic variables could be examined. The ideal lag duration was determined using the Akaike Information Criterion (AIC) and Bayesian Information Criterion (BIC), which ensured a balance between capturing the underlying data structure and avoiding over-parametrization. The empirical findings of the reduced-form VAR model and the triangular VAR model have revealed a complicated story of how oil supply news shocks ricochet across the United States’ macroeconomic environment. The Impulse Response Functions (IRFs) have shed light on the short-term and long-term consequences of these shocks on consumer pricing and industry productivity. The study found that shocks in oil supply news had an immediate and significant impact on the CPI and IPI, albeit with varied magnitudes and durations. The stability assessments, which included an examination of the eigenvalues of the coefficient matrices, have added to the analytical narrative by providing insights into the behavior and stability of the system under consideration. The oscillatory behavior suggested by complex eigenvalues, as well as the variable magnitudes of these eigenvalues over iterations, have provided a more comprehensive knowledge of the system dynamics. This study, which draws similarities with Känzig’s original work, has not only added to the existing body of knowledge, but has also provided a sophisticated understanding of the macroeconomic effects of oil supply news shocks in the United States. The study’s findings emphasize the need of policymakers and industry practitioners remaining sensitive to the informational dynamics around oil supplies, as these dynamics have significant implications for the broader economic environment. Furthermore, the empirical foundation presented by this work could serve as a springboard for future research endeavors investigating the macroeconomic effects of oil supply news shocks, not just in the United States, but across diverse geopolitical settings. The methodological apparatus used herein might be reproduced or developed to accommodate diverse economic situations and factors, resulting in a more comprehensive comprehension of the global economic fluctuations.