Fractional Cointegration, Commodity Markets,

Energy Prices, Agricultural Commodities, Long-

International Agri Commodities Memory Process, Investment Interdependence
Investment Interdependence in a
Fractionally Cointegrated VAR
1. Introduction
Framework
The global commodity markets are interconnected
and heavily influenced by price movements in the
Authors – Arnav Goel, Anshuman Bhartiya, Smit energy sector. Rising energy costs, particularly
Sanghvi, Aakash Satayavada, Pushkar Devasthali, crude oil prices, affect the production and
A Rameswar Patra, Reetish Rath, Vaibhav Kolse, transportation costs of agricultural commodities,
Vandan Doshi leading to volatility and co-movement across these
markets. Given the growing demand for biofuels
and the integration of global supply chains,
Highlights understanding the relationship between energy and
agricultural commodities is critical for investors,
● Examines the long-term equilibrium
policymakers, and market participants.
relationships between energy and
agricultural commodities using the FCVAR This research employs the FCVAR model, a robust
model. econometric framework that accounts for fractional
● Demonstrates significant spillover effects integration, to explore the long-term equilibrium
from energy prices (Brent Oil, Natural Gas, relationships between selected energy and
Gasoline) to key agricultural commodities agricultural commodities. The study aims to
(Wheat, Soybean, Corn). uncover the degree of market integration and the
● Provides insights into the implications for persistence of price shocks, providing valuable
investment strategies and risk management insights into the dynamics of commodity price
in commodity markets. transmission and its implications for investment
strategies.
Abstract

This study investigates the long-term

Research Objectives
interdependence between international energy and
● To examine the long-term equilibrium
agricultural commodities using a Fractionally
relationships between energy and
Cointegrated Vector Autoregressive (FCVAR)
agricultural commodities.
model. By analyzing daily price data from January
● To assess the persistence of price shocks
2004 to June 2024, this research identifies
across these interconnected markets.
significant cointegrating relationships and persistent
● To analyze the implications of these
co-movements driven by shared economic factors.
interdependencies for investment strategies
The findings reveal strong spillover effects from
and policy decisions.
energy prices to agricultural markets, suggesting
that fluctuations in energy costs play a crucial role
in shaping agricultural commodity prices. These
insights have important implications for investors
seeking cross-hedging opportunities and for 2. Related Literature Review
policymakers aiming to stabilize food prices and
ensure market efficiency. 2.1 Market Integration and Price Transmission

The literature on commodity markets highlights the

Keywords
significant impact of energy prices on agricultural
commodities. Studies by Baffes (2007) and 2.4 Identified Research Gaps
Nazlioglu (2011) demonstrate that rising oil prices
often lead to higher agricultural prices through Despite extensive research, several gaps remain:
increased costs of inputs like fertilizers and
transportation. Biofuel production further amplifies  Limited exploration of long-term
these linkages, particularly for crops like corn and dependencies using fractional integration
soybean (Serra & Zilberman, 2013). techniques like FCVAR.
 Insufficient analysis of the impact of
2.2 Long-Memory Processes in Commodity geopolitical events on the interdependence
Markets between energy and agricultural markets.
 A need for a comprehensive approach that
Research by Baillie and Bollerslev (1994) integrates both energy and agricultural
introduced the concept of long-memory processes sectors to assess investment
in financial time series, suggesting that shocks interdependence holistically.
have persistent but decaying effects over time.
Johansen and Nielsen (2012) extended this
concept to cointegration analysis, proposing the
FCVAR model to account for fractional integration. 3. Data
This model allows for a more flexible analysis of
long-term dependencies, making it suitable for 3.1 Descriptive Statistics Analysis
studying the interconnectedness of commodity
The dataset used for this analysis includes daily
markets.
price data for key energy and agricultural
commodities spanning from January 2004 to June
2.3 Empirical Evidence of Volatility Spillovers
2024. This extensive time frame captures multiple
The increasing financialization of commodity economic cycles, offering valuable insights into
markets has led to greater volatility and spillover both short-term fluctuations and long-term trends.
effects between energy and agricultural sectors The commodities analyzed include:
(Tang & Xiong, 2012). Studies using VAR, VECM,
● Energy Commodities: Brent Oil, Natural
and GARCH models have found strong evidence of
Gas, and Gasoline.
price transmission, particularly during periods of
● Agricultural Commodities: Wheat,
economic uncertainty (Nazlioglu et al., 2020).
Soybean, Corn, Cotton, Sugar, Rice,
However, few studies have employed the FCVAR
Coffee, and Cocoa.
model to capture the persistent co-movements
observed in these markets.

The descriptive statistics (Figure 1) provide a comprehensive summary of the key features of these
commodities' price behaviors over the analysis period.

Brent Natural
Statistic Gasoline Wheat Soybean Corn Cotton Sugar Rice Coffee Cocoa
Oil Gas
Count 4890 4890 4890 4890 4890 4890 4890 4890 4890 4890 4890
Mean 77.4 4.24 214.34 598.49 1118.2 461.36 77.89 16.97 13.3 148.63 2667.83
Min 19.33 1.48 41.18 293 527.25 186.25 39.14 8.45 7.06 86.65 1321
0.25 59.35 2.72 163.1 484.25 911 360.75 62.87 12.71 11.04 115.9 2227
0.5 74.32 3.56 209.9 562.25 1045 399.75 73.76 16.3 13.06 134.43 2525.5
0.75 97.6 4.84 264.64 694 1361.19 580.25 85.27 19.73 15.39 175.94 2929
Max 146.08 15.38 427.62 1425.25 1771 831.25 215.15 35.31 24.46 304.9 11878
Std 23.98 2.27 62.51 159.76 279.49 145.34 24.71 5.12 2.82 43.99 1051.37

Figure 1
Key Observations from Descriptive Statistics Brent Oil (std of 23.98) also demonstrates
significant volatility due to its exposure to global
A. Analysis of Mean Prices economic conditions, geopolitical events, and
changes in OPEC’s production policies.
Brent Oil has a mean price of 77.40, highlighting
its role as a critical global benchmark for energy Natural Gas, with a lower standard deviation of
pricing. It influences production costs across 2.27, indicates relatively less volatility compared to
industries, especially in transportation and other energy commodities. This suggests that
manufacturing. The high mean reflects sustained despite seasonal demand fluctuations, the
global demand and its sensitivity to supply chain availability of ample reserves and consistent supply
disruptions. from major producers helps stabilize its price.

Soybean follows with a mean price of 1118.20, C. Price Range and Identification of Outliers
making it the most valuable agricultural commodity
in the dataset. Its high price is driven by its dual The wide range between minimum and maximum
role in food production and biofuels, coupled with prices for several commodities highlights the
strong global demand for animal feed. potential for extreme price swings. For example,
Brent Oil prices varied from a low of 19.33 to a
Cocoa, with a mean price of 2667.83, is the highest high of 146.08, showing significant spikes during
among all agricultural commodities analyzed. The major economic or geopolitical crises, such as
elevated price level reflects its limited supply, the 2008 financial meltdown and recent
concentrated production regions (e.g., West Africa), conflicts affecting oil supply.
and vulnerability to climate factors affecting yields.
Cocoa’s maximum price of 11878, which is far
In contrast, Natural Gas shows a significantly lower above its mean of 2667.83, suggests the
mean price of 4.24. This can be attributed to presence of severe outliers. These extreme
abundant supply in key markets like the United values can be attributed to unexpected supply
States, advancements in extraction technologies, disruptions and sudden surges in demand from the
and seasonally influenced demand patterns. global chocolate industry.

Sugar has the lowest mean price (16.97), Natural Gas also has a notable range (1.48 to
suggesting a well-regulated market with relatively 15.38), reflecting sharp price fluctuations during
stable production levels. Government subsidies and severe weather events like cold winters, which
trade regulations often play a role in keeping sugar drive up demand for heating.
prices consistent.
D. Interquartile Range (IQR) Analysis
B. Volatility Insights
The IQR offers insights into the central tendency
Cocoa exhibits the highest standard deviation and stability of prices. Wheat and Corn have
(1051.37), indicating extreme price volatility. This moderate IQRs (e.g., Wheat ranges from 484.25 to
suggests that Cocoa is highly sensitive to supply 694.00), indicating relatively predictable price
shocks, weather disruptions, and geopolitical behavior. This stability is likely supported by
factors in its main production regions. The volatility consistent agricultural output and strategic
also reflects speculative trading, as Cocoa is a stockpiling practices by major producers.
key commodity in financial markets.
Cocoa and Soybean exhibit wider IQRs,
Among energy commodities, Gasoline (std of suggesting greater price variability even within the
62.51) shows substantial price variability, reflecting central 50% of observations. This reflects the
its direct link to crude oil prices and consumer influence of external factors such as adverse
demand, especially during peak travel seasons. weather conditions, global demand shifts, and
export restrictions that affect supply availability.
Rice (IQR from 11.04 to 15.39) and Sugar (IQR Soybean, as these fluctuations can impact food
from 12.71 to 19.73) show narrower spreads, security and global trade. Strategic reserves and
indicating more stable price distributions. These intervention measures (e.g., subsidies, export
commodities benefit from government controls) may be necessary to stabilize these
interventions, including price controls and markets during periods of crisis.
import/export regulations, which help maintain
consistent pricing. The post-2021 price surges seen across multiple
commodities reflect a new phase of heightened
uncertainty, driven by factors such as climate
change, ongoing geopolitical tensions, and
Insights for Investment and Policy Implications: disruptions in global supply chains. This
underscores the need for adaptive policy
The observed high volatility in Cocoa and frameworks and agile risk management
Gasoline suggests that these commodities carry approaches to handle future market volatility.
substantial risk for investors, making them
attractive for speculative trading but also requiring
robust risk management strategies. Derivative
instruments like futures contracts can be used to 3.2 Time Series Analysis of Price Trends
hedge against unexpected price swings.
The time series depiction of commodity prices
Natural Gas’s lower volatility and tighter IQR (Figure 2) provides a comprehensive view of the
indicate a more stable market environment, making price movements for selected energy and
it a potentially safer option for conservative agricultural commodities over the 20-year period
investors seeking exposure to the energy sector from January 2004 to June 2024. The chart
without the heightened risk seen in oil markets. illustrates the dynamics and co-movements of
different commodities, highlighting periods of
stability, volatility, and significant price shocks.
Policymakers need to be aware of the extreme
price volatility in key commodities like Cocoa and
Overview of Commodity Price Trends weather conditions, crop yields, and shifts in biofuel
demand:
The time series graph displays a diverse range of
price behaviors across the commodities analyzed, - Soybean prices show significant fluctuations
indicating varying degrees of sensitivity to global around 2012, likely influenced by drought
economic conditions, supply chain disruptions, and conditions in the U.S. Midwest, which
market-specific factors. impacted crop yields. Additionally,
increased demand for soy-based biofuels
Brent Oil exhibits the most dramatic price contributed to price increases.
fluctuations among all the commodities. It serves as
a global benchmark for crude oil, and its price - Wheat and Corn prices exhibit spikes during
movements reflect changes in global demand, the 2008 food crisis, driven by global
geopolitical risks, and supply shocks. The sharp supply shortages, export restrictions, and
spikes and subsequent drops are evident in several rising biofuel demand.
key periods –
- Another noticeable peak occurs in 2021,
- A significant dip during the 2008 financial reflecting disruptions from the COVID-19
crisis, followed by a strong recovery that pandemic and adverse weather events
peaked around 2014 due to robust global affecting production.
demand and OPEC’s production control.
Cocoa displays notable peaks and high volatility,
The most pronounced spike occurs post-2021, particularly around 2010 and again post-2021.
influenced by the COVID-19 pandemic and Cocoa production is concentrated in a few regions
subsequent recovery, supply chain issues, and (e.g., West Africa), making it vulnerable to supply
geopolitical events like the Russia-Ukraine shocks caused by political instability, adverse
conflict, which severely disrupted global oil weather conditions, and changes in global demand
supplies. from the chocolate industry.

A. Energy Commodities Analysis Stable Agricultural Commodities

Natural Gas prices show noticeable seasonal Rice, Sugar, and Cotton exhibit more stable
fluctuations, reflecting the impact of weather trends with relatively lower volatility compared to
patterns and heating demand, especially in colder other commodities. These staples tend to have
months. The time series indicates spikes during predictable production cycles and consistent
periods of extreme weather events (e.g., harsh demand:
winters) and disruptions in gas supply, as seen in
the mid-2000s and early 2020s.
- Rice prices show minimal fluctuations,
indicating stability in global rice production
Gasoline prices closely track the movements of
and strong government interventions,
Brent Oil but exhibit less volatility in some periods.
including subsidies and export controls,
This correlation is due to the direct relationship
aimed at ensuring food security.
between crude oil prices and refined gasoline
products. Gasoline prices show peaks during peak
- Sugar prices, while relatively stable, display
travel seasons and economic recoveries, while
occasional spikes related to changes in
demand shocks (e.g., during the pandemic
global trade policies, production issues, and
lockdowns) caused temporary declines.
shifts in demand for sugar-based ethanol.
B. Agricultural Commodities Analysis
- Cotton prices reflect changes in global
textile demand, weather conditions affecting
Soybean, Corn, and Wheat display moderate price crop yields, and trade policies. Notable price
volatility compared to energy commodities. These spikes around 2011 can be attributed to
agricultural products are sensitive to changes in supply shortages and strong demand from
the textile industry.
 C. Notable Market Events and External driven by common factors such as biofuel demand
Shocks and adverse weather conditions affecting crop
yields.
Several external shocks are evident in the time
series data, reflecting significant global economic Conversely, Rice and Sugar appear to be less
events - correlated with the broader market trends,
highlighting their relative stability and the influence
The 2008 financial crisis had a widespread impact of regulatory controls that buffer against extreme
on commodity prices, leading to sharp declines due price swings.
to reduced global demand and financial market
instability. Implications for Investors and Policymakers:

The COVID-19 pandemic in 2020 caused a The analysis of time series trends reveals
temporary collapse in demand for both energy and significant volatility in energy commodities,
agricultural commodities, followed by a rapid underscoring the need for effective hedging
recovery as economies reopened, highlighting the strategies, especially for investors exposed to oil
sensitivity of these markets to global demand markets. The strong co-movement between Brent
shocks. Oil and Gasoline suggests opportunities for cross-
hedging.
The Russia-Ukraine conflict in 2022 significantly
impacted energy markets, leading to a surge in For agricultural commodities, understanding
Brent Oil and Gasoline prices. The conflict seasonal patterns and the impact of external
disrupted key agricultural exports, causing price shocks is crucial for risk management. Price
spikes in Wheat and Corn due to supply chain stability in staples like Rice and Sugar indicates
disruptions. lower risk exposure, but sudden disruptions (e.g.,
trade restrictions, weather events) can still impact
D. Co-Movement and Correlation Analysis: these markets.

The time series graph suggests a degree of co- Policymakers must consider the broader
movement between energy and certain agricultural implications of commodity price volatility,
commodities, particularly during periods of particularly in light of recent events like the
economic crisis or geopolitical events. The strong pandemic and geopolitical conflicts. Stabilizing
correlation between Brent Oil and Gasoline prices prices through strategic reserves and market
is evident, reflecting their direct relationship. interventions can help mitigate the adverse effects
of extreme price fluctuations on consumers and
Agricultural commodities like Soybean and Corn industries.
also show co-movement during certain periods,
 4. Methodology

4.1 Introduction to the FCVAR Model

The Fractionally Cointegrated Vector

Autoregressive (FCVAR) model is employed in
this study to examine the long-term equilibrium
relationships between energy and agricultural
commodities. Unlike traditional Cointegrated Vector
Autoregressive (CVAR) models, which assume
integer integration (I(1) processes), the FCVAR
model accommodates fractional integration, This model formulation allows for the estimation of
allowing for more flexible analysis of time series both the fractional differencing parameters and the
data that exhibit long-memory properties and slow cointegrating vectors, making it a robust tool for
mean reversion. analysing persistent, slow-reverting behaviours in
the commodity markets.
In real-world time series, such as commodity
prices, deviations from equilibrium often persist for 4.2 Stationarity Testing - Augmented Dickey-
extended periods, indicating fractional integration Fuller (ADF) Test
rather than standard integration. The FCVAR model
captures these dynamics by allowing both the
The Augmented Dickey-Fuller (ADF) test was
variables and their deviations from equilibrium to be
conducted to assess the stationarity of the
fractionally integrated, offering a nuanced approach
commodity price series, a crucial step in
to identifying long-run dependencies that would be
determining the appropriate model specifications.
missed by conventional cointegration models.
Stationarity testing helps identify whether the time
series exhibits a unit root, indicating non-
The key equation of the FCVAR model can be stationarity, or if it is stationary, implying stable
expressed as follows: statistical properties over time.

Brent Natural
Statistic Gasoline Wheat Soybean Corn Cotton Sugar Rice Coffee Cocoa
Oil Gas
Test Statistic -2.249 -3.8965 -3.4553 -3.2062 -2.6277 -2.7264 -2.8638 -2.8256 -2.8074 -1.8381 -0.8076
p-value 0.189 0.0021 0.0093 0.0874 0.0874 0.0696 0.0497 0.0547 0.0572 0.3617 0.8169
Used Lags 5 32 23 23 30 18 32 19 31 22 32
Observations 4884 4857 4866 4866 4859 4871 4857 4857 4858 4867 4857
Critical Value
-3.4317 -3.4317 -3.4317 -3.4317 -3.4317 -3.4317 -3.4317 -3.4317 -3.4317 -3.4317 -3.4317
(1%)
Critical Value
-2.8621 -2.8621 -2.8621 -2.8621 -2.8621 -2.8621 -2.8621 -2.8621 -2.8621 -2.8621 -2.8621
(5%)
Critical Value
-2.5671 -2.5671 -2.5671 -2.5671 -2.5671 -2.5671 -2.5671 -2.5671 -2.5671 -2.5671 -2.5671
(10%)

Figure 3
The ADF test results (refer to Figure 3) showed stationary and do not require further differencing
mixed outcomes across the commodities: before model estimation.

Stationary Series: Natural Gas, Gasoline, Wheat, Non-Stationary Series: Brent Oil, Soybean, Corn,
and Cotton exhibited p-values below the 5% Sugar, Rice, Coffee, and Cocoa had p-values
significance level, indicating that these series are above 0.05, suggesting non-stationarity. These
series likely exhibit long-memory properties and are
well-suited for analysis using the FCVAR model, Strong Correlation between Soybean and Corn
which accommodates fractional integration. (0.89): The high correlation between these
agricultural commodities suggests shared
The identification of non-stationary series influences, such as biofuel demand and weather-
necessitates testing for fractional cointegration, as related supply shocks. Both crops are used
the FCVAR model can capture both short-term extensively in animal feed and biofuel production,
dynamics and long-term equilibrium relationships leading to co-movements in their prices.
for these variables.
Weak Correlations for Natural Gas: Natural Gas
4.3 Correlation Analysis shows weak or negative correlations with most
other commodities, indicating its relative
independence from the broader agricultural and oil
The correlation matrix (refer to Figure 4) provides
markets. The price of Natural Gas is influenced
an overview of the linear relationships between the
more by seasonal factors (e.g., heating demand)
selected commodities. Key observations include -
and specific supply dynamics, making it a
potentially useful diversification asset.
High Correlation between Brent Oil and
Gasoline (0.95): This strong positive correlation
The correlation analysis highlights the
reflects the direct relationship between crude oil
interconnected nature of some commodities while
and its refined product, gasoline. Price movements
also pointing out distinct, independent price
in Brent Oil are closely linked to gasoline prices,
movements for others, providing valuable insights
driven by changes in crude oil supply, refining
for risk management and investment strategies.
costs, and market demand.

Figure 4

4.4 Estimation Process in FCVAR

The estimation of the FCVAR model involves Lag Selection - The optimal lag length for the
several critical steps aimed at identifying and FCVAR model was chosen using information
analyzing long-term equilibrium relationships criteria such as the Akaike Information Criterion
between fractionally integrated time series – (AIC) and the Bayesian Information Criterion
(BIC). These criteria help balance model
complexity and goodness-of-fit, ensuring the
inclusion of relevant past observations in the significant roles in energy markets, agriculture, and
analysis. broader global supply chains.

Cointegration Rank Testing - Likelihood ratio (LR) Brent Oil, the most widely used global benchmark
tests were conducted to determine the number of
for crude oil pricing, is integral to the energy
cointegrating relationships, denoted as r. The
cointegration rank indicates the number of distinct market, influencing industrial operations and
long-term equilibria present among the selected transportation costs worldwide.
commodities.
Natural Gas, another key energy commodity, plays
Maximum Likelihood Estimation - The FCVAR a dual role in industrial processes and household
model parameters, including the fractional energy consumption.
differencing orders (d and b), the cointegration
matrix (β), and the adjustment coefficients (α), were
estimated using maximum likelihood methods. This On the agricultural side, Wheat and Soybean are
estimation captures the long-run equilibrium essential staples that drive global food supply,
relationships and the speed of adjustment towards pricing structures, and trade.
equilibrium.
Together, these commodities enable an analysis
Hypothesis Testing - Following the estimation, that spans individual price dynamics and explores
hypothesis tests were performed to impose the long-term equilibrium relationships between the
restrictions on the model parameters. For example,
energy and agricultural sectors.
tests for long-run exogeneity examined whether
certain variables do not respond to deviations from
equilibrium. These tests provide insights into the The choice of these commodities aligns with the
relative importance and influence of each research objective of examining fractional
commodity in the long-term relationships. cointegration, a statistical property signifying that
non-stationary time series are fractionally
4.5 Model Validation and Diagnostics integrated but exhibit co-movement over the long
run. This property is pivotal in understanding price
The residuals of the estimated FCVAR model were
dependencies in commodity markets, where long-
analysed for serial correlation using multivariate
white noise tests. The absence of significant serial term influences are often masked by short-term
correlation in the residuals indicates a well- volatility.
specified model, validating the adequacy of the
FCVAR framework for capturing the dynamics of Economic Influences on Price Dynamics
the selected commodities.
The price dynamics of the selected commodities
The validated FCVAR model was then used for are shaped by distinct economic and structural
forecasting and scenario analysis, offering insights factors. Energy commodities like Brent Oil and
into potential future trends based on the detected Natural Gas are particularly sensitive to
long-term relationships.
geopolitical events, supply-demand
imbalances, and advancements in energy
technologies. These factors contribute to short-
term price volatility while also establishing trends
5. Empirical Results and Discussion
that influence long-term price behavior.

5.1 Data Analysis: 2 Energy vs 2 Agricultural Conversely, agricultural commodities such as

Commodities Wheat and Soybean are predominantly affected
This analysis focuses on Brent Oil (C01), Natural by climate conditions, crop yields, and
Gas (NG1), Wheat (W-1), and Soybean (S1), international trade policies. These factors result
representing critical sectors of the global economy. in prolonged price trends influenced by systemic
These commodities were selected due to their disruptions and seasonal cycles. By capturing
these long-term and short-term influences, changes in Wheat and Soybean are less
fractional cointegration becomes a valuable susceptible to short-term shocks and more
analytical framework for exploring the intricate price influenced by long-term factors like crop cycles,
relationships in these markets. climate change, and global trade policies. Their
high persistence underscores the necessity of
Fractional Differencing and Persistence applying substantial fractional differencing to
Analysis achieve stationarity while preserving crucial long-
term dependencies.
The fractional differencing parameters (d-values)
provide insights into the persistence or "memory" in Implications for Analysis
the price series of each commodity. These values The persistence levels indicated by the d-values
quantify the degree of differencing required to make affirm the importance of fractional differencing
the time series stationary while retaining essential in preparing time series data for advanced
long-term dependencies. modelling techniques like the FCVAR
framework. These methods enable the
Brent Oil 0.377071 simultaneous examination of short-term fluctuations
and long-term equilibrium relationships, offering a
Natural Gas 0.454756 comprehensive understanding of price dynamics
across energy and agricultural markets.
Wheat 0.901566

Soyabean 0.881723 Significance of Fractional Differencing in

FCVAR

Table 5.1 (a) - Fractional Differencing The estimated d-values for each commodity
Parameters emphasize the critical role of fractional differencing
in the FCVAR model.
Brent Oil (d = 0.377):
The moderate d-value indicates that Brent Oil Fractional differencing serves as a method to
prices exhibit some long-term memory, where transform non-stationary time series into a
past price changes moderately affect future trends. stationary form while retaining the inherent
This behavior aligns with the dual nature of the oil long-term dependencies or memory present in
market, which experiences short-term shocks such the data.
as changes in production quotas or geopolitical
tensions alongside sustained trends driven by By applying fractional differencing, the time series
global energy demand and technological is appropriately pre-processed, allowing the
innovations in energy production. subsequent FCVAR model to effectively capture
Natural Gas (d = 0.454): both short-term dynamics (e.g., market shocks
Similar to Brent Oil, the d-value for Natural Gas or volatility) and long-term equilibrium
reflects moderate persistence. However, it exhibits relationships (e.g., co-movement between
slightly higher memory effects, influenced by energy and agricultural prices). This dual focus
factors like weather changes, infrastructure ensures a comprehensive analysis of commodity
development, and global policy shifts toward markets.
cleaner energy sources. These factors suggest that
while Natural Gas prices are subject to short-term 5.2 Johansen Cointegration Test Results
volatility, they also reflect enduring structural The Johansen cointegration test was conducted to
changes.
determine the presence and number of long-term
Wheat (d = 0.901) and Soybean (d = 0.882): equilibrium relationships among the selected
Agricultural commodities show significantly higher commodities - Brent Oil, Natural Gas, Wheat, and
persistence compared to energy commodities, with Soybean. This test is particularly effective for
d-values nearing 1. This indicates that price systems involving multiple variables, as it
identifies the number of cointegrating vectors Johansen test, which includes the trace statistics
and provides critical insights into the for hypotheses of 0, 1, 2, and 3 cointegrating
interdependencies of the series. vectors along with the corresponding critical values
at 90%, 95%, and 99% confidence levels.
Trace Statistics and Critical Values
Table 5.2(a) summarizes the results of the
Johansen Test Trace Statistics [4175.22729406, 1861.98702326, 183.64181788, 32.91590947]

Critical Values (90%, 95%, 99%) [44.4929, 47.8545, 54.6815]

[27.0669, 29.7961, 35.4628]
[13.4294, 15.4943, 19.9349]
[2.7055, 3.8415, 6.6349]

Eigenvalues [0.30423785, 0.23140205, 0.02335873, 0.00514836]

Table 5.2 (a) - Johansen Test Results

Rank (Null Trace Critical Value Conclusion

Hypothesis) Statistic (99%)

H0:r=0 4175.23 54.68 Reject H0: At least one cointegrating

relationship exists

H0:r≤1 1861.99 35.46 Reject H0: At least two cointegrating

relationships exist

H0:r≤2 183.64 19.93 Reject H0: At least three cointegrating

relationships exist

H0:r≤3 32.92 6.63 Reject H0: Four cointegrating

relationships exist

Table 5.2 (b) - Johansen Hypothesis

The results demonstrate that all trace statistics are significantly greater than their respective critical values,
consistently rejecting the null hypotheses.

The trace statistic for H0: r=0(4175.23) exceeds the 99% critical value (54.68) by a large margin, indicating
strong evidence of at least one cointegrating relationship. Similarly, the subsequent trace statistics (1861.99,
183.64, and 32.92) surpass their respective critical values, confirming the existence of four cointegrating
relationships among the commodities.

5.3 Eigenvalues and Strength of Relationships

Cointegrating Vector Eigenvalue Strength of Relationship

1 0.304 Strong

2 0.231 Moderate-Strong
 3 0.023 Weak

4 0.005 Very Weak

Table 5.3 (a) - Eigenvalue Relationship

The first eigenvalue (0.304) highlights the strongest considering both short- and long-term dynamics in
long-term relationship, reflecting significant co- commodity market studies.
movement among the selected commodities.
5.4 Vector Error Correction Models (VECM)
The second eigenvalue (0.231) also signifies a
The Vector Error Correction Model (VECM) reveals
relatively strong linkage, whereas the third and
the intricate dynamics between Brent Oil, Natural
fourth eigenvalues (0.023 and 0.005) represent
Gas, Wheat, and Soybean, uncovering their short-
weaker connections. term interactions and long-term equilibrium
relationships.
The ranking of eigenvalues underscores the
dominance of the first two cointegrating vectors in
capturing the long-term dynamics within the
system.

Interpretation and Implications

The presence of four cointegrating relationships
indicates that the selected commodities exhibit
significant long-term co-movement, driven by
shared economic factors and Table 5.4 (a) - VECM Results - 1
interdependencies. While individual prices may
fluctuate in the short term due to market-specific
shocks, the results confirm their tendency to adjust
toward a common equilibrium in the long run.

The strength of the first two cointegrating vectors,

as evidenced by the larger eigenvalues, suggests
that these relationships play a critical role in
shaping the overall dynamics of the system. These
Table 5.4 (b) - VECM Results - 2
findings are particularly relevant for econometric
modeling, such as Vector Error Correction Models
(VECM), which can capture both short-term
adjustments and long-run equilibrium relationships.

Conclusion
The Johansen cointegration test results confirm
that Brent Oil, Natural Gas, Wheat, and Soybean
are cointegrated, with four significant long-term Table 5.4 (c) - VECM Results - 3
relationships detected. The dominance of the first
two vectors highlights robust interconnections,
particularly between energy and agricultural
markets, which are likely influenced by global
economic trends and market forces. These results
provide a solid foundation for further modeling and
analysis, emphasizing the importance of
Table 5.4 (d) - VECM Results - 4
 The analysis is structured into stages, including lag
selection, cointegration testing, model estimation,
residual analysis, and forecasting.

Lag Selection and Model Order Determination

The initial phase involved determining the optimal
lag order (denoted as k) to capture the short-term
dependencies between Brent oil and the selected
agricultural commodities. The Akaike Information
Table 5.4 (E) - VECM Results - 5
Criterion (AIC) and Bayesian Information Criterion
(BIC) were utilized to evaluate various lag orders.
In the short run, significant linkages emerge, with
Brent Oil prices showing mean-reverting behavior
and being influenced by agricultural commodities  AIC Minimization: A lag order of k=3
like Wheat (-0.0027) and Soybean (-0.0054). This minimized the AIC, highlighting its ability to
underscores the impact of supply chains and better capture the dynamic relationships
shared production costs. Natural Gas exhibits between variables.
strong mean-reverting tendencies (-0.337) and  BIC Minimization: A lag order of k=0
largely independent short-term behavior, while minimized the BIC, indicating a simpler
Soybean maintains significant connections to both model with fewer parameters.
energy and agricultural markets.
Final Model Decision
In the long run, the cointegration analysis confirms To balance the trade-off between model complexity
a shared equilibrium among the commodities, and explanatory power:
highlighting persistent interdependencies driven by  A lag order of k=2 was selected for the
global economic forces and production linkages. analysis.
The error correction terms (ECTs) reveal varying
speeds of adjustment to deviations from  Serial correlation tests on the residuals
equilibrium: Soybean, with a rapid adjustment rate demonstrated that k=2 provides an
of 72.93%, demonstrates resilience to shocks, adequate explanation of the short-term
while Brent Oil, correcting at just 1.87%, reflects interactions while maintaining model
slower stabilization influenced by geopolitical and efficiency.
macroeconomic factors. The selected lag order strikes a balance between
capturing dynamic relationships and minimizing
These findings emphasize the interconnectedness
residual dependencies, ensuring robust short-term
of commodity markets and their varying responses
to shocks, offering critical insights for forecasting, relationship modeling.
risk management, and understanding global market
dynamics. The VECM framework thus serves as a
robust tool for analyzing the interplay of energy and
agricultural commodities.

5.5 FCVAR MODEL RESULTS - BRENT OIL VS

WHEAT, SOYBEAN, CORN

This report summarizes the application of the

Fractionally Cointegrated Vector Autoregressive
(FCVAR) model to analyze the long-term and short-
term relationships between Brent oil and three
agricultural commodities wheat, soybean, and corn. Table 5.5 (a) - FCVAR (1 Energy vs 3 Agriculture
Commodity)
Additionally, tests for serial correlation in the that there is one cointegrating relationship among
residuals showed acceptable results for k = 2, Brent oil, wheat, soybean, and corn.
indicating that this lag choice helps explain the
This finding suggests that while the prices of these
short-term interactions adequately.
commodities may vary in the short term, they are
bound by a stable, long-term equilibrium
relationship. For instance, any deviation in wheat,
soybean, or corn prices will likely see an eventual
correction toward equilibrium with Brent oil over
time.

Table 5.5 (b) - Serial Correlation of Residuals The model’s estimated fractional differencing
This section lays the foundation for subsequent parameter d was approximately 0.962, close to 1,
steps in the analysis, including the evaluation of indicating high persistence in the time series data.
cointegration and estimation of the FCVAR model. A d value near 1 suggests that price shocks to
Further insights into long-term relationships and these commodities have long-lasting effects, with
forecasting accuracy are presented in the following the impacts fading slowly over time. This level of
sections. persistence is characteristic of commodities, where
factors like supply chain disruptions, seasonal
5.5.1 Cointegration Rank Testing fluctuations, and geopolitical events can have
The next stage of the analysis focused on prolonged influences on prices. The model's ability
cointegration rank testing to determine the number to account for fractional integration, rather than
of stable, long-term relationships between Brent oil treating the data as purely stationary or purely
and the selected agricultural commodities - wheat, integrated, enhances the accuracy of long-term
soybean, and corn. This step is critical to identifying forecasting for these commodities.
whether these commodities exhibit co-movement
over the long term, even amidst short-term
fluctuations.

Methodology

5.5.2 Adjustment Dynamics and the Alpha

Table 5.5.1 (a) - Cointegration Rank Testing Matrix

The estimated cointegrating equation, also known

as the Beta matrix, revealed the specific long-term
relationships between the commodities. Brent oil
(represented as Var1 in the output) has a positive
relationship with wheat prices and a negative
relationship with soybean and corn prices.
Table 5.5.1 (b) - Likelihood Ratio Tests
This means that, in the long term, Brent oil and
The test results indicated that the most wheat tend to move in the same direction, while
statistically significant rank is r = 1, meaning soybean and corn prices tend to exhibit opposite or
weaker relationships with Brent oil. This dynamic
can be explained by the influence of Brent oil as a
primary input cost in agriculture - higher oil prices
can lead to higher costs for agricultural production,
impacting certain crops differently depending on
their sensitivity to energy prices.

The Alpha matrix, which shows the adjustment

speeds of each commodity towards the long-term
equilibrium, indicates that wheat and soybean
adjust more rapidly to deviations from
equilibrium, while Brent oil and corn exhibit
slower adjustments. In practical terms, this means
that wheat and soybean prices are more reactive to Table 5.5.3 (a) - Long – Run Matrix
imbalances, likely due to their higher demand
elasticity and shorter production cycles compared The short-term dynamics, captured by the Lag
to Brent oil and corn. Matrices (Gamma_1 and Gamma_2), reflect how
lagged values of each commodity affect others over
shorter periods. The relatively low values in these
matrices indicate that short-term interactions are
less significant than the long-term relationship
captured in the Beta and Alpha matrices. This
suggests that while there may be minor short-term
reactions among these commodities, they are
primarily driven by individual supply and demand
factors in the short run.

Table 5.5.2 – Alpha and Beta Matrix

5.5.3 Long-Run and Short-Run Effects

The Long-Run matrix (Pi) summarizes the overall

long-term relationships between Brent oil and the
agricultural commodities, combining the effects of
both the Beta (cointegration) and Alpha
(adjustment) matrices. This matrix shows relatively
small values, indicating that while there is a stable Table 5.5.3 (b) - Lag Matrix 1,2
equilibrium relationship, each commodity's long-
term impact on the others is modest.

This finding is typical in markets where

commodities are influenced by global supply and
demand but may not have strong direct
dependencies.

Table 5.5.3 (c) - Roots of the Characteristic

Polynomial
5.5.4 Residual Analysis and Model Fit

To assess the model's fit, we conducted a White

Noise Test on the residuals. Ideally, residuals
should exhibit white noise characteristics, meaning
they should have no significant patterns or
autocorrelations, indicating that the model has
captured the main dependencies.

The results of the test showed that while individual

variables (commodities) had residuals
approximating white noise, the multivariate
residuals were not perfectly white noise, suggesting
some remaining patterns. This outcome indicates Figure 5.5.5 Commodity Prices Forecast
that while the FCVAR model effectively captures
the primary long-term relationships, there may still 5.5.6 Conclusion
be minor dependencies left unexplained.
This FCVAR model analysis reveals a stable,
long-term relationship between Brent oil and
the agricultural commodities of wheat, soybean,
and corn. Despite their individual volatilities, these
commodities exhibit a common trend influenced by
Brent oil prices, especially in the long term.

 Wheat prices are positively correlated with

Brent oil, while soybean and corn show
Table 5.5.4 (a) - White Noise Tests weaker or opposite relationships.
 The high fractional differencing parameter
5.5.5 Forecasting Commodity Prices indicates that price shocks have long-lasting
effects, especially for wheat and soybean,
The final part of the analysis involved forecasting which adjust quickly back to equilibrium.
the prices of Brent oil, wheat, soybean, and corn for
the next 12 periods. In terms of practical application, this analysis is
valuable for anyone involved in commodity
The forecast plot reveals that wheat and soybean markets. The long-term dependencies identified
are projected to continue exhibiting high levels of here allow for better planning and risk management
volatility, consistent with their historical behaviour, strategies, while the forecast provides a data-driven
while corn prices are expected to remain relatively projection of future price trends.
stable.

This forecast provides valuable insights for

stakeholders in these markets, including farmers,
MODEL RESULTS - BRENT OIL VS
investors, and policymakers, allowing them to COTTON, SUGAR AND RICE
anticipate price trends and plan accordingly. The (More optimized than previous models)
dashed line in the plot demarcates the start of the
forecast period, highlighting the model’s predicted In this study, we applied the FCVAR model to
trajectories based on historical data. investigate the cointegration between Brent oil,
representing energy commodities, and three
agricultural commodities: cotton, sugar, and rice.
The primary aim is to determine whether these
commodities share a common stochastic trend,
which could imply a long-term equilibrium
relationship. Such analysis is essential for
understanding the dynamic linkages between
energy and agricultural markets, potentially
influenced by factors such as biofuel policies, cost- relationships among these commodities with a high
push inflation, and global economic shifts. degree of confidence in its adequacy.

Lag Selection Cointegration Rank Testing

The lag selection results from the FCVAR model The cointegration rank testing results shown below
indicate an optimal lag order of two for the analysis provide crucial insights into the long-term
of Brent Oil versus Cotton, Sugar, and Rice, with relationships between Brent Oil, Cotton, Sugar, and
the dimension of the system set at four (reflecting Rice prices. The table reports the Log-likelihood,
the four commodities under study). By comparing LR (likelihood ratio) statistic, and the p-values for
the AIC and BIC values, we find that the model with different assumed ranks (0 to 4). The LR statistic
k=1 minimizes both criteria (AIC = 48044.83 and tests the hypothesis of no cointegrating
BIC = 48295.05), suggesting it strikes the best relationships (or fewer cointegrating vectors)
balance between model complexity and fit among against the alternative of at least one cointegrating
the alternatives. relationship. A lower p-value indicates stronger
evidence for cointegration.

a. Rank 0 - the LR statistic is 58.934 with a p-

The likelihood ratio (LR) test for k=1 yields a value of 0.014, indicating significance at the 5%
significant LR statistic of 208.30 with a p-value of level, meaning we reject the null hypothesis of
0.000, reinforcing the suitability of this model no cointegration. This suggests that there is at
specification. Lower AIC and BIC scores generally least one cointegrating vector, pointing to a long-
imply a more efficient model that better captures term equilibrium relationship among the variables.
the underlying data structure without overfitting. b. Rank 1 - the LR statistic is 35.662 with a p-
value of 0.040, still significant but weaker than
The serial correlation tests on residuals reveal p- Rank 0.
values that are largely above conventional c. Rank 2 - the LR statistic drops further to
significance levels, suggesting that the residuals of 17.105 with a p-value of 0.122, which is not
the model are approximately white noise. For significant at the 5% level, suggesting limited
example, the p-values for the multivariate Q- support for additional cointegrating vectors beyond
statistic (pmvQ) and the various lags of the LM test the first one.
are all above 0.05, indicating no significant
autocorrelation in the residuals across multiple Finally, ranks 3 and 4 show LR statistics that are
lags. This finding implies that the model does a statistically insignificant (with p-values of 1.000),
reasonable job of accounting for temporal confirming that these ranks do not add further
dependencies in the data, with little systematic explanatory power.
pattern remaining in the residuals.
These results imply that a model with a
Such results are favourable, as they suggest that cointegration rank of 1 is appropriate, as it
the FCVAR model specification with k=1 provides a captures the essential long-term relationship
good fit to the data without leaving notable patterns among the commodities without unnecessary
unexplained. This model configuration, therefore, complexity. The presence of one cointegrating
allows us to explore cointegration and long-term
vector suggests a stable relationship over time
among Brent Oil, Cotton, Sugar, and Rice, which
could be influenced by shared economic factors
such as global supply-demand dynamics, currency
fluctuations, and market shocks. This finding has
practical implications for investors and policy-
makers, as it highlights interdependencies that
might be exploited for hedging, forecasting, and
decision-making in commodity markets.

Model Analysis

Fractional Differencing Parameter and Model Fit

The adjustment matrix (Alpha) shows how quickly
The fractional differencing parameter d=0.978 (with each commodity responds to deviations from the
a small standard error of 0.009) indicates that the equilibrium. Brent Oil has a near-zero adjustment
series are close to being fully integrated but exhibit coefficient (-0.001), indicating it minimally adjusts to
fractional behavior, suggesting a slow reversion to changes in the equilibrium, possibly acting as a
equilibrium. The close-to-one value of d implies that leading or influential commodity. In contrast, other
shocks to the system have lasting effects but commodities adjust more significantly, with Cotton
eventually revert over time. This slow mean- (0.001) and Rice (0.002) showing higher
reversion process is characteristic of markets that responsiveness to maintain equilibrium.
are interconnected, where adjustments happen
gradually.
Long-Run Matrix (Pi), Lag Matrix (Gamma), and
Roots of the Characteristic Polynomial -

The long-run matrix (Pi) shows the interaction

among the variables in the cointegrated system.
For instance, Cotton's effect on Brent Oil is -0.003,
suggesting a small negative influence.

The lag matrix (Gamma_1) illustrates short-term

adjustments. Notable values include Cotton's
influence on Brent Oil (-0.012) and Sugar’s
adjustment based on Cotton (0.003), signifying
short-term dependencies that differ from the long-
term equilibrium.
Cointegrating Equations (Beta) and Adjustment
Matrix (Alpha) - The roots of the characteristic polynomial, with
The cointegrating equation highlights the moduli close to 1, further indicate the model's
equilibrium relationship among Brent Oil, Cotton, stability and the persistence of shocks. Roots near
Sugar, and Rice. The equation shows Brent Oil (set the unit circle imply that the system is stable but
as 1 in the vector) having a direct link with other responsive, capturing long-term dependencies
commodities, with Cotton (-2.997), Sugar (6.365), effectively.
and Rice (-5.135) having varying impacts. These
coefficients signify the equilibrium relationship; for
instance, a 1-unit change in Brent Oil is associated
with roughly a 3-unit change in Cotton in the
opposite direction, a 6.4-unit change in the same
direction in Sugar, and a 5.1-unit change in Rice in
the opposite direction.
 Individual Variables -

Var1 (Brent Oil): The Q-statistic for Var1 is 27.921,

with a p-value of 0.000, which indicates significant
autocorrelation in Var1's residuals. The LM statistic
is 9.438, with a higher p-value of 0.307, indicating
no significant autocorrelation based on this test.

Var2 (Cotton): The Q-statistic of 53.266 and a p-

value of 0.000, which shows significant
autocorrelation in the residuals. The LM statistic is
14.701, with a marginal p-value of 0.065,
suggesting slight evidence of autocorrelation.

Var3 (Sugar): The Q-statistic is 38.200 with a p-

value of 0.000, also indicating significant
autocorrelation. The LM test statistic is 11.730 with
a p-value of 0.164, suggesting no significant
autocorrelation based on the LM test.

Var4 (Rice): The Q-statistic for Var4 is 18.000, with

a p-value of 0.021, which is marginally significant,
indicating slight autocorrelation. The LM test
statistic for Var4 is 7.850 with a p-value of 0.448,
showing no significant autocorrelation in the
residuals.

Multivariate White Noise Test on Residuals In summary, while the LM tests do not show
significant autocorrelation for any variable, the Q-
The Multivariate White Noise (MVWN) test on statistics for Var1, Var2, and Var3 indicate that
residuals is used to determine whether the some autocorrelation remains in the residuals for
residuals (errors) from the FCVAR model are white these variables, suggesting that the model may
noise, meaning they lack autocorrelation and have missed certain patterns.
exhibit purely random behavior. If the residuals
are white noise, it indicates that the model has This could imply that further refinement of the
effectively captured the structure of the data, model, such as adjusting lag structure or exploring
leaving no predictable pattern in the residuals. alternative model specifications, might be
necessary to fully capture the dynamics in these
 The overall Multivariate (Multivar) Q-statistic time series.
is 278.289, with a p-value of 0.000. This low
p-value (< 0.05) suggests that, collectively, Graphical Interpretation
the residuals for all variables exhibit some
level of autocorrelation, indicating that the
model may not have completely captured all
the dynamics in the data.
Co-Movement Patterns - Throughout the timeline, patterns in the graph indicate that these
there are notable instances where the commodities commodities do not operate in isolation over the
exhibit parallel movements, suggesting a level of long run; rather, they are influenced by shared
interdependence or shared influence. For example, economic factors, with Brent oil potentially acting as
a significant spike is observed for both Brent oil and a major driver given its role in agricultural
cotton around the mid-section of the graph, likely production and distribution costs.
due to shared economic or market events that
impact both energy and agricultural commodities. The fractional cointegration results highlight the
These patterns of simultaneous rise and fall persistence of price shocks from Brent oil to
indicate that external macroeconomic factors, such agricultural commodities. The high fractional
as global demand shifts, financial crises, or policy differencing parameter (𝑑 = 0.978) suggests that
changes, may be impacting these commodities short-term fluctuations in oil prices can have lasting
together. effects on agricultural commodities. For
stakeholders including investors, policymakers, and
Differences in Volatility - The graph demonstrates supply chain managers, understanding energy
that Brent oil experiences considerably higher price movements can provide valuable insight into
volatility compared to the agricultural commodities, future trends in agricultural prices, essential for
as evidenced by the sharp peaks and troughs. budgeting, pricing strategies, and planning in both
Cotton shows moderate volatility, reflecting sectors.
sensitivity to seasonal changes and supply-demand
dynamics in the agricultural market. In contrast,
sugar and rice display relatively stable, less volatile
price trends, which could be attributed to their 6. Conclusion and Policy Implications
nature as staple goods with more inelastic demand
compared to energy commodities.
This analysis underscores the economic linkage
between the energy and agricultural sectors. The
Distinct Seasonal and Long-Term Trends - Brent
long-term relationship implies that volatility in the oil
oil's sharp price fluctuations align with known global
market, often driven by geopolitical factors, supply
events impacting the oil market, such as
chain disruptions, or shifts in global demand, can
geopolitical tensions or production adjustments by
significantly impact agricultural commodity prices.
major oil-producing countries. Cotton also shows
For example, a surge in oil prices could elevate
seasonal fluctuations, likely due to cyclical
transportation and input costs (such as fertilizer),
agricultural production and demand patterns.
subsequently increasing the market prices for
Meanwhile, the trends in sugar and rice are more
agricultural products like cotton, sugar, and rice.
subdued, underscoring their relative stability and
the lower influence of external market shocks
For policymakers, these insights reinforce the need
compared to energy commodities.
for integrated risk management strategies that
account for the interconnectedness of energy and
This graph provides a visual confirmation of the
food prices. Food security initiatives and inflation
hypothesis that energy prices can indirectly
control measures should consider energy prices as
influence agricultural prices over the long term.
a factor influencing food costs, particularly during
Specifically, spikes in Brent oil prices may affect
periods of high oil price volatility.
agricultural production costs (e.g., fuel,
transportation, and fertilizer costs), which in turn
From an investment perspective, the FCVAR
may impact agricultural commodity prices over
results offer guidance on portfolio diversification.
time. Thus, the observed co-movement suggests
The interdependent nature of these markets
that oil price trends could serve as an indicator of
suggests that traditional diversification may not
cost pressures in agricultural markets.
provide complete insulation from cross-sectoral
price shifts. Therefore, investors seeking to hedge
Conclusion against commodity price volatility should be aware
of potential spillover effects from energy to
The FCVAR model, combined with visual analysis agricultural markets.
of the graph, reveals a meaningful fractional
cointegrating relationship between Brent oil and In conclusion, the FCVAR model provides
selected agricultural commodities (cotton, sugar, significant insights into the dynamics between Brent
and rice). This model outcome and the observed oil and agricultural commodities, highlighting the
interdependence of energy and food markets. This
interconnectedness calls for cross-sectoral
awareness and strategic planning, particularly
during times of energy crises or agricultural supply
disruptions. Monitoring energy market conditions
could serve as an early indicator of agricultural
price trends, supporting more resilient and informed
decision-making across these sectors.

References

 Baillie, R. T., & Bollerslev, T. (1994). Cointegration, fractional cointegration, and exchange rate
dynamics. Journal of Finance, 49(2), 737–745. [Link]
 Baffes, J. (2007). Oil spills on other commodities. Resources Policy, 32(3), 126–134.
[Link]
 Johansen, S., & Nielsen, M. Ø. (2012). Likelihood inference for a fractionally cointegrated vector
autoregressive model. Econometrica, 80(6), 2667–2732. [Link]
 Nazlioglu, S. (2011). World oil and agricultural commodity prices: Evidence from nonlinear causality.
Energy Policy, 39(5), 2935–2943. [Link]
 Nazlioglu, S., Hammoudeh, S., & Gupta, R. (2020). Oil and agricultural commodity markets:
Interdependence and implications. Energy Economics, 90, 104866.
[Link]
 Serra, T., & Zilberman, D. (2013). Biofuel-related price transmission literature: A review. Energy
Economics, 37, 141–151. [Link]
 Tang, K., & Xiong, W. (2012). Index investment and financialization of commodities. Financial Analysts
Journal, 68(6), 54–74. [Link]
 Wright, B. D. (2011). The economics of grain price volatility. Applied Economic Perspectives and Policy,
33(1), 32–58. [Link]
 Zivot, E., & Wang, J. (2006). Modeling financial time series with S-PLUS. Springer.
[Link]