Lade Inhalt...

Modelling and forecasting monthly petroleum prices of Ghana using subset ARIMA models

Bachelorarbeit 2012 104 Seiten

VWL - Statistik und Methoden






List of tables

List of figures

Chapter 1: Introduction
1.1 Background of the Study
1.2 Statement ofProblem
1.3 Objectives of the Study
1.4 Research Questions
1.5 Significance of the Study
1.6 Scope of the Study

Chapter 2: Related Review of Literature
2.1 Introduction
2.2 Theoretical Framework
2.2.1 The Economics Importance of Oil
2.2.2 History of Oil and Gas Exploration
2.2.3 Ghanaian Policy Subsidy
2.2.4 Supply Side Channel
2.2.5 Demand Side Channel
2.2.6 Economic Policy Relations
2.3 Empirical Framework
2.3.1 Forecasting

Chapter 3: Review of Basic Theory and Methods
3.1 Introduction
3.2 Research Design
3.3 Source ofData
3.4 Statistical Analysis Procedure
3.4.1 Box-Jenkins Methodology

Chapter 4: Preliminary and Further Analysis
4.1 Introduction
4.2 Preliminary analysis
4.3 Further analysis

Chapter 5: Results and Discussion
5.1 Introduction
5.2 Discussion ofResult
5.2.1 Stationarity
5.2.2 Model Identification
5.2.3 Model Estimations
5.2.4 Model Verification or Diagnostic Checking
5.2.5 Forecasting Stage

Chapter 6: Conclusion and Recommendation
6.1 Conclusions
6.2 Recommendations




The study is an attempt to build a univariate Time Series Model to forecast monthly petroleum prices for 2010/2011, from January 1990 to September 2010, since national petroleum agency (NPA) is failing to plan for fluctuation of petroleum prices. The data was source from the website of Bank of Ghana. The study employs Box-Jenkins methodology of building Seasonal Autoregressive Integrated Moving Average (SARIMA) model to achieve various objectives. Different selected models were tested by Residual plots of Autocorrelation and Partial Autocorrelation and Ljung Box Q statistic to ensure adequacy of results. The results reveal that demand and supply, crudel oil prices, gasoline, natural disasters and government regulations are some of factors that can influence fuel prices and ARIMA(1,1,5)x(1,0,1)11 is the best model for forecast. The future values expose that during the months to come; petroleum prices are going to experience an insignificant increase. In light of the forecast, I know Ghana will ascertain a healthy state of economy.


I would partially wish to single out my Head of Department Mr. Solomon Sarpong who was my lecturer and supervisor for his guidance and patience contributed immensely to the success of this work.

My gratitude also goes to Mr. Nashiru Suleman. I am extremely grateful to his friendly advice and comments at all levels of the study.

A last of word of gratitude goes to my very dear friend Angela Bioh for her support throughout this study.


I dedicate this work to my former lecturer Mr. Leonard Kyei, for his advice when choosing my profession.


Table 4.2: Summary Statistics ofMonthly Petroleum Prices per Barrel

Table 4.3: Detecting the trend in the Series

Table 4.4: ARIMA(l,l,l)x(l,0,l)u model fitted

Table 4.5: ARIMA(l,l,l)x(l,0,2)ll model fitted

Table 4.6: Comparative Result of the Tentative Model

Table 4.7: Modified Box-Pierce (Ljung-Box) Chi-Square statistic of ARIMA(l,l,l)x(l,0,l)ll

Table 4.8: ARIMA(l,l,l)x(l,0,l)ll model fitted

Table 4.9: Modified Box-Pierce (Ljung-Box) Chi-Square statistic of ARIMA(l,l,l)x(l,0,l)ll

Table 4.l0: ARIMA(l,l,2)x(l,0,l)ll model fitted

Table 4.ll: Modified Box-Pierce (Ljung-Box) Chi-Square statistic of ARIMA(l,l,2)x(l,0,l)ll

Table 4.l2: ARIMA(l,l,3)x(l,0,l)ll model fitted

Table 4.l3: Modified Box-Pierce (Ljung-Box) Chi-Square statistic of ARIMA(l,l,3)x(l,0,l)ll ARIMA(l,l,4)x(l,0,l)n

Table 4.16: ARIMA(1,1,5)x(1,0,1)11 model fitted

Table 4.17: Modified Box-Pierce (Ljung-Box) Chi-Square statistic of ARIMA(1,1,5)x(1,0,1)n

Table 4.18: ARIMA(2,1,1)x(1,0,1)11 model fitted

Table 4.19: Modified Box-Pierce (Ljung-Box) Chi-Square statistic of ARIMA(2,1,1)x(1,0,1)11

Table 4.20: ARIMA(2,1,2)x(1,0,1)u model fitted

Table 4.21: Modified Box-Pierce (Ljung-Box) Chi-Square statistic of ARIMA(2,1,2)x(1,0,1)11

Table 4.22: ARIMA(2,1,3)x(1,0,1)11 model fitted

Table 4.23: Modified Box-Pierce (Ljung-Box) Chi-Square statistic of ARIMA(2,1,3)x(1,0,1)11

Table 4.24: ARIMA(2,1,4)x(1,0,1)11 model fitted

Table 4.25: Modified Box-Pierce (Ljung-Box) Chi-Square statistic of ARIMA(2,1,4)x(1,0,1)11 ARIMA(2,l,5)x(l,0,l)n

Table 4.28: ARIMA(3,1,1)X(1,0,1)11 model fitted

Table 4.29: Modified Box-Pierce (Ljung-Box) Chi-Square statistic of ARIMA(3,1,1)x(1,0,1)n

Table 4.30: ARIMA(3,1,2)X(1,0,1)11 model fitted

Table 4.31: Modified Box-Pierce (Ljung-Box) Chi-Square statistic of ARIMA(3,1,2)x(1,0,1)11

Table 4.32: ARIMA(3,1,3)x(1,0,1)11 model fitted

Table 4.33: Modified Box-Pierce (Ljung-Box) Chi-Square statistic of ARIMA(3,1,3)x(1,0,1)11

Table 4.34: ARIMA(3,1,4)x(1,0,1)11 model fitted

Table 4.35: Modified Box-Pierce (Ljung-Box) Chi-Square statistic of ARIMA(3,1,4)x(1,0,1)11

Table 4.36: ARIMA(4,1,1)x(1,0,1)11 model fitted

Table 4.37: Modified Box-Pierce (Ljung-Box) Chi-Square statistic of ARIMA(4,1,2)x(1,0,1)11 ARIMA(4,l,3)x(l,0,l)n

Table 4.40: ARIMA(5,l,l)x(l,0,l)ll model fitted

Table 4.4l: Modified Box-Pierce (Ljung-Box) Chi-Square statistic of ARIMA(5,l,l)x(l,0,l)ll

Table 4.42: ARIMA(5,l,l)x(l,0,l)ll model fitted

Table 4.43: Modified Box-Pierce (Ljung-Box) Chi-Square statistic of ARIMA(5,l,2)x(l,0,l)ll

Table 4.44: The Result of the Best SARIMA Model

Table 4.45: ARIMA(l,l,5)x(l,0,l)llmodel fitted

Table 4.46: Correlation Matrix of the Estimated Parameters

Table 4.47: Forecasting Values of ARIMA(l,l,5)x(l,0,l) Model for Petroleum Prices (in US$ per Barrel)

Table 5.l: Initial Parameters Estimates

Table 5.2: Comparative Results from Various Models

Table 5.3: Optimal Model for Forecasting

Table 5.4: Forecast on the Basis of Optimum Model


Figure 4.1: Time series plot of petroleum prices of 1990-2010

Figure 4.2: Natural logarithm transformation time series plot of petroleum prices of 1990-2010

Figure 4.3: Plot of autocorrelation function (ACF) of petroleum prices of 1990­2010

Figure 4.4: Plot of partial autocorrelation function of petroleum prices of 1990­2010

Figure 4.5: Plot of autocorrelation function (ACF) of petroleum prices of 1990­2010 (1st difference)

Figure 4.6: Plot of partial autocorrelation (PACF) of petroleum prices of 1990­2010 (1st difference)

Figure 4.7: Graph of autocorrelation function (ACF) of residuals

Figure 4.8: Graph of partial autocorrelation function (PACF) of residuals.. .65

Figure 4.9: Residual plots for monthly petroleum prices

Figure 4.10: Actual and forecasts of petroleum prices

Figure 5.1: Graph of autocorrelation function (ACF) residuals

Figure 5.2: Graph of partial autocorrelation residuals

Figure 5.3: Graphical summary of the forecast



The significance of oil as an input into the macro economy, and its ability to predict future growth in economic variables, suggests that the oil price is an important variable to consider in the context of consumption.

Petroleum (from Greek: petra (rock) plus Latin: oleum (oil)) or crude oil is a naturally occurring, flammable liquid consisting of a complex mixture of hydrocarbons of various molecular weights and other liquid organic compounds, that are found in geologic formations beneath the Earth’s surface Wikipedia, (2012). Petroleum is also called fossil fuel. It is called a fossil fuel because it was formed from the remains of tiny sea plants and animals that died millions of years ago. When the plants and animals died, they sank to the bottom of the oceans. Here, they were buried by thousands of feet of sand and sediment, which turned into sedimentary rock. As the layers increased, they pressed harder and harder on the decayed remains at the bottom. The heat and pressure changed the remains and, eventually, petroleum was formed. Petroleum deposits are locked in porous rocks almost like water is trapped in a wet sponge. When crude oil comes out of the ground, it can be as thin as water or as thick as tar. Petroleum is called a nonrenewable energy source because it takes millions of years to form, (, 2012).

In the late 1800s, economic development depended largely on the strength of man, animal, and to limited use water, wind, and steam. Economic conditions progressed from clans of primitive gatherers to reasonably advanced agricultural societies. As the industrialized age was in its early stages, the primary sources of energy were wood, coal, and whale oil. The environmental impact of utilizing these energy sources was extreme and growing worse. Petroleum has been a known commodity through areas of natural seepage to the surface since early man, but was generally inaccessible to the masses. Its full potential had not yet begun to be realized. Population growth placed great economic stress on traditional fuels, and rising prices encouraged the search for alternatives.

In 1854, Canadian Abraham Gesner discovered an alternative to whale oil for use in lighting lamps by distilling kerosene from coal and oil. Edwin Lamentine Drake drilled the first successful oil well in 1859 in Titusville, Pennsylvania, and created an industry that would go on to make petroleum the most significant single economic factor to date over the entire history of the world. Industries not possible without petroleum and its derivatives now dominate world economy. Petroleum exists within the substrata of the earth in a number of forms depending on the hydrocarbon source, maturation process, elemental exposure, and the temperature and pressure of the reservoir (, 2012).

Crude oil is the most common form of petroleum and may range in specific gravity from being as light as 0.73 to being as heavy as over 1.07. Under standard surface conditions, the lightest crude oil will be a thin liquid of a brown or brownish-blue/green color, while the heaviest will be a black solid tar-like substance. The corresponding physical properties and chemical compositions also vary widely and determine which products may be derived from each specific crude oil and what refining processes will be most efficient in doing so. Gasoline is the primary fuel used to power internal combustion engines widely used in vehicles and machines. Jet fuel is used to power the extremely powerful engines that drive high performance aircraft (, 2012).

Oil prices have averaged $19.27 per barrel, in 1996 dollars, over the period 1947-1997. Prices have only exceeded $22.00 per barrel in response to war or conflict in the Middle East (Verleger, 1993). The major oil price shocks during this period were the 1973 Arab oil embargo, the 1979-80 events in Iran and Iraq, and the 1990 invasion of Kuwait. As a result of the Yom Kippur war, crude oil price, which had stayed between $2.50 and $3 since 1948, quadrupled from $3 per bbl in 1972 to $12 per bbl by the end of 1974. The revolution in Iran and the subsequent Iran-Iraq war more than doubled prices from $14 per bbl in 1978 to $35 perbbl in 1981 (Energy InformationAdministration, 1997).

The ensuing world recession and development of alternative energy sources, led to a decrease in demand and falling prices for most of the 1980s. Effort by Organisation of the Petroleum Exporting Countries (OPEC) to set production quotas, in an effort to shore up prices was largely unsuccessful, as member nations routinely violated limits. Prices surged again in 1990-91, in response to the uncertainty created by the Iraq invasion of Kuwait, but retreated in the face of an US-led military resolution of the conflict and increased supply from other nations. Recession in the US saw prices decline, until in 1994, inflation- adjusted prices attained their lowest level since 1973. Subsequently, a strong US economy and growth in Asia led to a firming up in demand. World petroleum demand grew 2.8% in 1995 and 2.2% in 1996. Oil prices increased by approximately $6 per barrel over the course of 1996, Petroleum (1996). Despite Iraqis re-entry into the world market in December 1996, the price recovery continued well into 1997, until the recent sharp downturn brought about by the Asian economic crises and the mild 1997-98 winter (Energy Information Administration, 1997).

Distillates are used to produce lower grade fuels such as kerosene for use as a heating fuel and diesel fuel for use in powerful vehicles such as trucks, ships and industrial machinery. Other even lower grade fuels are used to provide energy to industrial processes not requiring the same combustion quality required by higher speed engines. Distillates also yield a wide variety of waxes that are turned into products used for lining milk cartons, as water repellant coatings, cosmetics, electrical insulators, sealants, medicinal tablet coatings, crayons, candles, and many other everyday items winter (Energy Information Administration, 1997).

The global oil market is incredibly volatile. Unpredictable events like political unrest and natural disasters can spike the price of a barrel, translating into higher gasoline prices. Moreover, the long term price trend in the oil market is very clear prices have risen for decades, and they will continue to. This has a significant impact on both business and households, driving up transportation costs as well as the cost of anything that relies on petroleum during either production or delivery to market.

Since the beginning of January this year, organised labour and other interest groups including teachers kept mounting pressure on the government, amidst threats of strikes because of escalating economic hardships, which they claimed had come about because of increase in prices of petroleum products. The country’s unions demanded that the government restores the fuel subsidies in order to mitigate the harsh economic and social realities, threatening to advise themselves if President Evans Mills’s administration failed to do so by the latter part of last year. This was as a result of the withdrawal of subsidies on 29 December, 2011. Prices of petrol and diesel went up by 15 percent each at GH01.7548 per litre ($1.1348) and GH01.77O9 per litre ($1.1452) respectively, while LPG went up by 30 per cent at GH01.3619 per kilo ($0.8807). But the prices of kerosene, premix fuel and Renewable Fuel Oil (RFO) remain unchanged.

The price of crude did not rise from $12 in early 1999 to nearly $60 because the world suddenly ran out of oil. On the contrary, the world supply of petroleum has risen 10 percent since then, according to the International Energy Agency (IEA), from 65.8 million barrels a day in 1999 to 72.5 million in 2004. Cambridge Energy Research Associates estimates global oil production capacity will increase at least twice that rapidly over the next five years by as much as 16 million barrels a day by 2010. Oil prices did not quintuple after 1999 because Americans suddenly switched from mini-cars to SUVs. On the contrary, if all passenger cars, pickups and SUVs were replaced with bicycles, the United States would still import a lot of oil. United State import nearly 58 percent of all petroleum, yet only 45 percent of each barrel is used to produce gasoline, and a significant portion of that gasoline is used in delivery vans and taxis. Commuter and leisure driving accounts for little more than 40 percent of the oil we consume far less than the amount we import. The rest of each barrel of crude is used for heating oil and diesel fuel for trucks, bus, farm machinery and ships (23 percent), petrochemicals (17 percent), jet fuel (9 percent), asphalt (4 percent) and propane (4 percent) Alan (2005).

U.S. industries use petroleum to produce the synthetic fiber used in textile mills making carpeting and fabric from polyester and nylon. U.S. tire plants use petroleum to make synthetic rubber. Other U.S. industries use petroleum to produce plastic, drugs, detergent, deodorant, fertilizer, pesticides, paint, eyeglasses, heart valves, crayons, bubble gum and Vaseline. When the cost of oil goes up, production costs are increased and profits reduced for industries that depend on oil. Producer costs not consumer gasoline costs are the reason high oil prices threaten to shrink industrial production of goods directly affected and also of energy-intensive products such as aluminum and paper. This threat affects all new and old industrial economies, whether those nations import or export oil. The United States may be least vulnerable because of superior energy efficiency and a larger service sector, Alan (2005).

The marketplace forces of supply and demand determine the price of fuel. If demand grows or if a disruption in supply occurs, there will be upward pressure on prices. By the same token, if demand falls or there is an oversupply of product in the market, there will be downward pressure on prices. Those principles apply at the service station level as well. If a retailer prices its gasoline too high, and without regard to competition, the retailer’s customers may take their business to another station with lower prices. If a retailer loses enough volume, the retailer may then reduce prices in order to retain its customers. Competition among retail outlets thus affects pricing. You may notice that sometimes there are price differences between two gasoline stations on a busy street corner and between those outlets and the only station on a long stretch of highway. More choices generally mean more competition for business. And although retail outlets may sell gasoline carrying the brand of a major oil company, most dealerships are owned and operated by independent business people who are free to set the prices for their products and services.

As Ghana looks forward to becoming oil producing country, Ghana government, co-operate sectors and ordinary citizens are increasingly going to be paying closer attention to trends in global oil and gas prices. Although oil is not expected to be such a dominant force in Ghana"s economy as it is in the economies of some other African countries such as Nigeria or Angola. Its fluctuating prices are bound to effect development plans of the country.

According to a report made available to Ghana Business and Finance by Damina (2005), said that several African oil exporting countries including Ghana and other countries such as Algeria, Chad, Cote d'Ivoire, DR Congo, Egypt, Garbon, Lybia, Maritania, Nigeria, and Sudan are likely to experience rude budgetary awakening and consequential political shocks if or when in 2011, oil prices likely collapse to recent 5 to 10 years historical average prices of between $51 to $71 per barrel. For most African oil exporting economies, global oil price levels have a significant impact of government revenues because of the significant role that oil exports play as a percentage of the Gross Domestic Product (GDP). Oil generates an exogenous flow of revenue that has a significant impact on the budget process. Although Ghana will not produce enough oil will not become its major it an OPEC member and oil will not become its major export revenue earner, its citizens and business community will hence have to pay more attention to decision of OPEC and for developments in the sector, especially the decision and actions of other African produce.

According to Damina (2005), with European energy importing countries already enacting measures and dracontium, US spending cuts certain to take place after the November mid-term elections, global oil price levels increasing will be dictated by Chinese GDP growth patterns. Since 2001, the swing in global oil prices have carefully tracked Chinese growth pattern. Between 2000 and 2005 China and the US (the two largest consumers of crude oil) had a combined GDP growth rate of almost 12% (with China accounting for 78%).

However, by early 2010, while the combined GDP of China and US remained stagnant at growth of 12% in 2000 to 2004 period. Yet, during the same period average crude prices more than doubled from 2000 to 2004 monthly average ofjust $30 per barrel to over $70 per barrel in average by 2009.

Consumers worldwide have watched the cost of petroleum prices continue to fluctuate throughout the year. This raises the question, "Why does petrol prices rise and fall?" In the long term, the greatest single factor influencing petroleum prices is the cost of crude oil. However, marketplace forces of supply, demand and competition can have a significant effect on the price of petroleum in the short term.

Each time you pull up to the pump or open your utility bill, you may notice the price of fuel may have changed. There are many factors that can influence fuel prices. Some of them are:

- Demand and Supply
- Crude Oil Prices
- Gasoline
- Natural Gas
- Government Regulations
- Natural Disasters, etc.

In the light of the above, it could be understood that the high price of oil will invariably affect revenue mobilisation, expenditure (and therefore the fiscal position of government) and inflation. The study is an attempt to check the fluctuation in petroleum prices and forecast for 2011.


Nowadays, the increased oil prices worldwide are having a great impact on all economic activities. Like many countries, Thailand depends heavily on oil as a source of energy. Thai government by Prime Minister Thaksin Shinawatra called the Thai people to help save energy by limiting their driving speed to 90 kilometers an hour, turn off air conditioners when not necessary, and include the use of alternative energy as the production ofbio-diesel and ethanol.

Over the years there has been a fluctuation in petroleum prices, and a close consideration of the demand and supply side effects that sparked these price changes shows there is high probability that this changes will continue in the outlook period and beyond. West African Monetary Agency (2008) concluded that increase in world oil prices have been shown to worsen fiscal deficit positions of oil importing countries like Ghana. For this reason, we believe that if the government can see ahead of monthly petroleum prices, our deficit would not be worsen.


The objectives of this study were divided into two:

Main Objective

The main objective of this study is to generate forecasts of petroleum prices for January 2010to September 2011.

Specific Objective

- To suggest suitable forecasting ARIMA model for generation of forecasts.
- To examine the growth of the petroleum prices.
- To determine some of the possible causes of the fluctuation in the petroleum prices.


- Is there a trend in the monthly petroleum prices?
- Is the data stationary?
- Is there any seasonal variation in the data?
- What is the best or adequate ARIMA model to forecast petroleum price?
- What are the predicted values of the petroleum price?


The subject matter of forecasting is uncertainty. Uncertainty means no clarity of future. In a state of uncertainty, organizations make decisions based on historical experience or even gut feeling. The decisions thus taken through gut feeling are detrimental to organizations. This necessitates scientific approach to decision making.

Forecasting is one such scientific technique which helps organizations/processes in decision making in the state of uncertainty. In this report we are making an earnest effort to take you through one of the sophisticated forecasting techniques called ARIMA (Autoregressive Integrated Moving Average).

We believe this report would be useful to better give the appropriate policy responses, to mitigate the effects of such fluctuations as and when they occur. Again, it will serve as a source of reference to students who want to undertake studies in area of time series analysis using Box-Jenkins (1976) methodology.


The study covers the periods of 1990-2010 of petroleum prices in Ghana. The petroleum prices are in monthly bases (from January-December) for each year.



A great deal of attention has been given to oil price fluctuation. Empirical studies that these oil price shocks were immediately followed by worldwide recessions and periods of inflation spurred considerable research. By looking at the channel of transmission of oil price shocks to the economy, many researchers have argued that fluctuations of oil prices are linked to macro economic performance. The question is what causes of these fluctuations in oil prices are. The question became more relevant in early periods (1970s and early 80s), but is gradually being resolved as techniques and methodologies become more robust if not sophisticated, in response to increasing complicated economic phenomena and environment.


2.2.1 The Economic Importance of Oil

The world oil market is a capital-intensive environment characterized by complex interactions deriving from the wide variety of products, transportation/storage issues and stringent environmental regulation. Worldwide consumption of oil exceeds $500 billion, roughly 10% of the US GDP. Crude oil is also the world"smost actively traded commodity, accounting for about 10% of total world trade, Verleger and Philip (1993).

The economic importance of oil derives not only from the sheer size of the market, but also from the crucial, almost strategic, role it plays in the economies of oil-exporting and oil-consuming countries. Oil prices drive revenues to oil­exporting countries in a large number of which, oil exports comprise over 20% of the GDP. On the other hand, costs of oil imports (typically over 20% of the total import bill) have a substantial impact on growth initiatives in developing countries. Energy price shocks have often been cited as causing adverse macroeconomic impacts on aggregate output and employment, in countries across the world Verleger and Philip (1993).

2.2.2 History of Oil and Gas Exploration in Ghana

Contrary to popular misconception, Ghana has a fairly checkered history of petroleum exploration dating back over 100 years. In 1896, the West Africa Oil and Fuel Company (WAOFCO) became on record, the first oil company to pioneer oil exploration in the Gold Coast (now modern day Ghana). Even though there is scarcely much corroborative primary data available on this company, Dickson (2011) contends that, WAOFCO’s arrival was most remarkable as inadequate if any trusted data had accumulated on the prospects of uncovering commercially viable hydrocarbon reserves in the Tano fields. Nonetheless, WAOFCO’s chief ambition at the time was directed at the rich onshore Tano fields in Ghana’s Western Region. Between 1896 and 1903, WAOFCO drilled a total of five (5) wells. Only one of these, the (WAOFCO-2) well, resulted in the very first documented oil discovery. Between 1909 and 1913, Societe Francaise de Petrole (SFP) a French oil company also followed WAOFCO’s pioneering lead into the Gold Coast. SFP on its own drilled a total of six (6) wells (Dickson, 2011).

Its first well, the SFP-1 struck oil at a depth of 10-17 meters and produced 7 barrels of oil per day (bopd). Four (4) of the five (5) remaining wells also had promising oil indications. Between 1923 and 1925 the African and Eastern Trade Corporation (AETC), a subsidiary of United African Company (UAC) join in the early drilling rush in the onshore Tano area and encountered oil and gas. Subsequently, Gulf Oil Company also acquired the Onshore Tano license and drilled four (4) more deep wells in the area between the periods 1956 to 1957. New of promising oil discoveries made Ghana still attractive to foreign interests despite the preceding setbacks (Dickson, 2011).

For instance diverse groups of Soviet and Romanian geo-scientists in the early to mid 1960’s (1960 - 1967)joined in the rush for petroleum resources in the Volta and Accra/Keta Basins. Their exploratory activities and its resulting geophysical data however led to a very important operational shift; a shift from onshore to offshore shallow waters exploration (Dickson, 2011).

Even though the period following 1967 saw the exit of the Soviets and Romanians, new and ambitious expatriate companies came onboard, who carried out further offshore drilling activities. It is significant to recall that it was during this period that the discoveries of hydrocarbons were made for the very first time in the Saltpond Basin, in Ghana. In 1971, under the Busia government, R.R. Amponsah, with a sample of oil collected from one such successful exploratory well headed to Parliament and made public exhibition of locally discovered oil.

The first offshore commercial hydrocarbon production in the Saltpond Basin however started in 1975 under the regime of General Kutu Acheampong; it was operated by Agripetco. Up to the late 1970’s management of the petroleum sector was under Petroleum Department of the Ministry of Fuel and Power a department of the civil service (Dickson, 2011).

Ghana’s first petroleum law, Ghana National Petroleum Corporation (GNPC) Law, 1983, (PNDCL 64) was passed in 1983. Under section 26 of that Law, suitable staff of the Petroleum Department was transferred to form the core of that infant GNPC. From 1984, exploration activities took a new turn with the enactment of PNDCL 64 which provided new statutory and legal framework which would accelerate exploration and production (E&P) efforts. GNPC’s corporate mission was to promote, explore and develop the hydrocarbon resources of the nation through lean, efficient and technology-driven investments so as to enhance the economic development of Ghana. Its vision was to become a world- class corporation capable of making Ghana a fast growing destination for upstream petroleum investments in West Africa. Between the years 1983 and 1989, GNPC concluded several agreements with a number of foreign firms (Dickson, 2011).

One of the most notable of these agreements permitted US-based oil company Amoco, to prospect in ten offshore blocks between Ada and the western border with Togo. In 1989 three companies, two American and one Dutch, spent US$30 million drilling wells in the Tano basin. On June 21, 1992, an offshore Tano basin well produced about 6,900 barrels of oil daily (Dickson, 2011).

For a time, especially during the early 1990s, there were domestic attempts at appraising earlier oil and gas discoveries to determine whether a predominantly local operation might make exploitation more commercially viable. GNPC wanted to set up a floating system for production, storage, off­loading, processing, and gas-turbine electricity generation, hoping to produce 22 billion cubic feet per day, from which 135 megawatts of power could be generated and fed into the national and regional grid. GNPC also won a contract in 1992 with Angola’s state oil company, Sonangol, which provided for drilling and, production at two of Sonangol’s offshore oilfields. GNPC in return was to be paid with a share of the oil (Dickson, 2011).

On June 18, 2007 Kosmos Energy, a relatively small Dallas-based exploratory company in a press release announced that the exploration well offshore the Republic of Ghana in the rich West Cape Three Points Block has discovered significant oil accumulation based on the results of drilling and wire-line logs, and a sample of the reservoir fluid (Dickson, 2011).

2.2.3 Ghanaian Policy Subsidy

Prior to 2005, domestic petroleum prices had been subsidised by the government. In January 2003 prices were increased by 90 percent in an attempt to link the domestic prices to world prices, which sparked widespread domestic opposition. Facing an election in December 2004, though, the government unlinked domestic and international prices, and the total cost of subsidies increased sharply (World Bank Group Energy Sector Strategy, 2010).

In the same year, with the subsidy program becoming unsustainable, the government launched a poverty and social impact assessment (PSIA) for fuel. The PSIA was completed in less than a year and in February 2005 the government liberalised fuel prices, leading to a subsequent increase in prices of 50 percent. The price hike came together with a public relations campaign explaining the need for price increase and announcing measures to mitigate their impact. These measures included an immediate elimination of fees at primary and junior secondary schools, a program to improve public transport (World Bank, 2006) the allocation of extra funds for primary health care in Ghana’s poorest areas, and an increase in funds to a rural electrification scheme (UN Environment Programme, Retrieved 13 February, 2012). Although there was opposition to the price hikes from trade unions, the policy was generally accepted and there were no large scale demonstrations against the increase (World Bank Group Energy Sector Strategy, 2010).

The government continued its policy of liberalised prices subject to price ceilings in line with world prices from February 2005 until May 2008; but a surge in oil prices led the government to freeze the price ceilings between May and November 2008. In the 2008 national elections, the victorious opposition party had pledged to halt the increase in domestic oil prices. According to the Global Insight, the incoming government resorted to an effectively ad hoc pricing approach, with increases coming in April, June and November 2009 (World Bank Group Energy Sector Strategy, 2010).

In December 2011, Ghana cut fuel subsidies, with Alex Mould, CEO of Ghana"s National Petroleum Authority (GNPA) citing increases in crude oil prices and the depreciation of Ghana’s cedi currency as the primary factors for the cuts. The cuts came as Ghana faced increasing pressure from the International Monetary Fund (IMF) to remove the subsidies, which the IMF contended were not effective in directly aiding the poor and promoted corruption and smuggling (Sweet Crude Reports, 2011).

The cut on subsidies for petroleum products was effective 29 December 2011 and resulted in fuel prices increasing by about 20 percent by 1 January 2012 (Business Day, 18thJanuary, 2012) Civil society groups such as the Ghanaian Trade Union Congress promised indefinite nationwide strikes, and partially in response to this the government in early February 2012 proposed to effectively reverse this recent policy and cut prices by 20%, though the National Petroleum Authority had not yet signed off on the move as of 9 February 2012 (Financial Times, 2012).

2.2.4 Supply Side Channel

Since oil is a factor of production in most sectors and industries, a rise in oil prices increases the enterprises" production costs and thus, stimulates contraction in output (imenez-Rodriguez and Sanchez, 2004). Given a firm"s resource constraints, the increase in the prices of oil as an input of production reduces the quantity it can produce. Hunt et al (2001) add that an increase in input costs can drive down non-oil potential output supplied in the short run given existing capital stock and sticky wages. Moreover, workers and producers will counter the declines in their real wages and profit margins, putting upward pressure on unit labour costs and prices of finished goods and services.

According to Verleger and Philip (1993), oil price volatility shrinks investment activities in production of oil and gas. In addition a permanent increase in volatility might lead to a situation where future capacity will always be a little lower than in a world of zero price volatility and prices a little higher.

Hamilton (1983) shares the same point and stresses that concerns on oil prices variability and oil supply disruptions could cause postponement of investment decisions in the economy. There is also a possibility of a structural shift and a period of adjustment within an economy when prices of oil increase. As oil becomes relatively expensive vice versa other intermediate goods, energy­intensive industries contract their production whereas less energy-dependent sectors and more efficient users expand. Such period of adjustment is costly and time-consuming with higher unemployment and resource underutilization.

2.2.5 Demand Side Channel

As presented earlier, oil price increases translate to higher production costs, leading to commodity price increases at which firms sell their products in the market. Higher commodity prices then translate to lower demand for goods and services, therefore shrinking aggregate output and employment level.

Furthermore, higher oil prices affect aggregate demand and consumption in the economy. The transfer of income and resources from an oil-importing to oil-exporting economies is projected to reduce worldwide demand as demand in the former is likely to decline more than it will rise in the latter, Hunt et al., (2001). The resulting lower purchasing power of the oil-importing economy translates to a lower demand. Also, oil price shocks pose economic uncertainty on future performance of the macro economy. People may postpone consumption and investment decisions until they see an improvement in the economic situation. In sum, an increase in oil prices causes a leftward shift in both the demand and supply curve, resulting to higher prices and lower output.

2.2.6 Economic Policy Reactions

The effects of oil price increases on headline and core inflation may stimulate the tightening of monetary policy, Hunt et al., (2001). Authorities have the policy tools to minimize, if not totally eliminate, the adverse effects of such shock. The Central Bank of Ghana has its key policy interest rates that can influence demand and inflation directions in the economy. However, pursuing one policy can be counterproductive; when Central Bank of Ghana cuts its interest rate, demand rises, but at the expense of higher inflation, and vice versa.

The credibility of the monetary authorities in responding to oil shocks is at stake if monetary policy reactions appear inconsistent with the announced policy objectives. As a result, inflation expectation and process is disrupted Hunt et al (2001). In the Philippines, where the Central Bank of Ghana adopts an inflation­targeting framework, monetary policy to prevent further inflationary impulse from the increase in oil prices must be determined on a case-by-case basis. In part, such decision can rely on how such oil shock persists and how long it will take for the economy to adjust back to equilibrium. Money supply plays a role on the negative correlation between oil prices and economic activity. By means of the real money balances channel, increases in oil prices cause inflation which, in turn, reduces the quantity of real balances in the economy (Hooker, 1996).

Hooker (1996), further noted that “counter inflationary monetary policy responses to oil price shocks are responsible for the real output losses associated with these shocks”. This is because a highly restrictive monetary policy to further bring inflation down would invariably reduce output (trade-off between inflation and output).


Efforts were made to gather ample information as far as the works of others are concerned, but the fact that several people employing Time Series Analysis focus on Box-Jenkins methodology compelled me to use the findings of Gulshan and Sanjeev (2010), Xier (2009), Hussen (2011) and Appiah and Adetunde (2011). I will point out their objectives, methodology and findings of the study.


Gulshan and Sanjeev (2010) presented a paper with the aim to build a Univariate time series model to forecast the exports of industrial goods from Punjab for ensuing decade till 2020. The study employs Box-Jenkin"s methodology of building ARIMA (Autoregressive Integrated Moving Average) model to achieve various objectives of study.



ISBN (eBook)
ISBN (Buch)
903 KB
modelling ghana arima




Titel: Modelling and forecasting monthly petroleum prices of Ghana using subset ARIMA models