Prediction of Carbon Dioxide Emissions Using Fuzzy Linear Regression Model: a Case of Developed and Developing Countries

Carbon dioxide (CO2) emission is an important component in the stability of climate system, and plays a key role in green house effect. In the past few decades, CO2 emissions have increased exponentially. Goodall (2007), in his book mentioned that almost 30 billion tons of CO2 enters the atmosphere as a result of various human activities each year. The effect of the higher concentrations of CO2 to people could not be taken lightly. CO2 is held responsible for 58.8% of green house effect. The effect may cause major environment pollutions and climate instability. The escalation in CO2 emissions would give disastrous environmental consequences such as droughts, storms, floods and other environmental calamities. As a result of large volume of CO2 in atmosphere, it is noticeable that global sea level has escalated by 10 -20 cm during the 20th century (Mukhtar et al., 2004). It has been reported that there was not only escalating trend in sea level but also the temperature of the sea. Spence (2005) testified that global CO2 emissions have escalated by 30% and temperature has risen by 0.3-0.6 degree Celsius. These are among the much feared examples of environmental instability as a result of uncontrolled CO2 emissions. The risk of environmental catastrophe is therefore considered great enough to justify the awareness and study in CO2 emissions. A considerable amount of literature has been published on causal relationship between CO2 emissions and its contributing factors. Hwang and Yoo (2012) analyzed the short and long-run causality issues between energy consumption, CO2 emissions, and economic growth in Indonesia using timeseries techniques. The relationship between CO2 emissions with Gross Domestic Product (GDP) Abstract: Carbon dioxide (CO2) emissions have been continuously escalating in recent years. The escalating trend is consistent with the current economic activities and other uncertain variables such as demand and supply in businesses and energy needs. Linear model is one of the most commonly used methods to explain the relationship between CO2 emissions and the related economic variables. However, linear regression model fails to describe the relationship due to the variables’ uncertainty and vague information. As to overcome this problem, fuzzy linear regression model has been proposed in explaining the relationship. This paper aims to predict CO2 emissions using possibilistic fuzzy linear regression model by employing data from two countries. The prediction on the efficiency of CO2 emissions for the United Kingdom (UK) and Malaysia was measured. The predictive models identified population and Gross Domestic Products as the most effective predictors for the UK and Malaysia respectively. The root mean square errors of the UK and Malaysia predictive models were 2.895 and 1010.117 respectively. It shows that the CO2 emissions predictors of the UK are more efficient than Malaysia. Instead of crisp deterministic regression coefficients, the fuzzy coefficients with middle and spread values of fuzzy linear regression equations offer new contribution to describe the relationship between CO2 emissions and the related economic variables.