AN EXPLORATORY MODELING OF GLOBAL WARMING

AUTHOR: IGWENAGU CHINELO MERCY

DEPARTMENT: STATISTICS

AFFILIATION: NNAMDI AZIKIWE UNIVERSITY, AWKA

The problems associated with global warming, ranging from increase in global temperature, change in agricultural yields, glacier retreat, species extinction, increase in the ranges of diseases and disease vectors, were reviewed. These underscore the need to reduce emission which causes global warming. The proposed method of emission reduction is by emission trading according to the Kyoto protocol. If this proposal holds, for countries to participate actively, it is important to build a model for estimating their level of CO2 emission. The aim of this research, among others, is to develop an exploratory model of global warming, using CO2 emission as a surrogate and also to model the effects of global warming in Nigeria. This was done using various statistical techniques to explore some possible factors that could cause global warming, and to know their actual contributions. These methods include Correlation analysis, Regression analysis, Principal Component analysis, Factor analysis, and Path analysis. The correlation analysis result shows that there is linear association among the selected variables, with p- value < 0.001. In the regression analysis, the F- statistics of 578.733 with a p-value < 0.001 indicates that CO2 emission is related to some of the input variables used. Due to the noticed effect of multicollinearity, supervised principal component analysis was used and the result of the analysis shows that model built on this method gave a good fit, with the least standard error compared to models built from stepwise multiple regression. Path analysis result shows that energy consumption among others, with path coefficient of 0.983 has a direct effect on global warming; this supports the use of clean development mechanism for emission reduction. On the effects of global warming in Nigeria, the Path coefficient of 0.506 shows that the effect was more on temperature. The stepwise regression analysis gave a Durbin Watson d-statistics of 1.882 which indicates that there is no autocorrelation among the variable. Trend analysis of CO2 emission in Nigeria shows that CO2 emission increases at an approximate rate of 2% by the year, implying that Nigerians should be involved on the issue concerning global warming/climate change. 

TO VIEW THE FULL CONTENT OF THIS DOCUMENT, PLEASE VISIT THE UNIZIK LIBRARY WEBSITE USING THIS LINK, http://naulibrary.org/dglibrary/admin/book_directory/Thesis/11080.pdf

Advertisements

Tags: , , , , , , ,

Leave a Reply

Fill in your details below or click an icon to log in:

WordPress.com Logo

You are commenting using your WordPress.com account. Log Out / Change )

Twitter picture

You are commenting using your Twitter account. Log Out / Change )

Facebook photo

You are commenting using your Facebook account. Log Out / Change )

Google+ photo

You are commenting using your Google+ account. Log Out / Change )

Connecting to %s


%d bloggers like this: