A partial least squares regression approach to analyze the ecological footprint of 123 nations

The per capita ecological footprint (EF) is one of the most widely recognized measures of environmental sustainability. It tries to quantify the earth's biological capacity required to support human activity. This study first summarized the previous literature, and then presented the six factors which influenced the per capita EF, they are the nation's gross domestic product (GDP), urbanization independent of economic development, the distribution of income measured by the GINI coefficient, exports dependence as measured by the percentage of exports to total GDP, service intensity measured by the percentage of service to total GDP and their position in the core/periphery hierarchy of world system(WSP). Based on it, a new ecological footprint model based on partial least squares regression (PLSR) which is specifically designed to deal with multiple regression problems, especially for the number of observations is limited, missing data are numerous and the correlations between the predictor variables are high was conducted to predict the 13 nations' per capita EF used the 110 nations' data. The forecasting accuracy was measured by average absolute error and average relative error. They were 0.012889 and 0.3071% respectively. The results demonstrated that the EF model based on PLSR has good forecasting performance.