Extended STIRPAT model-based driving factor analysis of energy-related CO2 emissions in Kazakhstan

Driving factors analysis of agricultural carbon emissions based on extended STIRPAT model of Jiangsu Province, China

“…In this paper, spss 20.0 was used to test the correlation of various influencing factors of agricultural carbon emissions, Eview 8.0 was used to conduct the ordinary least square (OLS) estimation analysis, and the results (Tables 1 and 2) showed that there was serious multicollinearity among the influencing factors, and the OLS method should not be used for regression analysis (Wang et al, 2013(Wang et al, , 2017Xiong et al, 2019b).…”

“…Experiments, observations, environmental Kuznets (EKC) curve model and decoupling model mainly investigate the influence of specific factors, which is not conducive to the macro control of all factors in the whole region. Although the LMDI model can effectively identify the driving factors of agricultural carbon emissions, the impact factors are limited (Xiong, Chen, & Huang, 2019b). Multiple linear regression analysis also has many problems.…”

“…For example, when the selected independent variables are multi-correlated, the model cannot be established by using ordinary least square regression, and the classical principal component regression often presents contradictory situations, resulting in low confidence of its results and lack of basis for the selection of influence factors. STIRPAT model can identify more influencing factors, but it is mainly used in the field of energy and carbon emissions (Cansino, Román, & Ordóñez, 2016;Wang et al, 2017;Wang, Wu, Zhu, & Wei, 2013;Xiong et al, 2019b). The impact factors of agricultural greenhouse gas emissions lack theoretical support of this method, and there are few related studies at present.…”

“…Compared with previous studies, the research features and innovations of this paper are reflected in the following three aspects. In terms of research ideas, the basic influencing factors of agricultural carbon emissions were obtained on the basis of the extended Kaya identity (Xiong et al, 2016a(Xiong et al, , 2016b, and the influencing factors were improved by referring to relevant studies in the energy field (Cansino et al, 2016;Wang et al, 2013Wang et al, , 2017Xiong et al, 2019b), which provided a theoretical basis for the choice of basic factors, and then, the STIRPAT model was used for decomposition, which can identify more influencing factors, and ridge regression was used for analysis to overcome the multicollinearity problem. In terms of measurement indicators, this paper took into account the four basic influencing factors mentioned above, and added factors such as urbanization, mechanization level, and agricultural natural disasters, so as to comprehensively investigate the factors affecting agricultural carbon emissions.…”

International cooperation, production side emissions and environmental sustainability

“…It is now considered the Stochastic Impacts by Regression on Population Affluence and Technology (STIRPAT). Previous applications of STIRPAT include Martinez-Zarzoso and Maruotti (2011), Liu et al (2015) and Xiong et al (2019). This STIRPAT framework allows the testing of the environmental Kuznets curve (EKC) effect as in Grossman and Krueger (1991), Seldon and Song (1994) and Holtz-Eakin and Seldon (1995).…”