%0 Journal Article
%T “双碳”目标下我国碳排放影响因素探究<br>Research on Influencing Factors of China’s Carbon Emission under “Double Carbon” Goal
%A 郑赛琴
%J Statistics and Applications
%P 1628-1639
%@ 2325-226X
%D 2023
%I Hans Publishing
%R 10.12677/SA.2023.126166
%X 为早日实现我国的“双碳”目标，了解碳排放量影响因素并提供相应的建议具有重要的现实意义。本文基于《中国统计年鉴》《中国能源统计年鉴》、CEADs数据库以及各省《统计年鉴》中2010~2019年我国30个省份(除西藏自治区外)的面板数据，构建面板分位数回归模型，并与固定效应模型对比探究碳排放量的影响因素，再进一步采用随机森林算法对各变量进行重要性排序。结果表明：总人口、能源结构、能源强度、人均GDP、对外开放度对碳排放量具有显著的正向影响；产业结构对碳排放量的影响在面板分位数回归中较显著，且该影响程度随着分位数的增加逐渐减弱；城镇化率和政策变量仅在分位数为0.3的模型中是显著的，FDI仅在分位数为0.7的模型中是显著的；能源结构、总人口数的重要性最高，其次是对外开放度、FDI、人均GDP、能源强度、产业结构、城镇化率，最后是政策变量。<br />
In order to realize China’s “double carbon” goal as soon as possible, it is of great practical signifi-cance to understand the influencing factors of carbon emission and provide corresponding sugges-tions. Based on the panel data from China Statistical Yearbook, China Energy Statistical Yearbook, CEADs database and provincial Statistical Yearbook of 30 provinces in China (except Tibet Autono-mous Region) from 2010 to 2019, a panel quantile regression model was constructed to explore the influencing factors of carbon emission by comparing with the fixed-effect model. Then the random forest algorithm is used to rank the importance of each variable. The results show that total popula-tion, energy structure, energy intensity, per capita GDP and openness have significant positive ef-fects on carbon emission. The influence of industrial structure on carbon emission is significant in panel quantile regression, and the influence degree decreases with the increase of quantile. Urban-ization rate and policy variables are significant only in the model with a quantile of 0.3, and FDI is significant only in the model corresponding to 0.7. Energy structure and total population are the most important, followed by openness to the outside world, FDI, per capita GDP, energy intensity, industrial structure, urbanization rate, and finally policy variables.
%K 碳排放，面板分位数回归，固定效应模型，随机森林<br>Carbon Emission
%K Panel Quantile Regression
%K Fixed Effect Model
%K Random Forest
%U http://www.hanspub.org/journal/PaperInformation.aspx?PaperID=77551