财政支出的社会经济效应——基于面板随机森林的分析与优化

Socioeconomic Effects of Fiscal Expenditure:Based on the Analysis and Optimization by Panel Random Forest

为确定我国财政支出总量及各分项支出对社会经济的影响是否存在拐点,财政支出是否存在最优规模和最优结构,本文针对我国财政数据统计口径和统计周期的特点,基于面板数据改进了随机森林方法,利用该方法对52个国家1995-2016年的非平衡面板数据进行了分析,从中得出了财政支出促进经济社会发展的最优规模和最优结构。结论显示,财政总支出和一般公共服务、经济事务、文化娱乐以及宗教和教育支出对社会经济发展的作用存在拐点和合理区间。此外,健康、环保和社保支出对社会经济发展具有持续显著的正向作用。基于研究结论,本文最后针对我国国情,给出了我国财政支出的最优规模和最优结构,为优化我国财政支出总量和支出结构提出了政策建议。

In order to determine whether the effect of China＇s total fiscal expenditure and its structure on the socioeconomic development has an inflection point, and whether there is an optimal scale and optimal structure for fiscal expenditure, a panel random forest method is used to analyze the non-balanced panel data of 52 countries from 1995 to 2016. The panel random forest is based on historical regression tree, which is an improved algorithm of traditional regression tree. On the basis of the results of panel random forest, the optimal scale and optimal structure of fiscal expenditure to promote economic and social development are obtained. The conclusions show that there is an inflection point and a reasonable interval of the effects of total fiscal expenditure and the expenditure of general public services, economic affairs, cultural entertainment and religious and education（proportion of GDP） on socioeconomic development. In addition, the expenditure of health, environmental protection and social security have a significant positive effect on socioeconomic development. Based on the conclusions, the optimal scale and optimal structure of China＇s fiscal expenditure according to China＇s national conditions are given, the policy recommendations for optimizing China＇s fiscal expenditure and expenditure structure is also included.