基于SVMRSAR模型的受教育水平影响因素分析  

Analysis of influencing factors of educational level based on SVMRSAR model

作　　者：夏昊 宗序平[1] XIA Hao;ZONG Xuping(School of Mathematics Science,Yangzhou University,Yangzhou 225002,China)

机构地区：[1]扬州大学数学科学学院,江苏扬州225002

出　　处：《扬州大学学报（自然科学版）》2021年第4期1-4,32,共5页Journal of Yangzhou University：Natural Science Edition

基　　金：国家自然科学基金资助项目(40930952).

摘　　要：对于SVMRSAR模型,采用两阶段最小二乘法估计常系数参数,B样条函数序列估计非参数,并利用蒙特卡洛模拟评估参数估计的精确性.运用该模型分析了人口自然增长率、城镇人口比例、性别比例、人均教育投入、师资配比等因素对人均受教育年限的影响.分析结果表明:人均教育投入与师资力量对教育水平发展的影响最显著;性别占比对教育发展水平的影响明显自相关;不同省市的教育发展水平与邻近省市也有一定的关联.For SVMRSAR model,the two-stage least square method is used to estimate constant coefficient parameters,b-spline function sequence is used to estimate non-parameters,and Monte Carlo simulation is used to evaluate the accuracy of parameter estimation.Based on the SVMRSAR model,this paper analyzes the effects of the factors such as natural population growth rate,urbanization ratio,sex ratio,per capita investment in education,ratio of teachers on the average number of years of education.The results show that per capita education investment and faculty have the most significant impact on the development of education level.The influence of gender ratio on educational development level is obviously autocorrelation.The educational development level of different provinces and cities is also related to neighboring provinces.

关 键 词：SVMRSAR模型 人均受教育年限 参数估计 实证分析 

分 类 号：O212.4[理学—概率论与数理统计]