大中小微企业规模划型统计标准的实证研究  

An Empirical Study on the Statistical Standard for the Size Classification of Large,Medium,Small and Micro-sized Enterprises

在线阅读下载全文

作  者:高敏雪[1,2] 孙庆慧 胡强 甄峰 Gao Minxue;Sun Qinghui;Hu Qiang;Zhen Feng

机构地区:[1]中国人民大学应用统计科学研究中心 [2]中国大学统计学院

出  处:《复印报刊资料(统计与精算)》2022年第3期11-25,共15页STATISTICS AND ACTUARIAL SCIENCE

摘  要:研究目标:引入机器学习方法讨论大中小微企业规模划型标准问题。研究方法:基于国家统计局公开的第四次经济普查企业数据,采用Adasampling方法,结合基本描述统计方法判断企业规模划型问题。研究发现:多数行业规模划型采用单一指标可达到较好划分效果,缓解小微企业划分过于宽松的瘤疾,简化分类识别难度;现行小微企业分类阅值较为合理,但中小企业间和大中企业间分类阅值有明显偏差;可细化当前的企业规模划型标准,基于行业大类特征进行企业规模划型;分类阅值可建立机器学习与经济普查相结合的定期动态调整机制。研究创新:引入Adasampling方法讨论企业规模划型指标选取和划分阅值标准。研究价值:从理论上论证我国企业规模划型标准的科学性和优化方向。Research Objectives:To measure the statistical standard for the size classification of large,medium,small and micro-sized enterprises.Research Methods:By using the micro data of enterprises in the fourth National Economic Census,to discuss the topic with Adasampling method and descriptive statistical methods.Research Conclusions:Firstly,a proper single indicator can achieve a better classification effect,which can help alleviate the chronic disease of too loose identification of small and micro-sized enterprises.Secondly,the measurement results verify the rationality of the classification thresholds of small and micro-sized enterprises in the current standard,but there are obvious deviations in the classification thresholds of medium and small-sized enterprises and large and medium-sized enterprises.Thirdly,it is suggested that the current enterprise size classification standard can be specified and classified based on the characteristics of 2-digit level industries,and a regular dynamic adjustment mechanism can be funded by combining Machine Learning Methods and the National Economic Census.Research Innovations:To select and measure classification indicators and the determination of classification thresholds among large,medium,small and micro-sized enterprise by using Adasampling method.Research Values:To support official standard and its rearrangement of the size classification of large,medium,small and micro-sized enterprises in theory and statistical methods.

关 键 词:企业规模划型 大中小微企业划分标准 小微企业 Adasampling方法 

分 类 号:TP181[自动化与计算机技术—控制理论与控制工程] F279.2[自动化与计算机技术—控制科学与工程]

 

参考文献:

正在载入数据...

 

二级参考文献:

正在载入数据...

 

耦合文献:

正在载入数据...

 

引证文献:

正在载入数据...

 

二级引证文献:

正在载入数据...

 

同被引文献:

正在载入数据...

 

相关期刊文献:

正在载入数据...

相关的主题
相关的作者对象
相关的机构对象