基于有序logistic模型的研究生学术产出影响因素研究——以上海理工大学交通运输工程学科为例

On Influencing Factors of Postgraduate Academic Output Based on Ordinal Logistic Model——A Case Study of Transportation Discipline at University of Shanghai for Science and Technology

研究生作为高校科研队伍的重要组成部分,其科研能力和创新能力从一定程度上反应了大学教育和学术的水平.针对研究生学术产出的影响因素,从研究生和导师两个角度定性分析潜在影响因素的基础上,基于有序多分类logistic统计模型,分析各影响因素与研究生学术产出的关联性.研究以上海理工大学交通工程学科研究生为样本数据,考虑了7个与研究生相关和9个与导师相关的潜在因素,验证了数据采用有序多分类logistic模型进行分析的适用性,建立了回归分析模型并检验了模型,总体预测准确度为79.5%.在此基础上对模型结果进行了分析并提出了措施建议.研究发现,学生自身学习动力、导师职称、导师总学术产出、承担国家/省部级项目和指导同一届学生人数等因素具有显著影响,为研究生导师遴选、研究生招生、导师分配等相关政策的制定提供了依据.

As an important part of scientific research personnel in universities,the scientific research and innovation ability of graduate students reflects the level of university education and academics.This study focuses on the influencing factors of the graduate academic output.Based on the qualitative analysis of potential influencing factors from the perspectives of graduate students and supervisors,the correlation between influencing factors and postgraduate academic output was analyzed with the ordinal logistic model.The data of the graduate students at the University of Shanghai for Science and Technology were used in the study.The potential influencing factors,including 7 factors related to graduate students and 9 factors related to supervisors,were considered.The application presuppositions of the data to the ordinal logistic model were verified.The regression model was established with an overall prediction accuracy of 79.5%.Based on this,the results of the model were analyzed,and measures were proposed.The results show that the learning motivation of students,and the title,academic output,state/provincial projects,and the number of guiding students of supervisors have a significant effect on the postgraduate academic output.It can provide the basis for the formulation of relevant policies on the supervisor selection,student enrollment,and allocation of graduate supervisors.