Spearman秩相关系数的Python程序设计及应用——图书阅读与隐性知识习得能力相关性实证分析

Python Program Design and Application of Spearman Rank Correlation Coefficient -Empirical Analysis of the Correlation between Book Reading and Tacit Knowledge Acquisition Ability

样本若无重复数据时,计算Spearman秩相关系数的程序比较容易设计。如果样本出现重复数据时,则可以从样本数据的结、秩平均值等概念出发设计程序;此时,既要考虑不重复数据的秩,也要考虑对重复数据秩平均值的确定。该课题基于清华大学王星教授给出的数据结、秩平均值定义,设计Spearman秩相关系数的计算程序,并在实证分析中运用,操作简便易行。

If there is no duplicate data in the sample,the program for calculating Spearman rank correlation coefficient is easier to design.If there is duplicate data in the sample,the program can be designed from the concepts of knot and rank average of the sample data.At this time,we should consider not only the rank of non-repeated data,but also the determination of the rank average of repeated data.The project is based on the definition of data knot and rank average given by Professor Wang Xing of Tsinghua University,designs the calculation program of Spearman rank correlation coefficient and applies it in case analysis,which is simple and easy to operate.