经验不确定分布一致性检验方法研究

发布时间：2018-04-09 01:42

本文选题：经验不确定分布　切入点：专家经验数据　出处：《模糊系统与数学》2017年03期

【摘要】：经验不确定分布一致性检验是在不确定分布未知的情况下,利用专家经验数据对不确定分布进行推断的一种非参数检验方法,是不确定统计领域参数估计和回归分析的基础和前提。本文主要研究了几种专家经验不确定分布的一致性检验方法。首先,简述了不确定统计和专家经验数据的基本理论;其次,利用专家经验数据系统分析了两组专家的经验分布是否存在显著性差异的Mann-Whitney U检验法、Kolmogorov-Smirnov检验法、游程检验法和极端反应检验法;再次,研究了多组专家经验数据是否存在显著性差异的Kruskal-Wallis检验法和Jonckheere-Terpstra检验法。并借助Matlab 7.0和SPSS 20,利用概率统计中抽样分布理论进行实证分析。
[Abstract]:Empirical uncertainty distribution consistency test is a non-parametric test method for inferring uncertain distribution using expert empirical data in the case of uncertain distribution unknown.It is the basis and premise of parameter estimation and regression analysis in uncertain statistical field.In this paper, several consistency checking methods for uncertain distribution of expert experience are studied.Firstly, the basic theory of uncertain statistics and expert empirical data is briefly introduced. Secondly, the Mann-Whitney U test method and Kolmogorov-Smirnov test method are used to analyze whether there are significant differences in the empirical distribution between the two groups of experts by using the expert empirical data system.Run path test and extreme reaction test. Thirdly, the Kruskal-Wallis test and Jonckheere-Terpstra test were studied to determine whether there were significant differences in the empirical data of many groups of experts.With the help of Matlab 7.0 and SPSS 20, the sampling distribution theory in probability and statistics is used to make empirical analysis.
【作者单位】：海南大学数学系;
【基金】：海南省自然科学基金资助项目(117014) 海南大学青年基金资助项目(hdkyxj201720) 省中西部高校提升综合实力工作项目
【分类号】：O212

【相似文献】