模糊状态风险分析的广义Logistic回归理论与应用(1)——模糊水平聚类和变量筛选通用算法  

The Theory and Applications of Generalized Logistic Regression for Risk Analysis of Fuzzy State(1)—A General Algorithm for Clustering Fuzzy Levels and Selecting Covariates

作　　者：刘韵源[1] 刘嘉[2] 周家丽[1] 陈元立[1] 

机构地区：[1]中国医学科学院肿瘤研究所,北京100021 [2]北京大学医学部基础医学院

出　　处：《中国公共卫生》2000年第11期965-968,共4页Chinese Journal of Public Health

基　　金：国家自然科学基金资助项目,批准号:39770832

摘　　要：论述了“微弱相关影响因素”概念及其在预防医学中的重要意义 ,并研究了适宜处理此类资料的统计方法。借助模糊状态概念、交叉积差和统计量和信息量寻优标准 ,发展了暴露水平聚类优化、状态变量选择通用算法 ,可明显提高检测、识别微弱相关影响因素的效能与统计分析水准。The concept and statistical methods for weakly correlative factors,influencing the formation and development of chronic diseases,are proposed in this paper.By the aid of fuzzy state analysis,the Cross-Product Difference Sum(CPDS)and the Akaike's Information Criterion(AIC),a general algorithm,clustering fuzzy exposure levels and selecting covariates,is designed for solving problems connected with analytical abilities of detecting and recognozing weakly correlative-influencing factors.

关 键 词：微弱相关影响因素 模糊状态 交叉积差和 信息量标准 

分 类 号：R311[医药卫生—基础医学] R195