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

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.