模糊变系数回归模型在基金评价中的应用  

Application of Fuzzy Variable Coefficient Regression Model in Fund Evaluation

作　　者：文雯[1] 杨志辉[1] 

机构地区：[1]东华理工大学理学院,江西南昌330013

出　　处：《江西科学》2012年第3期271-276,共6页Jiangxi Science

基　　金：江西省自然科学基金(2010GQS0003)

摘　　要：在现有的CAPM模型基础上,利用模糊变系数回归分析方法,将模糊数设置为高斯模糊数,扩大模糊回归分析的实用范围,并运用局部核权最小二乘法对模型进行求解。给出了评价指标GOF,基于现实生活更适用的评判标准,建立适用于中国基金市场的模糊估值模型;与经典回归模型相比较,采用模糊变系数回归得到的参数估计有更好的应用价值。实证结果表明模糊变系数回归方法具有较好适用性。Based on the existing CAPM model, fuzzy variable coefficient regression was used, which consider Gaussian fuzzy numbers to expand the application range of the fuzzy regression analysis. And fit model by local nuclear power least squares. On the basis of the real life gives more suitable evaluation index GOF, and establish a fuzzy valuation model which is applicable for fund market. Compared with classic regression model, using the fuzzy variable coefficient regression to estimate the parameters have better application value. The results indicate that the fuzzy variable coefficient re- gression method has good suitability.

关 键 词：回归分析 高斯模糊数 模糊变系数模型 CAPM模型 基金评价 

分 类 号：O159[理学—数学]