On the Optimization Methods for Fully Fuzzy Regression Models
The goal of this paper is to construct a multiple fuzzy regression model by fuzzy parameters estimation using the fuzzy samples. We propose an optimization model that provides fuzzy coefficients to minimize the distance between the fuzzy regressands and the fuzzy regressors. It concerned with imprecise measurement of observed variables, linear programming estimation and non-parametric methods. This is different from the assumptions as well as the estimation techniques of the classical analysis. Empirical results demonstrate that our new approach is efficient and more realistic than the traditional regression analysis did.
fuzzy regression fuzxy parameter triangular membership function h-cut methods of least square
Yu-Yun Hsu Berlin Wu
General Education Center China University of Technology Taipei, Taiwan Department of Mathematical Sciences National Chengchi University Taipei, Taiwan
国际会议
The 10th International Conference on Intelligent Technologies(第十届智慧科技国际会议 InTech09)
桂林
英文
329-333
2009-12-12（万方平台首次上网日期，不代表论文的发表时间）