Reduction to least-squares estimates in multiple fuzzy regression analysis

Authors:
Chi-Tsuen Yeh
Affiliations:
Department of Mathematics Education, National University of Tainan, Tainan, Taiwan, R.O.C
Venue:
IEEE Transactions on Fuzzy Systems
Year:
2009

Citing 16
Cited 2

Real and complex analysis, 3rd ed.

Real and complex analysis, 3rd ed.
Fuzzy least squares

Information Sciences: an International Journal
Multiobjective fuzzy linear regression analysis for fuzzy input-output data

Fuzzy Sets and Systems
Exponential possibility regression analysis

Fuzzy Sets and Systems - Special issue on fuzzy information processing
A generalized fuzzy weighted least-squares regression

Fuzzy Sets and Systems
General fuzzy least squares

Fuzzy Sets and Systems
Linear regression with random fuzzy variables: extended classical estimates, best linear estimates, least squares estimates

Information Sciences: an International Journal
Fuzzy regression methods—a comparative assessment

Fuzzy Sets and Systems
Multidimensional least-squares fitting with a fuzzy model

Fuzzy Sets and Systems
Hybrid fuzzy least-squares regression analysis and its relibabilty measures

Fuzzy Sets and Systems
Fuzzy least-squares linear regression analysis for fuzzy input-output data

Fuzzy Sets and Systems - Information processing
Least-squares fuzzy regression with fuzzy random variables

Fuzzy Sets and Systems
Fuzzy least-squares algorithms for interactive fuzzy linear regression models

Fuzzy Sets and Systems - Theme: Modeling and learning
Extended fuzzy regression models using regularization method

Information Sciences—Informatics and Computer Science: An International Journal
Fuzzy nonparametric regression based on local linear smoothing technique

Information Sciences: an International Journal
Multiple regression with fuzzy data

Fuzzy Sets and Systems

Weighted semi-trapezoidal approximations of fuzzy numbers

Fuzzy Sets and Systems
Weighted semi-trapezoidal approximations of fuzzy numbers

Fuzzy Sets and Systems

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper, we deal with the problem of leastsquares multiple regression with fuzzy data. The regression coefficients are assumed to be real (crisp). A formula for solving the regression coefficients in one-variable models is derived. If each independent variable is effective (i.e., its corresponding regression coefficient is nonzero), the multiple regression problem can be replaced with a 0-1 programming problem. Its optimal solution is easily computed. Finally, we also propose effective algorithms to compute the regression coefficients in a general case.