Library Subscription: Guest
Begell Digital Portal Begell Digital Library eBooks Journals References & Proceedings Research Collections
International Journal for Uncertainty Quantification

Impact factor: 1.000

ISSN Print: 2152-5080
ISSN Online: 2152-5099

Open Access

International Journal for Uncertainty Quantification

DOI: 10.1615/Int.J.UncertaintyQuantification.2018020755
pages 123-141

A PARTIAL LEAST-SQUARES PATH MODEL FOR MULTIATTRIBUTE DECISION-MAKING UNDER FUZZY ENVIRONMENT

Xiaohong Chen
School of Business, Central South University, Changsha 410083, China; Key Laboratory of Hunan Province for Mobile Intelligence, Hunan University of Commerce, Changsha 410205, China
Hui Li
School of Business, Central South University, Changsha 410083, China
Chunqiao Tan
School of Business, Central South University, Changsha 410083, China; School of Economics and Management, Nanjing University of Information Science and Technology, Nanjing 210044, China

ABSTRACT

In practical multiattribute decision-making problems, attributes are often correlated and some attributes (latent attributes) that play significant parts in evaluating alternatives cannot be directly observed, leading to an incorrect result. This paper proposes a partial least-squares path model for multiattribute decision-making under a triangular fuzzy environment, which not only addresses interaction between attributes but also fully reveals the effects of latent attributes on the evaluation of alternatives, and their weights are objectively assigned. First, utilizing a least-squares method, a triangular fuzzy regression model is built with the defuzzification of the residual sum of squares. On the basis of a triangular fuzzy regression model, an iterative algorithm is proposed for a triangular fuzzy partial least-squares path model. Four indexes are given to investigate the goodness of the proposed model. Then the procedure of the triangular fuzzy partial least-squares path model-based multiattribute decision-making is introduced. Finally, an illustrated example is provided to demonstrate the feasibility and validity of the proposed method.