eduzhai > Physical Sciences > Physics Sciences >

Fuzzy Regression Model Based on Fuzzy Distance Measure

  • Save

... pages left unread,continue reading

Document pages: 15 pages

Abstract: Some existed fuzzy regression methods have some special requirements forthe object of study, such as assuming the observed values as symmetric triangularfuzzy numbers or imposing a non-negative constraint of regressionparameters. In this paper, we propose a left-right fuzzy regression method,which is applicable to various forms of observed values. We present a fuzzydistance and partial order between two left-right (LR) fuzzy numbers and welet the mean fuzzy distance between the observed and estimated values as themean fuzzy error, then make the mean fuzzy error minimum to get the regressionparameter. We adopt two criteria involving mean fuzzy error (comparativemean fuzzy error based on partial order) and SSE to compare theperformance of our proposed method with other methods. Finally four differenttypes of numerical examples are given to illustrate that our proposedmethod has feasibility and wide applicability.

Please select stars to rate!

         

0 comments Sign in to leave a comment.

    Data loading, please wait...
×