An Interval Approach for Fuzzy Linear Regression with Imprecise Data
نویسندگان
چکیده
In this paper, a revisited approach for fuzzy regression linear model representation and identification is introduced. By adopting the commonly used principle of D-cuts, the fuzzy regression implementation is reduced to the handling of conventional intervals, for inputs, parameters and outputs. Using the Midpoint-Radius representation of intervals, the uncertainty attached to linear models becomes more interpretable. Actually, it is possible to determine the output uncertainty origin (model parameters and/or inputs). In this context, a possibilistic regression method is proposed to identify models of minimal global uncertainty, that is with respect to all possible inputs.
منابع مشابه
UNCERTAINTY DATA CREATING INTERVAL-VALUED FUZZY RELATION IN DECISION MAKING MODEL WITH GENERAL PREFERENCE STRUCTURE
The paper introduces a new approach to preference structure, where from a weak preference relation derive the following relations:strict preference, indifference and incomparability, which by aggregations and negations are created and examined. We decomposing a preference relation into a strict preference, anindifference, and an incomparability relation.This approach allows one to quantify diff...
متن کاملMeasuring the performances of Medical Diagnostic Laboratories based on interval efficiencies
The classic data envelopment analysis (DEA) models have overlooked the intermediate products, internal interactions and the absence of data certainty; and deal with analyzing the network within the “Black Box” mode. This results in the loss of important information and at times a considerable modification occurs in efficiency results. In this paper, a Three-stage network model is considered wit...
متن کاملFUZZY LINEAR REGRESSION BASED ON LEAST ABSOLUTES DEVIATIONS
This study is an investigation of fuzzy linear regression model for crisp/fuzzy input and fuzzy output data. A least absolutes deviations approach to construct such a model is developed by introducing and applying a new metric on the space of fuzzy numbers. The proposed approach, which can deal with both symmetric and non-symmetric fuzzy observations, is compared with several existing models by...
متن کاملRanking DMUs by ideal points in the presence of fuzzy and ordinal data
Envelopment Analysis (DEA) is a very eective method to evaluate the relative eciency of decision-making units (DMUs). DEA models divided all DMUs in two categories: ecient and inecientDMUs, and don't able to discriminant between ecient DMUs. On the other hand, the observedvalues of the input and output data in real-life problems are sometimes imprecise or vague, suchas interval data, ordinal da...
متن کاملAn Exact Algorithm for Likelihood-Based Imprecise Regression in the Case of Simple Linear Regression with Interval Data
Likelihood-based Imprecise Regression (LIR) is a recently introduced approach to regression with imprecise data. Here we consider a robust regression method derived from the general LIR approach and we establish an exact algorithm to determine the set-valued result of the LIR analysis in the special case of simple linear regression with interval data.
متن کامل