An Innovative Approach on Fuzzy Correlation Coefficient with Interval Data

Abstract

We usually use the correlation coefficient to observe the relation of two variables. But if the data are exhibited by a fuzzy type, such as interval data, instead of the real number data, the traditional methods for evaluating correlation coefficients do not work. In this paper, we propose an innovative approach to measure the correlation for variables when the data are in the form of intervals. Such the correlation coefficient interval will be called the fuzzy correlation coefficient. Finally two empirical studies are given to compare the traditional correlation coefficient and the fuzzy correlation coefficient. The results show that the fuzzy correlation coefficient can provides an efficient and creative measurement in the perception measurement.