Correlation coefficient evaluation for the fuzzy interval data

The issue of evaluating an appropriate correlation with fuzzy data is an important topic in the econometrics and management science, especially when the data sets illustrate uncertainty, inconsistence, and incompleteness. This study extends the concept of Pearson's correlation coefficient to compute the correlation coefficient of the data sets that are fuzzy in nature. However, no common proposal for such extension exists. This study proposes several ways to evaluate the correlation coefficient when the fuzzy data are with interval types. Two empirical studies show that the methods that this study proposes for evaluating the coefficient of fuzzy correlations are useful and efficient from the perspective of econometrics and management. (C) 2015 Elsevier Inc. All rights reserved.