教育政策與行政領域處理量化資料，常以傳統二值邏輯為主。在統計學上，我們常使用皮爾森相關係數來表達兩變數間線性關係的強度，及其關係之方向。皮爾森相關係數所處理的資料都是明確的實數值，但是，當資料是模糊數時，如何計算出廣義模糊相關係數呢？本研究探討區間模糊樣本資料值求得模糊相關係數，並提出廣義模糊相關係數。本研究是以影響學習成就評量的因素，做實證研究分析，得出更合理的分析。而此模糊相關區間定義也能應用在兩資料值為實數或其中一筆資料值為實數的情況，可以解釋更多在實務上所發生的相關現象。

The field of educational policy and administration often calculates quantitative data on the basis of traditional two-valued logic. In the statistics research, the magnitude and direction of the linear relationship between two variables are usually expressed by Pearson's correlation coefficient. Traditionally, Pearson's correlation coefficient deals with real numbers. However, when the data are composed of fuzzy numbers, it is not feasible to use this traditional approach to compute the correlation coefficient. The present study investigates a new approach to calculating fuzzy correlations. We propose broad formulas in order to adjust the coefficient more reasonably and deal with fuzzy data more accurately. An empirical study is used to illustrate the application of fuzzy correlations in the evaluation of student achievement. Moreover, the formulas derived in this study can be possibly applied to other shapes of fuzzy data such as triangular and trapezoidal fuzzy data.