在統計學上，我們常使用皮爾森相關係數(Pearson’s Correlation Coefficient)來表達兩變數間線性關係的強度，同時也表達出關係之方向。傳統之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，並不適合使用傳統的方法來計算模糊相關係數。而本研究探討區間模糊樣本資料值求得模糊相關係數，首先將區間型模糊資料分為離散型和連續型，提出區間模糊相關係數定義，並提出廣義誤差公式，將相關係數作合理的調整，使所求的出相關係數更加精確。在第三章我們以影響數學成就評量的因素，作實證研究分析，得出合理的分析。而此相關係數定義和廣義誤差公式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。 / In the statistic research, we usually express the magnitude of linear relation between two variables by means of Pearson’s Correlation Coefficient, which is also used to convey the direction of such relation. Traditionally, correlation coefficient deals with data which consist of specific real numbers. But when the data are composed of fuzzy numbers, it is not feasible to use this traditional approach to figure out the fuzzy correlation coefficient. The present study investigates the fuzzy samples of interval data to find out the fuzzy correlation coefficient. First, we categorize the fuzzy interval data into two types: discrete and continuous. Second, we define fuzzy correlation with interval data and propose broad formulas of error in order to adjust the coefficient more reasonably and deal with it more accurately. In Chapter Three, we conduct empirical research by the factor which affects the evaluation of mathematical achievement to acquire reasonable analysis. By doing so, broad definition of coefficient and formulas of error can also be applied to the conditions of either both values of the data are real number or one value of the data is real number, and can explain more related practical phenomenon.

本文所探討的中心為貝氏模型運用於加速壽命試驗，並且假設受測項目之壽命服從Weibull分配。加速實驗環境有三種，其中第二種環境代表正常狀態，採用加速壽命試驗的方式涵蓋了三種：固定應力、漸進之逐步應力和變量曲線之逐步應力。對於先驗參數，並不是直接給予特定的值，而是透過專家評估，給定各種環境之下的產品可靠度之中位數或百分位數，再利用這些資訊經過數值運算解出先驗參數。資料的型態分成兩種，一為區間資料，另一為型一設限資料，透過蒙地卡羅法模擬出後驗分配，並且估計正常環境狀態的可靠度。 / This article develops a Bayes inference model for accelerated life testing assuming failure times at each stress level are Weibull distributed. Using the approach, there are three stressed to be used, and the three testing scenarios to be adapted are as follows：fixed-stress, progressive step-stress and profile step-stress. Prior information is used to indirectly define a multivariate prior distribution for the scale parameters at the various stress levels. The inference procedure accommodates both the interval data sampling strategy and type I censored sampling strategy for the collection of ALT test data. The inference procedure uses the well-known Markov Chain Monte Carlo methods to derive posterior approximations.