近年來,製程能力指標已被多數的品管工程師廣泛地應用在品質管制方面,以評估製程是否合乎能力水準。然而,工業製造上通常包含許多非常態的製程,所以在使用常態假設下的製程能力指標時,會導致錯誤的結果。基於這個理由,本文利用Clements’ method,針對非常態分配,Lognormal與Inverse Gaussian分配,參數與偏態及峰度之間的關係,探討偏態和峰度的變化對於估計製程能力指標的影響。研究結果顯示,在Lognormal分配下所估計的製程能力指標較Inverse Gaussian分配更具有準確性和精確度。 In recent years, process capability indices (PCI’s) have been applied in the quality control by most practitioners, that are used to assess the ability of a production process whether is capable. However, industrial production usually involves many non-normal processes, so the use of PCI’s based on an assumption of a normality may yield misleading results. Due to this reason, this article use Clements’ method to calculating estimators of the process capability indices based on two non-normal distributions, Lognormal and Inverse Gaussian distributions. Furthermore, comparing the effect between the variety of skewness and kurtosis with parameters in measuring process capability. The simulation results indicate that the Lognormal distribution is more accurate and precise than the Inverse Gaussian distribution in measuring process capability.