Construction of upper confidence limit of coefficient of variation for content uniformity

Abstract

Relative standard deviation (coefficient of variation) plays an important role in meeting the current compendial requirements for content uniformity. Since the sample RSD value would vary from sample to sample in a population (batch), the scientist would need not only the sample estimate of the RSD but also its 95% two-sided upper confidence limit, for making the proper statistical inference as well as for arriving at the appropriate pharmaceutics decisions. The primary purpose of this paper is to depict the five available methods for determining the confidence limit and to discuss their relative merits and similarities in the context of a content uniformity study associated with Product-C. Suitable tables are furnished to facilitate rapid access to the desired RSD confidence limit.