ENBIS-16 in Sheffield

11 – 15 September 2016; Sheffield Abstract submission: 20 March – 4 July 2016

Improving the Standard Practice for Demonstrating Capability to Comply with an Acceptance Procedure (ASTM E2709)

13 September 2016, 10:50 – 11:10

Abstract

Submitted by
Jacqueline Asscher
Authors
Jacqueline Asscher (Kinneret College), Sharon Levi (Pharmaceutical Industry)
Abstract
This paper presents three improvements that were developed by the authors when they considered applying ASTM E2709 in a pharmaceutical company.
The standard itself follows an indirect strategy of using the sample mean and standard deviation of a sample of observations with a normal distribution to obtain a lower bound of the probability of passing a single-stage or multiple-stage acceptance procedure. A direct strategy would use the sample mean and standard deviation to evaluate compliance with specifications. The methodology in the standard is to check whether the entire triangular confidence region for the population mean and standard deviation lies within the region of combinations of population mean and standard deviation for which the probability of passing the acceptance procedure is at least a minimum required level. For multiple-criterion and multiple-stage acceptance procedures, the probability of passing the acceptance procedure is calculated as a lower bound.
The three improvements involved simplifying the calculations, extending the acceptance procedure to include an additional type of criterion, and using an alternative method to calculate the acceptance probabilities. Adopting the latter improvement reduces costs in many cases.
The question of whether the indirect strategy is at all useful is also raised.

Return to programme