| Abstract: | We consider modified tolerance intervals for assessing content (dose) uniformity from one‐ and two‐stage designs. This work was motivated by a proposal from the International Pharmaceutical Aerosol Consortium on Regulation and Science (IPAC‐RS) to modify tolerance intervals to reduce their known conservatism away from the centre of the acceptance interval. IPAC‐RS's original proposal suffers from anti‐conservatism, but we find this is due to the choice of constants, not the form of the acceptance rule. We propose an alternative basis for choosing the constants in the acceptance rules and compare attained levels to those of other choices, including revised constants proposed by IPAC‐RS. These alternate choices of the constants lead to modified tolerance intervals that are either conservative at the sample sizes for which they were chosen or may have slight anti‐conservatism, within the limits of the simulations. Copyright © 2004 John Wiley & Sons, Ltd. |
