A0196
Title: Sequential process monitoring using empirical likelihood methods
Authors: Cornelis Potgieter - Southern Methodist University (United States) [presenting]
Abstract: Many sequential monitoring procedures rely on strong parametric assumptions such as normality of the observations. When the parametric assumptions are not met, the procedure can have an inflated false signal rate. We construct sequential monitoring techniques using an empirical likelihood approach. These techniques can be used to monitor for a change in mean and/or variance, and can also be used to monitor more robust measures of location/scale. The performance of the proposed methods is compared to some procedures commonly used in practice.
