A design criterion for symmetric model discrimination based on flexible nominal sets

Description

Experimentaldesign applications for discriminating between models have been hampered by the assumption of knowing beforehand which model is the trueone, which is counter to the very aim of the experiment. Previous approaches to alleviate this requirement were either symmetrizations of asymmetric techniques, or Bayesian, minimax, and sequential methods. We present a genuinely symmetric criterion based on a linearized distance between mean value surfaces and the newly introduced tool of flexible nominal sets. We demonstrate the computational efficiency of the approach using the proposed criterion and provide a Monte Carlo evaluation of its discrimination performance based on the likelihood ratio. An application for a pair of competing models in enzyme kinetics is given.

Period	24 Aug 2022
Event title	Compstat 2022
Event type	Conference
Location	ItalyShow on map