|
Organizers |
Inference for the two-component error model
by
Geoff Jones
Massey University
The two-component error model was introduced by Rocke and Lorenzo (Technometrics, 1995, 37 pp176-184) for modelling the errors in a calibration assay. It postulates the presence of both additive and multiplicative errors in a regression relationship. Estimation and inference based on maximum likelihood are rather difficult because they are based on the numerical optimization of a numerically integrated likelihood. In particular, interval estimation of unknown concentrations is a seemingly intractable problem. Here Markov chain Monte Carlo methods are considered as an alternative.
Date received: August 29, 2001
Copyright © 2001 by the author(s). The author(s) of this document and the organizers of the conference have granted their consent to include this abstract in Atlas Conferences Inc. Document # cahg-41.