Document ESAIM: PS, 2008, Vol. 12, p. 196-218
DOI: 10.1051/ps:2007045
Parametric inference for mixed models defined by stochastic differential equations
Sophie Donnet1 and Adeline Samson21 Paris-Sud University, Laboratoire de Mathématiques, Orsay, France; UMR CNRS 8145, University Paris 5, Paris, France; adeline.samson@univ-paris5.fr
2 INSERM U738, Paris, France; University Paris 7, Paris, France; UMR CNRS 8145, University Paris 5, Paris, France
Received July 13, 2006. Revised April 14, 2007. Published online 23 January 2008
Abstract
Non-linear mixed models defined by stochastic differential equations (SDEs) are considered: the parameters of the diffusion process are random variables and vary among the individuals. A maximum likelihood estimation method based on the Stochastic Approximation EM algorithm, is proposed.
This estimation method uses the Euler-Maruyama approximation of the diffusion, achieved using latent auxiliary data introduced to complete the diffusion process between each pair of measurement instants.
A tuned hybrid Gibbs algorithm based on conditional Brownian bridges simulations of the unobserved process paths is included in this algorithm.
The convergence is proved and the error induced on the likelihood by the Euler-Maruyama approximation is bounded as a function of the step size of the approximation.
Results of a pharmacokinetic simulation study illustrate the accuracy of this estimation method. The analysis of the Theophyllin real dataset illustrates the relevance of the SDE approach relative to the deterministic approach.
Mathematics Subject Classification. 62M99, 62F10, 62F15, 62M09, 62L20, 65C30, 65C40, 62P10
Key words: Brownian bridge, diffusion process, Euler-Maruyama approximation, Gibbs algorithm, incomplete data model, maximum likelihood estimation, non-linear mixed effects model, SAEM algorithm
© EDP Sciences, SMAI 2008