Mixed Effects in Stochastic Differential Equation Models

Abstract

A class of statistical models is proposed where random effects are incorporated into a stochastic differential equations model, and an expression for the likelihood function is derived. In general, though, it is not possible to find an explicit expression for the likelihood function, but in a very simple example it is derived and explicit maximum likelihood estimators are found. The estimators are evaluated in a simulation study, and illustrated on dissolution data of metoprolol tartrate tablets.