A QUASI-LIKELIHOOD APPROACH TO ESTIMATING PARAMETERS IN DIFFUSION-TYPE PROCESSES

Estimation of parameters in diffusion models is usually handled by maximum likelihood and involves the calculation of a Radon-Nikodym derivative. This methodology is often not available when minor changes are made to the model. However, these complications can usually be avoided and results obtained under more general conditions using quasi-likelihood methods. The basic ideas are explained in this paper and are illustrated through discussion of the Cox-Ingersoll Ross model and a modification of the Langevin model.