Introduction

This book provides a comprehensive approach to the many computational procedures that can be applied to a previously specified linear model in State-Space (SS) form. Some important advantages of the SS approach are listed. A model is a mathematical representation of a system. A procedure is a tool to manipulate a model. Models and procedures are different things and, therefore, a desirable feature for any procedure is to be independent of particular model formulations. Accordingly, it makes sense to concentrate the development of computational procedures on the SS model, using the generality of this formulation as an “abstraction layer” to separate them from specific model families. Throughout the book, two models are considered to be equivalent if they result in the same probability distribution of the sample. This concept is also known as “observational equivalence” in the literature.