Essays in applied time series econometric methodology : the role of random field regression

Abstract

This thesis is a collection of essays in applied time series econometrics, focusing particularly on the role of random field regression. The thesis is introduced in Chapter 1, which discusses the motivation for the thesis and outlines its structure. The second chapter discusses nonlinear econometric modelling. It introduces the concept of nonlinearity and discusses its importance in economics and econometrics. It also provides a treatment of several approaches to modelling nonlinearity in economics, before giving an account of the approach to nonlinear econometric modelling proposed by Hamilton (2001). It then describes some of the methods of nonlinear optimisation that may be used in the Gauss computer program provided by Hamilton for the implementation of his methodology. The performance of this program is investigated using data relating to Hamilton's examples, two versions of the Gauss software and a range of alternative numerical optimisation options.