Preface

Summary

There has been much research conducted on non stationary time series in the last few decades, and the related literature continues to expand. Research on non stationary time series can be categorized into two areas: unit roots and cointegration. The literature on unit roots dates back to White (1958), and methods related to unit roots are now popular among economists and other social scientists. The concept of cointegration was developed by Engle and Granger (1987), and the techniques for cointegration have been accepted as standard tools in economics and other areas.

The aim of this book is to introduce the literature on unit roots in a comprehensive manner to both students and empirical and theoretical researchers in economics and other areas. The literature on nonstationary time series is now so huge that it seems difficult, if not impossible, to include all the related topics in a single monograph. Therefore, this book focuses on unit roots.

This book takes the approach of discussing as many papers as possible in presenting developments in the literature on unit roots. Yet it emphasizes important works that either contain novel ideas or have been cited often. By reading this book, the student or researcher can understand major developments in the literature on unit roots and related areas. The papers covered in this book were published in more than 30 major journals in econometrics, statistics, and other branches of social science up to 2013. A few unpublished papers and book chapters are also included.

This book is ideal for graduate students and researchers in economics, finance, political science, sociology, statistics, and other areas who want to learn about unit roots as they conduct their empirical research projects or theoretical research on unit roots. Material in this book can be taught in graduate-level courses on time series analysis along with more conventional textbooks such as Brockwell and Davies (1991), Hamilton (1994), and Fuller (1976). This book is also useful as a reference for researchers interested in nonstationary time series analysis.