Preface

Summary

Objectives of the Book

Since the seminal work of Sims (1980a), structural vector autoregressions have evolved into one of the most widely used models in empirical research using time series data. They are used in macroeconomics and in empirical finance, but also in many other fields including agricultural economics and energy economics. The evolution of the structural vector autoregressive (VAR) methodology since 1980 has not always been smooth. Over time many new ideas have been explored, sometimes uncritically applied or misunderstood by practitioners, then questioned, and later refined or replaced by alternative methods. The development of new methods of identification, estimation, and inference for structural VAR models continues at a rapid pace even today. One of the objectives of this book is to summarize these new developments and to put them in perspective. The other is to take stock of what we have learned about more traditional structural VAR models and to interpret these models from today's perspective. The profession's understanding of these models has evolved substantially, becoming more nuanced in recent years and allowing us to understand better some of the methodological debates of the past.

In this book, we not only review the ever-increasing range of structural VAR tools and methods discussed in the literature; we also highlight their pros and cons in practice and provide guidance to empirical researchers as to the most appropriate modeling choices. In addition, we trace the evolution of the structural VAR methodology and contrast it with other common methodologies including the narrative approach to identification and the use of calibrated or estimated dynamic stochastic general equilibrium (DSGE) models. We stress that structural VAR models should be viewed as one of several econometric tools used in empirical work, each of which has its own strengths and weaknesses.

The book is intended as a bridge between the often quite technical econometric literature on structural VAR modeling and the needs of empirical researchers. The focus of the book is not on providing the most rigorous theoretical arguments, but on enhancing the reader's understanding of the methods in question and their assumptions, allowing him or her to decide on the most suitable methods for applied work. In many cases, empirical examples are provided for illustration. References to articles in academic journals are provided for readers with an interest in the more technical aspects of the discussion.