Econometric and Tinbergen Institutes Lectures

Francis X. Diebold is the Paul F. and Warren S. Miller Professor of Economics at the University of Pennsylvania and professor of finance and statistics at the university's Wharton School. Glenn D. Rudebusch is executive vice president and director of economic research at the Federal Reserve Bank of San Francisco. They are the coauthors of Business Cycles: Durations, Dynamics, and Forecasting (Princeton). Understanding the dynamic evolution of the yield curve is critical to many financial tasks, including pricing financial assets and their derivatives, managing financial risk, allocating portfolios, structuring fiscal debt, conducting monetary policy, and valuing capital goods. Unfortunately, most yield curve models tend to be theoretically rigorous but empirically disappointing, or empirically successful but theoretically lacking. In this book, Francis Diebold and Glenn Rudebusch propose two extensions of the classic yield curve model of Nelson and Siegel that are both theoretically rigorous and empirically successful. The first extension is the dynamic Nelson-Siegel model (DNS), while the second takes this dynamic version and makes it arbitrage-free (AFNS). Diebold and Rudebusch show how these two models are just slightly different implementations of a single unified approach to dynamic yield curve modeling and forecasting. They emphasize both descriptive and efficient-markets aspects, they pay special attention to the links between the yield curve and macroeconomic fundamentals, and they show why DNS and AFNS are likely to remain of lasting appeal even as alternative arbitrage-free models are developed. Based on the Econometric and Tinbergen Institutes Lectures, Yield Curve Modeling and Forecasting contains essential tools with enhanced utility for academics, central banks, governments, and industry. "Diebold and Rudebusch have succeeded in writing a milestone book that will be used variously as a standard reference, a guide for future research topics, a text book, or as a convenient introduction to the topics of yield curve modeling and macro-finance. Hence, while forecasting (especially about the future) is always fraught with peril, I'm confident that copies of the book will find their way into many collections, and that they will be actively used when they get there."---Leo Krippner, International Review of Economics and Finance "[T]he methods presented in the book are of great importance in financial market practice. The book is designed for academics, students, and practitioners working in yield curve modeling and forecasting, and it will be useful for all interested in bond markets and their links with the macroeconomic environment."---Malgorzata Doman, Zentralblatt MATH "This lucid and concise book is unique in the field of term structure modeling. It leads readers from yield curve basics, with a popular and intuitive term structure model, to the frontiers of academia in associated fields. By the end of the book, readers will be inspired and enlightened enough to push those frontiers in the many open research directions noted by the authors, particularly in the emerging field of macro-finance."-Leo Krippner, Reserve Bank of New Zealand "This timely and enlightening book covers the latest developments in the cutting-edge field of yield curve modeling in financial economics and macro-finance. Even active researchers in this area undoubtedly will learn something new. The book is clearly written by two distinguished scholars who share their insights and provide many refreshing clear-cut messages about theoretical and empirical issues in yield curve modeling and forecasting."-Lasse Bork, Aalborg University, Denmark

John Geweke is Distinguished Research Professor at the University of Technology Sydney, and research professor at the University of Colorado. He is the coeditor of the Journal of Econometrics and his most recent previous book is Contemporary Bayesian Econometrics and Statistics (Wiley). Econometric models are widely used in the creation and evaluation of economic policy in the public and private sectors. But these models are useful only if they adequately account for the phenomena in question, and they can be quite misleading if they do not. In response, econometricians have developed tests and other checks for model adequacy. All of these methods, however, take as given the specification of the model to be tested. In this book, John Geweke addresses the critical earlier stage of model development, the point at which potential models are inherently incomplete. Summarizing and extending recent advances in Bayesian econometrics, Geweke shows how simple modern simulation methods can complement the creative process of model formulation. These methods, which are accessible to economics PhD students as well as to practicing applied econometricians, streamline the processes of model development and specification checking. Complete with illustrations from a wide variety of applications, this is an important contribution to econometrics that will interest economists and PhD students alike. "This book is original and powerful. It develops a Bayesian paradigm that embraces the reality of applied modeling, in which 'discoveries' of things previously unimagined are made regularly. It will be of immediate interest to all economists and statisticians who want to push Bayesian principles toward innovative practice (and who doesn't?)."-Francis X. Diebold, University of Pennsylvania "How do we know whether a statistical model is good enough for a particular economic research problem? To answer this question, John Geweke introduces the concept of incomplete models, showing how they can be effective tools for model building. This book is a significant contribution to econometrics-and a pleasure to read."-Richard Paap, Erasmus University Rotterdam "This excellent book seamlessly links many important econometric methods, models, and concepts."-Gary Koop, University of Strathclyde

Edward P. Herbst is an economist in the Division of Research and Statistics at the Federal Reserve Board. Frank Schorfheide is Professor of Economics at the University of Pennsylvania and research associate at the National Bureau of Economic Research. He also is a fellow of the Penn Institute for Economic Research, a visiting scholar at the Federal Reserve Banks of Philadelphia and New York, and a coeditor of Quantitative Economics. For more, see edherbst.net and sites.sas.upenn.edu/schorf. Dynamic stochastic general equilibrium (DSGE) models have become one of the workhorses of modern macroeconomics and are extensively used for academic research as well as forecasting and policy analysis at central banks. This book introduces readers to state-of-the-art computational techniques used in the Bayesian analysis of DSGE models. The book covers Markov chain Monte Carlo techniques for linearized DSGE models, novel sequential Monte Carlo methods that can be used for parameter inference, and the estimation of nonlinear DSGE models based on particle filter approximations of the likelihood function. The theoretical foundations of the algorithms are discussed in depth, and detailed empirical applications and numerical illustrations are provided. The book also gives invaluable advice on how to tailor these algorithms to specific applications and assess the accuracy and reliability of the computations. Bayesian Estimation of DSGE Models is essential reading for graduate students, academic researchers, and practitioners at policy institutions. "Well written and well organized, and the topic analyzed is very interesting and current."---Manuel Salvador, MathSciNet "This book depicts valuable and revealing methods for solving, estimating, and analyzing a class of dynamic equilibrium models of the macroeconomy. It describes formally tractable techniques for the study of macroeconomic models that feature transition mechanisms for a large number of underlying shocks. Both authors have played important roles in developing and applying these techniques. This is a terrific resource for how to use these methods in practice."-Lars Peter Hansen, David Rockefeller Distinguished Service Professor of Economics, University of Chicago, and recipient of the Nobel Prize in economics "This timely book collects in one place many of the key Markov chain Monte Carlo methods for numerical Bayesian inference along with many of their recent refinements. Written for applied users, it offers clear descriptions of each algorithm and illustrates how it can be used to estimate dynamic stochastic general equilibrium models in macroeconomics."-James D. Hamilton, Professor of Economics, University of California, San Diego "This is perhaps the most thorough book available on how to estimate DSGE models using sophisticated Bayesian computation tools. It is an excellent resource for professionals and advanced students of the topic."-Serena Ng, Professor of Economics, Columbia University

Peter E. Rossi is the James Collins Professor of Marketing, Economics, and Statistics at UCLA's Anderson School of Management. He has published widely in marketing, economics, statistics, and econometrics and is a coauthor of Bayesian Statistics and Marketing. This book reviews and develops Bayesian non-parametric and semi-parametric methods for applications in microeconometrics and quantitative marketing. Most econometric models used in microeconomics and marketing applications involve arbitrary distributional assumptions. As more data becomes available, a natural desire to provide methods that relax these assumptions arises. Peter Rossi advocates a Bayesian approach in which specific distributional assumptions are replaced with more flexible distributions based on mixtures of normals. The Bayesian approach can use either a large but fixed number of normal components in the mixture or an infinite number bounded only by the sample size. By using flexible distributional approximations instead of fixed parametric models, the Bayesian approach can reap the advantages of an efficient method that models all of the structure in the data while retaining desirable smoothing properties. Non-Bayesian non-parametric methods often require additional ad hoc rules to avoid "overfitting," in which resulting density approximates are nonsmooth. With proper priors, the Bayesian approach largely avoids overfitting, while retaining flexibility. This book provides methods for assessing informative priors that require only simple data normalizations. The book also applies the mixture of the normals approximation method to a number of important models in microeconometrics and marketing, including the non-parametric and semi-parametric regression models, instrumental variables problems, and models of heterogeneity. In addition, the author has written a free online software package in R, "bayesm," which implements all of the non-parametric models discussed in the book. "As the creator of bayesm (R software for Bayesian inference) and lead author of Bayesian Statistics and Marketing, Rossi has deep knowledge of the book's titular methods." "Peter Rossi, an expert on Bayesian analysis, presents a crisp introduction to an increasingly important class of models and their use in econometric applications."-Andrew Gelman, Columbia University "This book shows that a combination of the Bayesian paradigm and (infinite) mixtures of normal distributions can be used to construct a very flexible and robust class of semi- or non-parametric methods. Rossi presents these methods in such a way that they can be applied by anyone with a basic knowledge of Bayesian econometrics. The book will be highly valued as a source of inspiration for incorporating non-parametric ideas in Bayesian models and as a reference for many applications of these techniques."-Dennis Fok, Erasmus University Rotterdam "Rossi shows that the Bayesian approach to statistics can be applied to marketing and microeconometrics data without making the strong 'parametric' assumptions about functional forms and error distribution that are commonly made. The discussion and examples make a good case for the non-parametric Bayesian approach to these problems, and researchers will find it a valuable resource."-Edward Greenberg, professor emeritus, Washington University in St. Louis