Economic forecasting involves choosing simple yet robust models to best approximate highly complex and evolving data-generating processes. This poses unique challenges for researchers in a host of practical forecasting situations, from forecasting budget deficits and assessing financial risk to predicting inflation and stock market returns. Economic Forecasting presents a comprehensive, unified approach to assessing the costs and benefits of different methods currently available to forecasters. This text approaches forecasting problems from the perspective of decision theory and estimation, and demonstrates the profound implications of this approach for how we understand variable selection, estimation, and combination methods for forecasting models, and how we evaluate the resulting forecasts. Both Bayesian and non-Bayesian methods are covered in depth, as are a range of cutting-edge techniques for producing point, interval, and density forecasts. The book features detailed presentations and empirical examples of a range of forecasting methods and shows how to generate forecasts in the presence of large-dimensional sets of predictor variables. The authors pay special attention to how estimation error, model uncertainty, and model instability affect forecasting performance. * Presents a comprehensive and integrated approach to assessing the strengths and weaknesses of different forecasting methods* Approaches forecasting from a decision theoretic and estimation perspective* Covers Bayesian modeling, including methods for generating density forecasts* Discusses model selection methods as well as forecast combinations* Covers a large range of nonlinear prediction models, including regime switching models, threshold autoregressions, and models with time-varying volatility* Features numerous empirical examples* Examines the latest advances in forecast evaluation* Essential for practitioners and students alike

For some seven decades, econometrics has been almost exclusiveley dealing with constructing and applying econometric equation systems, which constitute constraints in econometric optimization models. The second major component, the scalarvalued objective function, has only in recent years attracted more attention and some progress has been made. This book is devoted to theories, models and methods for constructing scalarvalued objective functions for econometric optimization models, to their applications, and to some related topics like historical issues about pioneering contributions by Ragnar Frisch and Jan Tinbergen.

Over the past 25 years, applied econometrics has undergone tremen dous changes, with active developments in fields of research such as time series, labor econometrics, financial econometrics and simulation based methods. Time series analysis has been an active field of research since the seminal work by Box and Jenkins (1976), who introduced a gen eral framework in which time series can be analyzed. In the world of financial econometrics and the application of time series techniques, the ARCH model of Engle (1982) has shifted the focus from the modelling of the process in itself to the modelling of the volatility of the process. In less than 15 years, it has become one of the most successful fields of 1 applied econometric research with hundreds of published papers. As an alternative to the ARCH modelling of the volatility, Taylor (1986) intro duced the stochastic volatility model, whose features are quite similar to the ARCH specification but which involves an unobserved or latent component for the volatility. While being more difficult to estimate than usual GARCH models, stochastic volatility models have found numerous applications in the modelling of volatility and more particularly in the econometric part of option pricing formulas. Although modelling volatil ity is one of the best known examples of applied financial econometrics, other topics (factor models, present value relationships, term structure 2 models) were also successfully tackled."

Empirical Studies In Applied Economics presents nine previously unpublished analyses in monograph form. In this work, the topics are presented so that each chapter stands on its own. The emphasis is on the applications but attention is also given to the econometric and statistical issues for advanced readers. Econometric methods include multivariate regression analysis, limited dependent variable analysis, and other maximum likelihood techniques. The empirical topics include the measurement of competition and market power in natural gas transportation markets and in the pharmaceutical market for chemotherapy drugs. Additional topics include an empirical analysis of NFL football demand, the accuracy of an econometric model for mail demand, and the allocation of police services in rural Alaska. Other chapters consider the valuation of technology patents and the determination of patent scope, duration, and reasonable royalty, and the reaction of financial markets to health scares in the fast-food industry. Finally, two chapters are devoted to the theory and testing of synergistic health effects from the combined exposure to asbestos and cigarette smoking.

The present book deals with coalition games in which expected pay-offs are only vaguely known. In fact, this idea about vagueness of expectations ap pears to be adequate to real situations in which the coalitional bargaining anticipates a proper realization of the game with a strategic behaviour of players. The vagueness being present in the expectations of profits is mod elled by means of the theory of fuzzy set and fuzzy quantities. The fuzziness of decision-making and strategic behaviour attracts the attention of mathematicians and its particular aspects are discussed in sev eral works. One can mention in this respect in particular the book "Fuzzy and Multiobjective Games for Conflict Resolution" by Ichiro Nishizaki and Masatoshi Sakawa (referred below as 43]) which has recently appeared in the series Studies in Fuzziness and Soft Computing published by Physica-Verlag in which the present book is also apperaing. That book, together with the one you carry in your hands, form in a certain sense a complementary pair. They present detailed views on two main aspects forming the core of game theory: strategic (mostly 2-person) games, and coalitional (or cooperative) games. As a pair they offer quite a wide overview of fuzzy set theoretical approaches to game theoretical models of human behaviour."

In this book, time use behavior within households is modeled as the outcome of a bargaining process between family members who bargain over household resource allocation and the intrafamily distribution of welfare. In view of trends such as rising female employment along with falling fertility rates and increasing divorce rates, a strategic aspect of female employment is analyzed in a dynamic family bargaining framework. The division of housework between spouses and the observed leisure differential between women and men are investigated within non-cooperative bargaining settings. The models developed are tested empirically using data from the German Socio-Economic Panel and the German Time Budget Survey.

Empirical measurement of impacts of active labour market programmes has started to become a central task of economic researchers. New improved econometric methods have been developed that will probably influence future empirical work in various other fields of economics as well. This volume contains a selection of original papers from leading experts, among them James J. Heckman, Noble Prize Winner 2000 in economics, addressing these econometric issues at the theoretical and empirical level. The theoretical part contains papers on tight bounds of average treatment effects, instrumental variables estimators, impact measurement with multiple programme options and statistical profiling. The empirical part provides the reader with econometric evaluations of active labour market programmes in Canada, Germany, France, Italy, Slovak Republic and Sweden.

Generalized method of moments (GMM) estimation of nonlinear systems has two important advantages over conventional maximum likelihood (ML) estimation: GMM estimation usually requires less restrictive distributional assumptions and remains computationally attractive when ML estimation becomes burdensome or even impossible. This book presents an in-depth treatment of the conditional moment approach to GMM estimation of models frequently encountered in applied microeconometrics. It covers both large sample and small sample properties of conditional moment estimators and provides an application to empirical industrial organization. With its comprehensive and up-to-date coverage of the subject which includes topics like bootstrapping and empirical likelihood techniques, the book addresses scientists, graduate students and professionals in applied econometrics.

and Feldman, 1996 or Audretsch and Stephan, 1996) show that unformalized knowledge may playa major role in the innovation of new products. Now if unformalized knowledge is communicated personally, distance will be an important variable in this process, since the intensity of contacts between persons can be expected to be negatively correlated to the distance between them. In the discussion of section 3.3.1 (page 42) we saw that it was this aspect of localization that Marshall had in mind when he was alluding to "local trade secrets."4 Note that if this spatial dimension of communication between agents exists, it is possible to transfer it to regional aggregates of agents: the closer two regions, the more they will be able to profit from the respective pool of human capital (R&D-output etc.) of the other region. This argument gives a spatial 5 interpretation of the literature on endogenous growth. Now if these spillovers have a spatial dimension then it follows from the discussion in chapter 3 that they will be one driving force in the dynamics of agglomeration. With the model to be developed in this chapter I will investigate the hy pothesis that it is these forces of agglomeration (i.e. spatial spillovers of nonrival goods or foctors) that are responsible for the inhomogeneous pattern of growth con vergence. To analyze this phenomenon, I consider different types of regional aggregates and different distances in the model."

This book deals with the omitted variable tests for a multivariate time-series regression model. What are the consequences of testing for the omission of a variable when the model is dynamically misspecified? What is the small sample bias of the omitted variable test when the model dynamics is correctly specificfied? The answers to these questions are proposed in this book. As an empirical illustration, the analysis is applied to the homogeneity test of a demand system. I particularly thank Professor Dr. Philippe J. Deschamps who draw my attention on this subject and who made very helpful comments and sugges- tions. Additionally, I would like to thank Professor Dr. Reiner Wolff for his comments especially on the chapter dealing with consumer theory. Special thanks go to Maria Jose Redondo, who read this book several times and for the inspiring discussions with her. I would also like to thank Dr. Ali Vak- ili (always ready to answer any questions in mathematics), Prof. Dr. Hans Wolf gang Brachinger, Curzio De Gottardi, Peter Mantsch, Dr. Paul-Andre Monney, Dr. Uwe Steinhauser, Leon Stroeks and Dr. Peter Windlin. Frances Angell improved the English of this work. The research for this book had been financially suppurted by the Univer- site de Fribourg (Switzerland). Finally, I appreciated the support from Springer-Verlag and I thank Dr.

Stochastic Volatility in Financial Markets presents advanced topics in financial econometrics and theoretical finance, and is divided into three main parts. The first part aims at documenting an empirical regularity of financial price changes: the occurrence of sudden and persistent changes of financial markets volatility. This phenomenon, technically termed stochastic volatility', or conditional heteroskedasticity', has been well known for at least 20 years; in this part, further, useful theoretical properties of conditionally heteroskedastic models are uncovered. The second part goes beyond the statistical aspects of stochastic volatility models: it constructs and uses new fully articulated, theoretically-sounded financial asset pricing models that allow for the presence of conditional heteroskedasticity. The third part shows how the inclusion of the statistical aspects of stochastic volatility in a rigorous economic scheme can be faced from an empirical standpoint.

An accessible treatment of Monte Carlo methods, techniques, and applications in the field of finance and economics Providing readers with an in-depth and comprehensive guide, the Handbook in Monte Carlo Simulation: Applications in Financial Engineering, Risk Management, and Economics presents a timely account of the applicationsof Monte Carlo methods in financial engineering and economics. Written by an international leading expert in thefield, the handbook illustrates the challenges confronting present-day financial practitioners and provides various applicationsof Monte Carlo techniques to answer these issues. The book is organized into five parts: introduction andmotivation; input analysis, modeling, and estimation; random variate and sample path generation; output analysisand variance reduction; and applications ranging from option pricing and risk management to optimization. The Handbook in Monte Carlo Simulation features: * An introductory section for basic material on stochastic modeling and estimation aimed at readers who may need a summary or review of the essentials * Carefully crafted examples in order to spot potential pitfalls and drawbacks of each approach * An accessible treatment of advanced topics such as low-discrepancy sequences, stochastic optimization, dynamic programming, risk measures, and Markov chain Monte Carlo methods * Numerous pieces of R code used to illustrate fundamental ideas in concrete terms and encourage experimentation The Handbook in Monte Carlo Simulation: Applications in Financial Engineering, Risk Management, and Economics is a complete reference for practitioners in the fields of finance, business, applied statistics, econometrics, and engineering, as well as a supplement for MBA and graduate-level courses on Monte Carlo methods and simulation.

The book reports experimental studies and a theoretical investigation of non-cooperative bargaining games with joint production. Such games have rarely been studied within laboratory experiments despite being more general and more natural than bargaining without production. It is shown that equity theory is a good predictor of subjects' behavior. Furthermore subjects exhibit different equity notions. One chapter addresses problems of statistical data analysis that are specific to experiments. Applying evolutionary game theory within a model of bargaining with production it is shown theoretically that altruistic preferences, which generate moderate bargaining behavior, can survive the process of evolution.

The three decades which have followed the publication of Heinz Neudecker's seminal paper `Some Theorems on Matrix Differentiation with Special Reference to Kronecker Products' in the Journal of the American Statistical Association (1969) have witnessed the growing influence of matrix analysis in many scientific disciplines. Amongst these are the disciplines to which Neudecker has contributed directly - namely econometrics, economics, psychometrics and multivariate analysis. This book aims to illustrate how powerful the tools of matrix analysis have become as weapons in the statistician's armoury. The majority of its chapters are concerned primarily with theoretical innovations, but all of them have applications in view, and some of them contain extensive illustrations of the applied techniques. This book will provide research workers and graduate students with a cross-section of innovative work in the fields of matrix methods and multivariate statistical analysis. It should be of interest to students and practitioners in a wide range of subjects which rely upon modern methods of statistical analysis. The contributors to the book are themselves practitioners of a wide range of subjects including econometrics, psychometrics, educational statistics, computation methods and electrical engineering, but they find a common ground in the methods which are represented in the book. It is envisaged that the book will serve as an important work of reference and as a source of inspiration for some years to come.

The use of computer simulations to study social phenomena has grown rapidly during the last few years. Many social scientists from the fields of economics, sociology, psychology and other disciplines now use computer simulations to study a wide range of social phenomena. The availability of powerful personal computers, the development of multidisciplinary approaches and the use of artificial intelligence models have all contributed to this development. The benefits of using computer simulations in the social sciences are obvious. This holds true for the use of simulations as tools for theory building and for its implementation as a tool for sensitivity analysis and parameter optimization in application-oriented models. In both, simulation provides powerful tools for the study of complex social systems, especially for dynamic and multi-agent social systems in which mathematical tractability is often impossible. The graphical display of simulation output renders it user friendly to many social scientists that lack sufficient familiarity with the language of mathematics. The present volume aims to contribute in four directions: (1) To examine theoretical and methodological issues related to the application of simulations in the social sciences. By this we wish to promote the objective of designing a unified, user-friendly, simulation toolkit which could be applied to diverse social problems. While no claim is made that this objective has been met, the theoretical issues treated in Part 1 of this volume are a contribution towards this objective.

Parallel Algorithms for Linear Models provides a complete and detailed account of the design, analysis and implementation of parallel algorithms for solving large-scale linear models. It investigates and presents efficient, numerically stable algorithms for computing the least-squares estimators and other quantities of interest on massively parallel systems. The monograph is in two parts. The first part consists of four chapters and deals with the computational aspects for solving linear models that have applicability in diverse areas. The remaining two chapters form the second part, which concentrates on numerical and computational methods for solving various problems associated with seemingly unrelated regression equations (SURE) and simultaneous equations models. The practical issues of the parallel algorithms and the theoretical aspects of the numerical methods will be of interest to a broad range of researchers working in the areas of numerical and computational methods in statistics and econometrics, parallel numerical algorithms, parallel computing and numerical linear algebra. The aim of this monograph is to promote research in the interface of econometrics, computational statistics, numerical linear algebra and parallelism.

Are foreign exchange markets efficient? Are fundamentals important for predicting exchange rate movements? What is the signal-to-ratio of high frequency exchange rate changes? Is it possible to define a measure of the equilibrium exchange rate that is useful from an assessment perspective? The book is a selective survey of current thinking on key topics in exchange rate economics, supplemented throughout by new empirical evidence. The focus is on the use of advanced econometric tools to find answers to these and other questions which are important to practitioners, policy-makers and academic economists. In addition, the book addresses more technical econometric considerations such as the importance of the choice between single-equation and system-wide approaches to modelling the exchange rate, and the reduced form versus structural equation problems. Readers will gain both a comprehensive overview of the way macroeconomists approach exchange rate modelling, and an understanding of how advanced techniques can help them explain and predict the behavior of this crucial economic variable.

A novel methodology is put forward in this book, which empowers researchers to investigate and identify potential spatial processes among a set of regions. Spatial processes and their underlying functional spatial relationships are commonly observed in the geosciences and related disciplines. Examples are spatially autocorrelated random variables manifesting themselves in distinct global patterns as well as local clusters and hot spots, or spatial interaction leading to stochastic ties among the regions. An example from observational epidemiology demonstrates the flexibility of Moran's approach by analyzing the spatial distribution of cancer data from several perspectives. Recent advances in computing technology, computer algorithms, statistical techniques and global and local spatial patterns by means of Moran's "I" feasability. Moran's "I" is an extremely versatile tool for exploring and analyzing spatial data and testing spatial hypotheses.

The analysis ofwhat might be called "dynamic nonlinearity" in time series has its roots in the pioneering work ofBrillinger (1965) - who first pointed out how the bispectrum and higher order polyspectra could, in principle, be used to test for nonlinear serial dependence - and in Subba Rao and Gabr (1980) and Hinich (1982) who each showed how Brillinger's insight could be translated into a statistical test. Hinich's test, because ittakes advantage ofthe large sample statisticalpropertiesofthe bispectral estimates became the first usable statistical test for nonlinear serial dependence. We are forever grateful to Mel Hinich for getting us involved at that time in this fascinating and fruitful endeavor. With help from Mel (sometimes as amentor, sometimes as acollaborator) we developed and applied this bispectral test in the ensuing period. The first application ofthe test was to daily stock returns {Hinich and Patterson (1982, 1985)} yielding the important discovery of substantial nonlinear serial dependence in returns, over and above the weak linear serial dependence that had been previously observed. The original manuscript met with resistance from finance journals, no doubt because finance academics were reluctant to recognize the importance of distinguishing between serial correlation and nonlinear serial dependence. In Ashley, Patterson and Hinich (1986) we examined the power and sizeofthe test in finite samples.

The maximum principle and dynamic programming are the two most commonly used approaches in solving optimal control problems. These approaches have been developed independently. The theme of this book is to unify these two approaches, and to demonstrate that the viscosity solution theory provides the framework to unify them.

Neural networks have had considerable success in a variety of disciplines including engineering, control, and financial modelling. However a major weakness is the lack of established procedures for testing mis-specified models and the statistical significance of the various parameters which have been estimated. This is particularly important in the majority of financial applications where the data generating processes are dominantly stochastic and only partially deterministic. Based on the latest, most significant developments in estimation theory, model selection and the theory of mis-specified models, this volume develops neural networks into an advanced financial econometrics tool for non-parametric modelling. It provides the theoretical framework required, and displays the efficient use of neural networks for modelling complex financial phenomena. Unlike most other books in this area, this one treats neural networks as statistical devices for non-linear, non-parametric regression analysis.

Franz Ferschl is seventy. According to his birth certificate it is true, but it is unbelievable. Two of the three editors remembers very well the Golden Age of Operations Research at Bonn when Franz Ferschl worked together with Wilhelm Krelle, Martin Beckmann and Horst Albach. The importance of this fruitful cooperation is reflected by the fact that half of the contributors to this book were strongly influenced by Franz Ferschl and his colleagues at the University of Bonn. Clearly, Franz Ferschl left his traces at all the other places of his professional activities, in Vienna and Munich. This is demonstrated by the present volume as well. Born in 1929 in the Upper-Austrian Miihlviertel, his scientific education brought him to Vienna where he studied mathematics. In his early years he was attracted by Statistics and Operations Research. During his employment at the Osterreichische Bundeskammer fUr Gewerbliche Wirtschaft in Vienna he prepared his famous book on queueing theory and stochastic processes in economics. This work has been achieved during his scarce time left by his duties at the Bundeskammer, mostly between 6 a.m. and midnight. All those troubles were, however, soon rewarded by the chair of statistics at Bonn University. As a real Austrian, the amenities of the Rhineland could not prevent him from returning to Vienna, where he took the chair of statistics.

Nonlinear Time Series Analysis of Economic and Financial Data provides an examination of the flourishing interest that has developed in this area over the past decade. The constant theme throughout this work is that standard linear time series tools leave unexamined and unexploited economically significant features in frequently used data sets. The book comprises original contributions written by specialists in the field, and offers a combination of both applied and methodological papers. It will be useful to both seasoned veterans of nonlinear time series analysis and those searching for an informative panoramic look at front-line developments in the area.

In the mid-eighties Mehra and Prescott showed that the risk premium earned by American stocks cannot reasonably be explained by conventional capital market models. Using time additive utility, the observed risk pre mium can only be explained by unrealistically high risk aversion parameters. This phenomenon is well known as the equity premium puzzle. Shortly aft erwards it was also observed that the risk-free rate is too low relative to the observed risk premium. This essay is the first one to analyze these puzzles in the German capital market. It starts with a thorough discussion of the available theoretical mod els and then goes on to perform various empirical studies on the German capital market. After discussing natural properties of the pricing kernel by which future cash flows are translated into securities prices, various multi period equilibrium models are investigated for their implied pricing kernels. The starting point is a representative investor who optimizes his invest ment and consumption policy over time. One important implication of time additive utility is the identity of relative risk aversion and the inverse in tertemporal elasticity of substitution. Since this identity is at odds with reality, the essay goes on to discuss recursive preferences which violate the expected utility principle but allow to separate relative risk aversion and intertemporal elasticity of substitution."

This study was written while I was a doctoral student in the Graduier- tenkolleg Finanz-und Gutermiirkte at the University of Mannheim; it has been accepted as a doctoral dissertation in February 1997. I am indebted to my advisors, Professors Axel Borsch-Supan and Martin Hellwig at Mannheim and John Rust at Madison, for their encouragement and for many helpful discussions and comments. At various stages, I benefited from comments on portions of the manu- script by, and from discussions with, Thomas Astebro, Charles Calomiris, Timothy Dunne, Frank Gerhard, Annette Kohler, Jens Koke, Stephan Monissen, Gordon Phillips, Winfried Pohlmeier, Kenneth Troske, Wol- fram Wissler and seminar participants at Columbia Business School, the University of Mannheim, the University of Tiibingen, the University of Wisconsin at Madison, Yale University, the ENTER Jamborees at Uni- versity College London, January 1995, and at Tilburg University, January 1997, at a Meeting of the DFG-Schwerpunktprogramm Industrieokonomik und Inputmiirkte, Heidelberg, November 1996, and at the annual meeting of the Verein fur Socialpolitik, Bern, September 1997. Silke Januszewski and Melanie Liihrmann provided dedicated assistence during the prepa- ration of the final version of the manuscript.