Statistical Inference In Continuous Time Economic Models

Continuous-time econometrics is no longer an esoteric subject although most still regard it as such, so much so that it is hardly mentioned in standard textbooks on econometrics. Thanks to the work done in the last 20 years, both the theoretical and the applied side are by now well developed. Methods of estimation have been theoretically elaborated and practically implemented through computer programs. Continuous-time macroeconometric models for different countries have been constructed, estimated and used. Being myself involved in these developments, it was with great pleasure that I accepted the invitation to organize a session on continuous-time econometrics in the context of the International Symposium on Economic Modelling (jointly organized by the University of Urbino and the book series International Studies in Economic Modelling, and co-sponsored by the Consiglio Nazionale delle Ricerche). The reaction of 'continuists' from all over the world was so enthusiastic that I was able to arrange two sessions, one on the theory and the other on the applications. The symposium was held in Urbino on 23-25 July 1990. The papers presented in Urbino have been revised in the light of the discussion at the symposium and the referees' comments. Hence, what is published here should become another standard reference in the field of continuous-time econometrics.

Economic Modeling and Inference takes econometrics to a new level by demonstrating how to combine modern economic theory with the latest statistical inference methods to get the most out of economic data. This graduate-level textbook draws applications from both microeconomics and macroeconomics, paying special attention to financial and labor economics, with an emphasis throughout on what observations can tell us about stochastic dynamic models of rational optimizing behavior and equilibrium. Bent Jesper Christensen and Nicholas Kiefer show how parameters often thought estimable in applications are not identified even in simple dynamic programming models, and they investigate the roles of extensions, including measurement error, imperfect control, and random utility shocks for inference. When all implications of optimization and equilibrium are imposed in the empirical procedures, the resulting estimation problems are often nonstandard, with the estimators exhibiting nonregular asymptotic behavior such as short-ranked covariance, superconsistency, and non-Gaussianity. Christensen and Kiefer explore these properties in detail, covering areas including job search models of the labor market, asset pricing, option pricing, marketing, and retirement planning. Ideal for researchers and practitioners as well as students, Economic Modeling and Inference uses real-world data to illustrate how to derive the best results using a combination of theory and cutting-edge econometric techniques. Covers identification and estimation of dynamic programming models Treats sources of error--measurement error, random utility, and imperfect control Features financial applications including asset pricing, option pricing, and optimal hedging Describes labor applications including job search, equilibrium search, and retirement Illustrates the wide applicability of the approach using micro, macro, and marketing examples

Non-recursive models as discrete approximations to systems of stochastic differential equations; Some discrete approximations to continuous time stochastic models; Econometric estimation of stochastic differential equation systems; The structural estimation of a stochastic differnetial equation system; The problem of identification in finite parameter continuous time models; The estimation of linear stochastic differnetial equations with exogenous variables; Some computations based on observed data series of the exogenous variable component in continuous systems; Fourier estimation of continuous time models; A model of disequilibrium neoclassical growth and its applications to the United Kingdom.

This monograph presents a continuous time macroeconometric model of the United Kingdom incorporating stochastic trends. It describes the model in detail to permit a rigorous mathematical analysis of its steady-state and stability properties, thus providing a valuable check on the capacity of the model to generate plausible long-run behaviour.

This unique book provides an overview of continuous time modeling in the behavioral and related sciences. It argues that the use of discrete time models for processes that are in fact evolving in continuous time produces problems that make their application in practice highly questionable. One main issue is the dependence of discrete time parameter estimates on the chosen time interval, which leads to incomparability of results across different observation intervals. Continuous time modeling by means of differential equations offers a powerful approach for studying dynamic phenomena, yet the use of this approach in the behavioral and related sciences such as psychology, sociology, economics and medicine, is still rare. This is unfortunate, because in these fields often only a few discrete time (sampled) observations are available for analysis (e.g., daily, weekly, yearly, etc.). However, as emphasized by Rex Bergstrom, the pioneer of continuous-time modeling in econometrics, neither human beings nor the economy cease to exist in between observations. In 16 chapters, the book addresses a vast range of topics in continuous time modeling, from approaches that closely mimic traditional linear discrete time models to highly nonlinear state space modeling techniques. Each chapter describes the type of research questions and data that the approach is most suitable for, provides detailed statistical explanations of the models, and includes one or more applied examples. To allow readers to implement the various techniques directly, accompanying computer code is made available online. The book is intended as a reference work for students and scientists working with longitudinal data who have a Master's- or early PhD-level knowledge of statistics.