Empirical Economic Model Discovery And Theory Evaluation

A synthesis of the authors' groundbreaking econometric research on automatic model selection, which uses powerful computational algorithms and theory evaluation. Economic models of empirical phenomena are developed for a variety of reasons, the most obvious of which is the numerical characterization of available evidence, in a suitably parsimonious form. Another is to test a theory, or evaluate it against the evidence; still another is to forecast future outcomes. Building such models involves a multitude of decisions, and the large number of features that need to be taken into account can overwhelm the researcher. Automatic model selection, which draws on recent advances in computation and search algorithms, can create, and then empirically investigate, a vastly wider range of possibilities than even the greatest expert. In this book, leading econometricians David Hendry and Jurgen Doornik report on their several decades of innovative research on automatic model selection. After introducing the principles of empirical model discovery and the role of model selection, Hendry and Doornik outline the stages of developing a viable model of a complicated evolving process. They discuss the discovery stages in detail, considering both the theory of model selection and the performance of several algorithms. They describe extensions to tackling outliers and multiple breaks, leading to the general case of more candidate variables than observations. Finally, they briefly consider selecting models specifically for forecasting.

Lucid account of the process of constructing and evaluating an empirical model.

A synthesis of the authors' groundbreaking econometric research on automatic model selection, which uses powerful computational algorithms and theory evaluation. Economic models of empirical phenomena are developed for a variety of reasons, the most obvious of which is the numerical characterization of available evidence, in a suitably parsimonious form. Another is to test a theory, or evaluate it against the evidence; still another is to forecast future outcomes. Building such models involves a multitude of decisions, and the large number of features that need to be taken into account can overwhelm the researcher. Automatic model selection, which draws on recent advances in computation and search algorithms, can create, and then empirically investigate, a vastly wider range of possibilities than even the greatest expert. In this book, leading econometricians David Hendry and Jurgen Doornik report on their several decades of innovative research on automatic model selection. After introducing the principles of empirical model discovery and the role of model selection, Hendry and Doornik outline the stages of developing a viable model of a complicated evolving process. They discuss the discovery stages in detail, considering both the theory of model selection and the performance of several algorithms. They describe extensions to tackling outliers and multiple breaks, leading to the general case of more candidate variables than observations. Finally, they briefly consider selecting models specifically for forecasting.

The main problem in econometric modelling of time series is discovering sustainable and interpretable relationships between observed economic variables. The primary aim of this book is to develop an operational econometric approach which allows constructive modelling. Professor Hendry deals with methodological issues (model discovery, data mining, and progressive research strategies); with major tools for modelling (recursive methods, encompassing, super exogeneity, invariance tests); and with practical problems (collinearity, heteroscedasticity, and measurement errors). He also includes an extensive study of US money demand. The book is self-contained, with the technical background covered in appendices. It is thus suitable for first year graduate students, and includes solved examples and exercises to facilitate its use in teaching. About the Series Advanced Texts in Econometrics is a distinguished and rapidly expanding series in which leading econometricians assess recent developments in such areas as stochastic probability, panel and time series data analysis, modeling, and cointegration. In both hardback and affordable paperback, each volume explains the nature and applicability of a topic in greater depth than possible in introductory textbooks or single journal articles. Each definitive work is formatted to be as accessible and convenient for those who are not familiar with the detailed primary literature.

Handbook of Empirical Economics and Finance explores the latest developments in the analysis and modeling of economic and financial data. Well-recognized econometric experts discuss the rapidly growing research in economics and finance and offer insight on the future direction of these fields. Focusing on micro models, the first group of chapters describes the statistical issues involved in the analysis of econometric models with cross-sectional data often arising in microeconomics. The book then illustrates time series models that are extensively used in empirical macroeconomics and finance. The last set of chapters explores the types of panel data and spatial models that are becoming increasingly significant in analyzing complex economic behavior and policy evaluations. This handbook brings together both background material and new methodological and applied results that are extremely important to the current and future frontiers in empirical economics and finance. It emphasizes inferential issues that transpire in the analysis of cross-sectional, time series, and panel data-based empirical models in economics, finance, and related disciplines.

This collection, written by highly-placed practitioners and academic economists, provides a picture of how economic modellers and policy makers interact. The book provides international case studies of particular interactions between models and policy making, and argues that the flow of information is two-way.

Concern about the role and the limits of modeling has heightened after repeated questions were raised regarding the dependability and suitability of the models that were used in the run-up to the 2008 financial crash. In this book, Lawrence Boland provides an overview of the practices of and the problems faced by model builders to explain the nature of models, the modeling process, and the possibility for and nature of their testing. In a reflective manner, the author raises serious questions about the assumptions and judgments that model builders make in constructing models. In making his case, he examines the traditional microeconomics-macroeconomics separation with regard to how theoretical models are built and used and how they interact, paying particular attention to the use of equilibrium concepts in macroeconomic models and game theory and to the challenges involved in building empirical models, testing models, and using models to test theoretical explanations.