Handbook of econometrics. Vol. 5 (Q5959704)

This fifth volume of the ``Handbook of Econometrics'' is concerned with new developments in theoretical econometrics. Divided into three parts, eight different topics are presented by authors which are known to be specialists in these fields. The primary objective of the volume is to collate in one place a body of research tools useful in applied econometrics and in empirical research in economics. Another objective of the series is to update the essays on theoretical econometrics presented in the previous volumes of the series to include improvements in methods previously surveyed and methods not previously surveyed. The first part contains four essays on developments in econometric theory. In a comprehensive survey, \textit{J. Horowitz} reviews recent developments on the bootstrap in econometrics and statistics with special emphasis on the application of the bootstrap to econometric models. The second essay, by \textit{M. Arellano} and \textit{Bo Honoré}, is an update of the essay by \textit{G. Chamberlain} on panel data in Volume 2 of this series, see Zbl 0585.62185, to reflect developments in panel data methods in the past decade and a half. After this chapter, \textit{W. Brock} and \textit{S. Durlauf} present a first rigorous econometric analysis of models of social interactions. This field has been an active area of research in economic theory, but formal econometric analysis was still outstanding up to now. \textit{G. van den Berg} updates the essay by \textit{J.J. Heckman} and \textit{B. Singer} in Volume 3 of the Handbook, see Zbl 0604.62114, to consider developments in econometric duration analysis. The essays in the second part (Part 12 of the series) present comprehensive surveys of new computational methods in econometrics. Special interest is devoted to Bayesian methods in econometrics, which offer an attractive alternative to classical methods given that computational costs are very low nowadays. In Part 13 two main topics are covered. The first topic deals with calibration as an econometric method and is written by \textit{C. Dawkins}, \textit{T.N. Srinivasan} and \textit{J. Whalley}. Measurement errors and its consequences in economic data are the second topic surveyed by \textit{J. Bound}, \textit{C. Brown} and \textit{N. Mathiowetz}. Focusing primarily on data from labor markets, the authors document that the model of classical measurement errors finds little support in the data. New patterns of measurement errors are found that provide suggestions on what an empirically concordant model of measurement errors would look like.