The aim of this third, completely re-written, re-edited and considerably expanded, edition of this book is to provide a general overview of both the basics and - cent, more sophisticated, theoretical developments in panel data econometrics. It also aims at covering a number of ?elds of applications where these methods are used for improving our knowledge and understanding of economic agents’ beh- iors. Since the pioneering works of Edwin Kuh (1959), Yair Mundlak (1961), Irving Hoch (1962), and Pietro Balestra and Marc Nerlove (1966), the pooling of cross s- tions and time series data has become an increasingly popular way of quantifying economic relationships. Each series provides information lacking in the other, so a combination of both leads to more accurate, reliable and informative results than would be achievable by one type of series alone. Over the last three decades of the last century, much fundamental work has been done: investigation of the properties of different estimators and test statistics, analysis of dynamic models and the effects of eventual measurement errors, etc. The more recent years and in particular the ten years elapsed since the second edition of this book have witnessed even more considerable changes. Indeed, our ability to estimate and test nonlinear models have dramatically improved and issues such as the unobserved heterogeneity in nonlinear models, attrition and selectivity bias have received considerable attention. This explains why the number of chapters dealing with such issues has increased in this third edition.
