Panel data econometrics is one of the most exciting fields in econometrics to day. The possibility of modeling more realistic behavioral hypotheses and challenging methodological issues, together with the increasing availability of panel data have led to the phenomenal proliferation of studies on panel data. This edition is a substantial revision of the second edition. Two new chapters on modeling cross-sectionally dependent data and the dynamic system of equations have been added. Some of the more complicated concepts have been further streamlined and new material on correlated random-coefficients models, pseudo-panels, duration and count data models, quantile analysis, alternative approaches for controlling the impact of unobserved heterogeneity in nonlinear panel data models, inference with data having both large cross section and long time series, etc. have been incorporated into existing chapters. It is hoped that the present version can provide a reasonably comprehensive, coherent, and intuitive review of panel methodologies that are useful for empirical analysis. However, no single monograph can do justice to the huge amount of literature in this field. I apologize for any omissions of the important contributions in panel data analysis.

I would like to thank the former and current Cambridge University Press publisher, Scott Parris and Karen Maloney, for their encouragement and support for this project.