By making both causal and process analyses possible, panel data has enjoyed increasing popularity in empirical science. In this compilation, several statistical techniques are presented in the face of a growing need to analyze panel data. Measurement error, missing data, heterogeneous populations and particular requirements for causal interference make the analysis of change more difficult. Readers will find up-to-date approaches covering a wide range of topics. Among these are loglinear and probit models, state space models, and structural equation and multilevel growth curve models of panel data.