This volume collects seven of Marc Nerlove's previously published, classic essays on panel data econometrics written over the past thirty-five years, together with a cogent essay on the history of the subject, which began with George Biddell Airey's monograph published in 1861. Since Professor Nerlove's 1966 Econometrica paper with Pietro Balestra, panel data and methods of econometric analysis appropriate to such data have become increasingly important in the discipline. The principal factors in the research environment affecting the future course of panel data econometrics are the phenomenal growth in the computational power available to the individual researcher at his or her desktop and the ready availability of data sets, both large and small, via the Internet. The best way to formulate statistical models for inference is motivated and shaped by substantive problems and understanding of the processes generating the data at hand to resolve them. The essays illustrate both the role of the substantive context in shaping appropriate methods of inference and the increasing importance of computer-intensive methods.
1. The history of panel data econometrics, 1861-1997; 2. Pooling cross-section and time-series data in the estimation of a dynamic model: the demand for natural gas (with Pietro Balestra); 3. Experimental evidence on the estimation of dynamic economic relations from a time-series of cross-sections; 4. Further evidence on the estimation of dynamic economic relations from a time-series of cross-sections; 5. A note on error-components models; 6. Growth rate convergence, fact or artifact? An essay on panel data econometrics; 7. Properties of alternative estimators of dynamic panel models: an empirical analysis of cross-country data for the study of economic growth; 8. Likelihood inference for dynamic panel models.