Rainer Winkelmann

Ein dichterisches konzipiertes Werk mit doppelt dialogischem Aufbau: im u eren Dialog kehrt ein Missionsarzt im Ruhestand nach Simbabwe zur ck, um unter anderem einen alten Missionar zu besuchen, der aufgrund seiner Krankheit den Tod vor Augen sieht und unbedingt noch von einem merkw rdigen fr heren Erlebnis erz hlen m chte, bei dem er einem hochintelligenten Wissenschaftler begegnet, was den inneren Dialog ergibt. Als Theologiestudent war er nach einem Krankenbesuch unbewu t bis in den Keller des Hospital abgerutscht, wo er in der wissenschaftlichen Abteilung von einem gutaussehenden Herrn durch die R ume geleitet wird, in denen auch rein gedankliche Experimente oder Demonstrationen durchgef hrt werden, die psychische, gedankliche und den Glauben ber hrende und insgesamt richtungsweisende Elemente enthalten. Am Ende zeigt sich, dass der Leiter der Wissenschaft im Keller eine Person wie Mephisto war, die auch in der Heiligen Schrift bewandert ist und dadurch auch auf Konsequenzen f r die Menscheit verweisen kann.

The “count data” ?eld has further ?ourished since the previous edition of this book was published in 2003. The development of new methods has not slowed down by any means, and the application of existing ones in applied work has expanded in many areas of social science research. This, in itself, would be reason enough for updating the material in this book, to ensure that it continues to provide a fair representation of the current state of research. In addition, however, I have seized the opportunity to undertake some major changes to the organization of the book itself. The core material on cross-section models for count data is now presented in four chapters, rather than in two as previously. The ?rst of these four chapters introduces the Poissonregressionmodel,anditsestimationbymaximumlikelihoodorpseudo maximum likelihood. The second focuses on unobserved heterogeneity, the third on endogeneity and non-random sample selection. The fourth chapter provides an extended and uni?ed discussion of zeros in count data models. This topic deserves, in my view, special emphasis, as it relates to aspects of modeling and estimation that are speci?c to counts, as opposed to general exponential regression models for non-negative dependent variables. Count distributions put positive probability mass on single o- comes, and thus o?er a richer set of interesting inferences.

The availability of microdata has increased rapidly over the last decades, and standard statistical and econometric software packages for data analysis include ever more sophisticated modeling options. The goal of this book, now initssecondedition,istofamiliarizethereaderwithawiderangeofcommonly used models, and thereby to enable her/him to become a critical consumer of current empirical research, and to properly conduct own empirical analyses. The book can be used as a textbook for an advanced undergraduate, a Master’s or a ?rst-year Ph. D. course on the topic of microdata analysis. In economicsandrelateddisciplines,suchacourseistypicallyo?eredaftera?rst course on the linear regression model. Alternatively, the book can also serve as a supplementary text to applied ?eld courses, such as those dealing with empirical analyses in labor, health or education. Finally, it might provide a useful reference for graduate students, researchers and practitioners who encounter microdata in their work. The focus of the book is on regression-type models in the context of large cross-section samples where the dependent variable is qualitative or discrete, or where the sample is not randomly drawn from the population of interest, due to censoring or truncation of the dependent variable. While our ba- groundisineconomics,andweoccasionallyrefertoproblemsandapplications fromempiricaleconomics,themodelsdiscussedinthisbookshouldbeequally relevant wherever microdata are used, inside the social sciences, including for example quantitative political science and sociology, as well as outside.

The availability of microdata has increased rapidly over the last decades, and standard statistical and econometric software packages for data analysis include ever more sophisticated modeling options. The goal of this book, now initssecondedition,istofamiliarizethereaderwithawiderangeofcommonly used models, and thereby to enable her/him to become a critical consumer of current empirical research, and to properly conduct own empirical analyses. The book can be used as a textbook for an advanced undergraduate, a Master’s or a ?rst-year Ph. D. course on the topic of microdata analysis. In economicsandrelateddisciplines,suchacourseistypicallyo?eredaftera?rst course on the linear regression model. Alternatively, the book can also serve as a supplementary text to applied ?eld courses, such as those dealing with empirical analyses in labor, health or education. Finally, it might provide a useful reference for graduate students, researchers and practitioners who encounter microdata in their work. The focus of the book is on regression-type models in the context of large cross-section samples where the dependent variable is qualitative or discrete, or where the sample is not randomly drawn from the population of interest, due to censoring or truncation of the dependent variable. While our ba- groundisineconomics,andweoccasionallyrefertoproblemsandapplications fromempiricaleconomics,themodelsdiscussedinthisbookshouldbeequally relevant wherever microdata are used, inside the social sciences, including for example quantitative political science and sociology, as well as outside.

The “count data” ?eld has further ?ourished since the previous edition of this book was published in 2003. The development of new methods has not slowed down by any means, and the application of existing ones in applied work has expanded in many areas of social science research. This, in itself, would be reason enough for updating the material in this book, to ensure that it continues to provide a fair representation of the current state of research. In addition, however, I have seized the opportunity to undertake some major changes to the organization of the book itself. The core material on cross-section models for count data is now presented in four chapters, rather than in two as previously. The ?rst of these four chapters introduces the Poissonregressionmodel,anditsestimationbymaximumlikelihoodorpseudo maximum likelihood. The second focuses on unobserved heterogeneity, the third on endogeneity and non-random sample selection. The fourth chapter provides an extended and uni?ed discussion of zeros in count data models. This topic deserves, in my view, special emphasis, as it relates to aspects of modeling and estimation that are speci?c to counts, as opposed to general exponential regression models for non-negative dependent variables. Count distributions put positive probability mass on single o- comes, and thus o?er a richer set of interesting inferences.