Suchergebnisse

Based on a course in the theory of statistics this text concentrates on what can be achieved using the likelihood/Fisherian method of taking account of uncertainty when studying a statistical problem. It takes the concept ot the likelihood as providing the best methods for unifying the demands of statistical modelling and the theory of inference. Every likelihood concept is illustrated by realistic examples, which are not compromised by computational problems. Examples range from asimile comparison of two accident rates, to complex studies that require generalised linear or semiparametric mode

This paper tries to apply common methods to estimate unbiased coefficients for the return to schooling in Germany for the year 2004. Based on the simple Mincer-type wage equation, the return to schooling is around 9.5% per year. There is no sheepskin effect. As expected the return in the private sector is higher than in the public sector. Females have a higher return than males, but there are no differences between East and West Germans. An Instrumental Variables and a 3-Stage-Least-Squares approach give very high returns. For correcting the sample selection, the Heckman Two Step Procedure and the Heckman Maximum Likelihood Approach are used. For both methods, the coefficients are very similar, but higher than without correcting for it.

Dynamic nonlinear panel models are estimated on the first 14 waves (waves A to N) of the German Socio-Economic Panel to test (among other things) for state dependence effects in male unemployment behaviour. Estimation of the models is based on the maximum likelihood approach. The best model turns out to be the dynamic probit model with equi-correlated disturbances where an individual"s unemployment probability at a given point in time depends on his labour force status in the previous period and which controlls for unobserved population heterogeneity. This model shows that there are strong and significant state dependence effects in individual unemployment as well as significant unobserved heterogeneity of the disturbances. This means, reducing unemployment today will have positive long-term effects on the labour market in the future

This volume focuses on econometric models that confront estimation and inference issues occurring when sample data exhibit spatial or spatiotemporal dependence. This can arise when decisions or transactions of economic agents are related to the behaviour of nearby agents. Dependence of one observation on neighbouring observations violates the typical assumption of independence made in regression analysis. Contributions to this volume by leading experts in the field of spatial econometrics provide details regarding estimation and inference based on a variety of econometric methods including, maximum likelihood, Bayesian and hierarchical Bayes, instrumental variables, generalized method of moments, maximum entropy, non-parametric and spatiotemporal. An overview of spatial econometric models and methods is provided that places contributions to this volume in the context of existing literature. New methods for estimation and inference are introduced in this volume and Monte Carlo comparisons of existing methods are described. In addition to topics involving estimation and inference, approaches to model comparison and selection are set forth along with new tests for spatial dependence and functional form. These methods are applied to a variety of economic problems including: hedonic real estate pricing, agricultural harvests and disaster payments, voting behaviour, identification of edge cities, and regional labour markets. The volume is supported by a web site containing data sets and software to implement many of the methods described by contributors to this volume

This book has grown out of half a century of experience of teaching undergraduate econometrics at the Econometric Institute in Rotterdam. It combines a solid exposition of econometric methods with the application-oriented approach that is characteristic of the Rotterdam tradition in econometrics. Covering basic econometric methods (statistics, simple and multiple regression, nonlinear regression, maximum likelihood, generalized method of moments), this books explains their practical applications in modern business and economics and provides examples of these. Much attention is paid to the creative process of model building, with due attention for diagnostic testing and model improvement. The last part of the book is devoted to two major application areas: the econometrics of choice data (logit and probit, multinomial and ordered choice, truncated and censored data, duration data) and the econometrics of time series data (univariate time series, trends, volatility, vector autoregressions, and a brief discussion of SUR models, panel data, and simultaneous equations). In addition, data sets and (for instructors) full solutions of all exercises are available to readers. The book provides a thorough training in modern applications of econometrics to practical questions in business and economics. It is guided by a spirit of practical learning, and provides a wealth of examples and practical exercises based on a wide variety of data sets drawn from business and micro, macro, and international economics. The book will be suitable for introductory applied econometrics courses at undergraduate level up to more advanced courses at the graduate level.