Search

Die Anonymisierung von sensiblen Individualdaten führt zu einem Konflikt zwischen dem Ziel der Minimierung des Reidentifikationsrisikos und der Qualität ökonometrischer Schätzungen. Der durch Anonymisierung bedingte Verlust an Effizienz und/oder der Konsistenz eines Schätzers wirft die grundsätzliche Frage auf, inwieweit anonymisierte Individualdaten überhaupt für die wissenschaftliche Nutzung geeignet sind.Deshalb gehen wir in dieser Arbeit der Frage nach, welchen Einfluss Anonymisierungsverfahren auf die Eigenschaften von ökonometrischen Schätzern haben. Zunächst untersuchen wir die Auswirkungen gängiger Anonymisierungsverfahren auf lineare ökonometrische Schätzer in endlichen Stichproben. Im zweiten Schritt untersuchen wir, inwieweit sich die Selektionseffekte durch Anonymisierung aufgrund von Data Blanking mit Hilfe von semiparametrischen Verfahren korrigieren lassen. Die quantitative Evidenz beruht auf Monte-Carlo-Simulationen und einer illustrativen Anwendung für einen Querschnitt der Kostenstrukturerhebung.

In this paper we develop a dynamic model for integer counts to capture the dis- creteness of price changes for financial transaction prices. Our model rests on an autoregressive multinomial component for the direction of the price change and a dynamic count data component for the size of the price changes. Since the model is capable of capturing a wide range of discrete price movements it is particularly suited for financial markets where the trading intensity is moderate or low as for most European exchanges. We present the model at work by applying it to transaction data of the Henkel share traded at the Frankfurt stock exchange over a period of 6 months. In particular, we use the model to test some theoretical implications of the market microstructure theory on the relationship between price movements and other marks of the trading process.

This paper presents structural estimates for a bargaining model which neststhe right-to-manage, the efficient wage bargaining, the seniority and the standard neoclassical labor demand model as special cases. In contrast to most existing models, ourapproach accounts for heterogeneous skill groups which differ in terms of productivityand representation in the bargaining process through union preferences. The paper introduces the concept of 'virtual' firms which allows us to (i) test the efficient contract model against models implying that firms operate on the labor demand curve and to (i) overcome a potential misspecification of firms' output markets.Estimates of structural parameters are obtained from a novel cross-section of German firms of the business related service sector which includes information on skill-specific wage rates at the firm level. Central results of this paper are that unions do care about both wages and employment in the bargaining process and that firms operate on thecontract curve. The bargaining power of unions in East Germany turns out to be muchweaker than in West Germany.

This paper analyzes the interday stability of the price process using transaction data. While the vast majority of empirical studies on the microstructure of financial markets rests on the tacit assumption that observed prices are generated by a time-invariant price process, we question this assumption by means of a minimum distance estimation framework. Starting from estimates specific for each day's price process, this procedure enables us to work out a common structure across trading days and allows us to disentangle the pecularities of trading days which are marked by certain news events. The determinants of transaction price changes for the BUND future trading at the LIFFE on the basis of 22 subsequent trading days are analyzed. Our empirical findings confirm that trading days do share a common structure to a large extent. However, single event dominated days are likely to show a differing price process. On the one hand, this fact renders pooled parameter estimates inconsistent. On the other hand, this procedure opens an avenue for an in depth analysis of information processing in financial markets.

This paper deals with the labor market entrance of young people in the Federal Republic of Germany. The main focus is on failures during this stage. First, an overview of the youth labor market in Germany is given. Then, the transition from vocational training to work is analyzed: The duration of the first spell of non-employment after completition of formal vocational training is analyzed by means of a proportional hazard function approach. Besides the strong influence of the human capital variables there is a striking effect of the family background of the youths. The following section addresses as to what extent early failures in the work history have long-lasting effects on future incomes.