Refine
Year of publication
Document Type
- Working Paper (12)
- Report (3)
Has Fulltext
- yes (15)
Is part of the Bibliography
- no (15)
Keywords
- Börsenkurs (4)
- asset pricing (4)
- Schätzung (3)
- Bias (2)
- Deutschland (2)
- Exponential smoothing (2)
- Schätzfunktion (2)
- Schätztheorie (2)
- Zeitreihenanalyse (2)
- indirect inference estimation (2)
This paper studies the market quality of an internalization system which is designed as part of an open limit order book (the Xetra system operated by Deutsche Börse AG). The internalization sys-tem (Xetra BEST) guarantees a price improvement over the inside spread in the Xetra order book. We develop a structural model of this unique dual market environment and show that, while adverse selection costs of internalized trades are significantly lower than those of regular order book trades, the realized spreads (the revenue earned by the suppliers of liquidity) is significantly larger. The cost savings of the internalizer are larger than the mandatory price improvement. This suggests that internalization can be profitable both for the customer and the internalizer. JEL Classification: G10
This paper provides an empirical assessment of hypotheses that identify causes of demand side constraints of individual labour supply. In a comparative study for the USA and the FRG we focus on analysing the effect of productivity gaps (industry wage growth beyond productivity growth), industry investment intensity and regional labour market conditions on individual employment probabilities. Furthermore, we investigate whether demand side constraints of labour supply can be caused by a spill over from commodity markets. Efficiency wage theory and the theory of inter-industry wage differentials are utilised to derive identifying restrictions that are applicable to the labour supply models for both countries. The econometric contribution of the paper is the derivation and application of a two step estimation method for the class of simultaneous random effects double hurdle models, of which the labour supply model employed in this paper is a special case. To provide the empirical basis for the comparative study, the Panel Study of Income Dynamics and the German Socio-Economic Panel are linked to the OECD’s International Sectoral Database. JEL classification: C33, C34, J64, O57
Modelling consumer behaviour in a profile design using a three equation generalised Tobit model
(1997)
We propose the application of a three equation generalised Tobit to model different aspects of consumer behaviour in a full profile study design. The model takes into account that consumer behaviour can be measured by preference scores, purchase probability and purchase volume. We aim to avoid the drawbacks of traditional conjoint analysis where the latter two aspects are disregarded. Starting from a full profile design, we develop the appropriate questionnaire layout, the econometric model, the likelihood function and tests. The model is applied in a market entry study for an innovative medicament after a reform of Germany´s public health system in 1993-1994. JEL Classification: C35,M31,L65
Kursänderungen auf Aktienmärkten können informationsinduziert durch neu zu verarbeitende Informationen oder liquiditätsinduziert durch kurzfristige Angebots- bzw. Nachfrageüberhänge auftreten. Diese zwei so unterschiedlich verursachten Kursreaktionen sind in empirischen Untersuchungen nur schwer zu trennen. Das Modell von Easley, Kiefer, O’Hara und Paperman (1996) bietet eine theoretische Basis zur separaten Erfassung von liquiditätsorientiertem und informationsbasiertem Handel und eröffnet darüber hinaus auch einen Weg zur empirischen Quantifizierung dieser Größen.
In der vorliegenden Untersuchung nutzen wir diesen Ansatz zur Analyse des Handels deutscher Aktien über das Computerhandelssystem IBIS. Dabei zeigt sich, daß innerhalb der DAX-Werte Informationsereignisse bei den sehr stark gehandelten Aktien nicht häufiger als bei weniger oft gehandelten Werten auftreten. Die Unterschiede im Handelsvolumen sind auf unterschiedlich starke Handelsaktivität sowohl informierter als auch uninformierter Marktteilnehmer zurückzuführen. Weiterhin zeigt sich, daß das Risiko, mit informierten Marktteilnehmern zu handeln, bei den sehr umsatzstarken Aktien am geringsten ist.
In Einklang mit dem sogenannten Montagseffekt ist die Wahrscheinlichkeit für das Auftreten von negativen Informationsereignissen zu Wochenanfang besonders groß. Dieses Ergebnis könnte durch eine Tendenz von Managern erklärt werden, negative Informationen freitags nach Börsenschluß zu veröffentlichen. Eine getrennte Untersuchung für Handelstage mit niedriger und solche mit hoher Volatilität zeigt, daß an Handelstagen mit höherer Volatilität die Handelsintensität sowohl informierter als auch uninformierter Investoren größer ist. Auch die Wahrscheinlichkeit, an solchen Tagen mit besser informierten Marktteilnehmern zu handeln, steigt. Dieser Anstieg ist allerdings nicht statistisch signifikant.
The long-run consumption risk model provides a theoretically appealing explanation for prominent asset pricing puzzles, but its intricate structure presents a challenge for econometric analysis. This paper proposes a two-step indirect inference approach that disentangles the estimation of the model's macro-economic dynamics and the investor's preference parameters. A Monte Carlo study explores the feasibility and efficiency of the estimation strategy. We apply the method to recent U.S.\data and provide a critical re-assessment of the long-run risk model's ability to reconcile the real economy and financial markets. This two-step indirect inference approach is potentially useful for the econometric analysis of other prominent consumption-based asset pricing models that are equally difficult to estimate.
The long-run consumption risk model provides a theoretically appealing explanation for prominent asset pricing puzzles, but its intricate structure presents a challenge for econometric analysis. This paper proposes a two-step indirect inference approach that disentangles the estimation of the model's macroeconomic dynamics and the investor's preference parameters. A Monte Carlo study explores the feasibility and efficiency of the estimation strategy. We apply the method to recent U.S. data and provide a critical re-assessment of the long-run risk model's ability to reconcile the real economy and financial markets. This two-step indirect inference approach is potentially useful for the econometric analysis of other prominent consumption-based asset pricing models that are equally difficult to estimate.