Univ., Diplomarbeit--Duisburg, 2008.

Univ., Diss--Frankfurt

Frankfurt (Main), University, Thesis (doctoral), 2001.

In this thesis advanced regression methods are applied to discuss and investigate highly relevant research questions in the areas of finance and economics. In the field of credit risk the thesis investigates a hierarchical model which allows to obtain a consensus score, if several ratings are available for each firm. Autoregressive processes and random effects are used to model both a correlation structure between and within the obligors in the sample. The model also allows to validate the raters themselves. The problem of model uncertainty and multicollinearity between the explanatory variables is addressed in the other two applications. Penalized regressions, like bridge regressions, are used to handle multicollinearity while model averaging techniques allow to account for model uncertainty. The second part of the thesis makes use of Bayesian elastic nets and Bayesian Model Averaging (BMA) techniques to discuss long-term economic growth. It identifies variables which are significantly related to long-term growth. Additionally, it illustrates the superiority of this approach in terms of predictive accuracy. Finally, the third part combines ridge regressions with BMA to identify macroeconomic variables which are significantly related to aggregated firm failure rates. The estimated results deliver important insights for e.g., stress-test scenarios. (author's abstract)

This dissertation encompasses four studies on selected topics in financial regulation and financial stability. The first paper asks whether there is empirical evidence of cyclicality in regulatory capital requirements prescribed by Basel regimes. This much debated issue was until then only addressed in theoretical papers, or simulation studies. While we do not find evidence on cyclicality in the Basel I or Basel II Standardized Approach, we find statistically and economically significant evidence concerning Basel II IRB portfolios. The second paper implements an agent based model to simulate an artificial asset market. This setup is then used to assess the impact of (i) a short selling ban, (ii) a Tobin Tax like transaction tax, (iii) mandatory Value-at-Risk limits and (iv) arbitrary combinations of these. I present results that show that while reducing volatility, a short selling ban nurtures market bubbles, and a Tobin Tax increases the variance of the returns. In this model a mandatory risk limit is beneficial from all stability perspectives taken. I examine the robustness of the model regarding its initial parameterization and show that high levels of a Tobin Tax lead to substantial market turbulence. The third paper considers the question which macroeconomic variables are linked to a time series of special interest from a financial stability perspective: firm defaults. Furthermore, we evaluate the empirical evidence of a hidden credit cycle by adding a latent factor to our models. We conclude that there is no empirical support of a hidden credit cycle in Austria once sufficient regressors are included and industry sectors differ in their respective macro drivers. The forth paper extends this work by implementing Bayesian Model Averaging (BMA) - a modern technique to counter model uncertainty. Furthermore we enrich this statistical approach by combining BMA with Bayesian ridge regression. We draw the conclusion that BMA is indeed a powerful tool to counter model uncertainty. Interest rates and components of inflation are distilled as major drivers for firm failures in Austria. (author's abstract)

Zugl.: Köln, Univ., Diss., 2005

Zugl.: Münster (Westfalen), Univ., Diss., 2006

Universiẗat, Diss., 2006--Münster.

Universiẗat, Diss.--Augsburg, 2007.

Thesis (doctoral)--University of St. Gallen, 2008.