Contributions in Merlin

In this thesis a contrarian carry trade strategy, acting on the precedent spot return as a carry signal, is constructed and evaluated. The evaluation of the performance shows that the strategy is profitable in-sample, but not out-of-sample and exhibits statistical characteristics which are uncommon for the carry trade. I conduct a cross-sectional foreign exchange regression and find that the precedent spot return is a valid and statistically significant predictor of future excess returns. The compiled volatility indi- cators can be used as a carry signal which yields less profitable strategies. I find empirical evidence that portfolio returns regressed on the volatility indicators have small betas, are statistically significant while they lack explanatory power. Carry signal diversification improves the overall performance and the risk-adjusted returns of the contrarian carry trade strategy and closing out the carry exposure conditional on volatility indicators results in a greater or equal Sharpe ratio.

null

null

null

Contingent convertible (coco) bonds gained in importance with the increased regulatory capital requirements following the financial crisis. The Basel III framework allows banks to meet a certain degree of the capital requirements with coco bonds. These financial instruments have various design features which lead to a heterogeneous variability of instruments. In a first part, this thesis discusses the design features and examines the respective incentives they provide based on existing literature. A main characteristic of coco bonds is the loss absorption mechanism. This mechanism is activated, once a certain triggering threshold is breached. Depending on this loss absorption mechanism, the triggering event potentially leads to wealth-transfers between coco bond investors and shareholders. Thus, wealth may either transfer from coco bond investors to shareholders or vice versa or not at all. In an empirical investigation, this thesis finds that the majority of examined coco bonds would lead to a wealth-transfer from coco bond investors to shareholders. This finding implicates that moral hazard arises and coco bond issuers are incentivized to take more risk after a coco bond issuance. This thesis finds that the average coco bond issuer takes more risk than expected in the year after the coco bond issuance. This effect is stronger for the average issuer of a principal write-down coco bond compared to the average issuer of coco bonds with a mandatory conversion. However, this thesis finds no statistically significant relation between the coco bond’s estimated wealth-transfer and the abnormal risk the issuer takes.

We study the difference between the returns to the integrated approach to style investing and those to the mixed approach. Unlike the mixed approach, the integrated approach aggregates factor characteristics at security level. Recent literature finds that the integrated approach dominates the mixed approach. Using statistical tools for robust performance testing, we demystify these findings as a statistical fluke. We do not find any evidence favoring the integrated approach. What we do find is that the integrated approach exhibits a higher sensitivity to the low-risk anomaly. However, this reduction in risk does not lead to an improvement in performance.

Measurement invariance is a necessary precondition for meaningful cross-country comparisons, and three levels have been differentiated: configural, metric, and scalar. Unfortunately, establishing the most stringent form, i.e., scalar measurement invariance, across groups is difficult. Recently, Muthén and Asparouhov proposed testing for approximate rather than exact measurement invariance as this may be sufficient for meaningful comparisons. Following their strategy, the results of cross-country approximate measurement invariance tests of the PVQ-21 scale to measure values in the European Social Survey (ESS) are presented (N = 274,447 respondents from 15 countries participating in all six rounds). Applying the new approximate method for the test of measurement invariance allows both using more moderate constraints of approximate equality of parameters across groups and exploring the extent of noninvariance. Approximate measurement invariance was established in almost all rounds for two higher-order values: openness to change and self-enhancement. In the case of the two other higher-order values, self-transcendence and conservation, approximate measurement invariance was established across a subset of countries.

Cortical area parcellation is a challenging problem that is often approached by combining structural imaging (e.g., quantitative T1, diffusion-based connectivity) with functional imaging (e.g., task activations, topological mapping, resting state correlations). Diffusion MRI (dMRI) has been widely adopted to analyse white matter microstructure, but scarcely used to distinguish grey matter regions because of the reduced anisotropy there. Nevertheless, differences in the texture of the cortical 'fabric' have long been mapped by histologists to distinguish cortical areas. Reliable area-specific contrast in the dMRI signal has previously been demonstrated in selected occipital and sensorimotor areas. We expand upon these findings by testing several diffusion-based feature sets in a series of classification tasks. Using Human Connectome Project (HCP) 3T datasets and a supervised learning approach, we demonstrate that diffusion MRI is sensitive to architectonic differences between a large number of different cortical areas defined in the HCP parcellation. By employing a surface-based cortical imaging pipeline, which defines diffusion features relative to local cortical surface orientation, we show that we can differentiate areas from their neighbours with higher accuracy than when using only fractional anisotropy or mean diffusivity. The results suggest that grey matter diffusion may provide a new, independent source of information for dividing up the cortex.

This paper introduces a new method for deriving covariance matrix estimators that are decision-theoretically optimal within a class of nonlinear shrinkage estimators. The key is to employ large-dimensional asymptotics: the matrix dimension and the sample size go to infinity together, with their ratio converging to a finite, nonzero limit. As the main focus, we apply this method to Stein’s loss. Compared to the estimator of Stein (Estimation of a covariance matrix (1975); J. Math. Sci. 34 (1986) 1373–1403), ours has five theoretical advantages: (1) it asymptotically minimizes the loss itself, instead of an estimator of the expected loss; (2) it does not necessitate post-processing via an ad hoc algorithm (called “isotonization”) to restore the positivity or the ordering of the covariance matrix eigenvalues; (3) it does not ignore any terms in the function to be minimized; (4) it does not require normality; and (5) it is not limited to applications where the sample size exceeds the dimension. In addition to these theoretical advantages, our estimator also improves upon Stein’s estimator in terms of finite-sample performance, as evidenced via extensive Monte Carlo simulations. To further demonstrate the effectiveness of our method, we show that some previously suggested estimators of the covariance matrix and its inverse are decision-theoretically optimal in the large-dimensional asymptotic limit with respect to the Frobenius loss function.