The univariate collapsing method (UCM) for portfolio optimization is based on obtaining the predictive mean and a risk measure such as variance or expected shortfall of the univariate pseudo-return series generated from a given set of portfolio weights and multivariate set of assets under interest and, via simulation or optimization, repeating this process until the desired portfolio weight vector is obtained. The UCM is well-known conceptually, straightforward to implement, and possesses several advantages over use of multivariate models, but, among other things, has been criticized for being too slow. As such, it does not play prominently in asset allocation and receives little attention in the academic literature. This paper proposes use of fast model estimation methods combined with new heuristics for sampling, based on easily-determined characteristics of the data, to accelerate and optimize the simulation search. An extensive empirical analysis confirms the viability of the method.
What is the added value of a security which qualifies as a “high-quality liquid asset” (HQLA) under the Basel III “Liquidity Coverage Ratio” (LCR)? In this paper, we quantify the added value in terms of yield changes and, as suggested by Stein (2013), call it “HQLA premium”. To do so, we exploit the introduction of the LCR in Switzerland as a unique quasi-natural experiment and we find evidence for the existence of an HQLA premium in the order of 4 basis points. Guided by theoretical considerations, we claim that the HQLA premium is state dependent and argue that our estimate is a lower bound measure. Furthermore, we discuss the implications of an economically significant HQLA premium. Thereby, we contribute to a better understanding of the LCR and its implications for financial markets.
An artificial neural network (ANN) algorithm is proposed that incorporates both market segmentation and discriminant (regression) analysis of the segments. The method simultaneously estimates the models relating consumer characteristics to market segments, i.e., subjects are assigned to (unique) segments so that subjects within a class show similar purchase behavior and share the same characteristics (psychographics/sociodemographics). Parameters of all models are estimated by the backpropagation algorithm. The performance of the ANN methodology is assessed in a Monte-Carlo study. In contrast to the usual stepwise approach adopted in segmentation studies, our study found that simultaneous segmentation and discrimination are preferable for finding an overall optimum in that this way clusters are formed not only to create homogeneous submarkets but also to show a good dicriminatory behavior.
Two neural network approaches, Kohonen's Self-Organizing (Feature) Map (SOM) and the Topology Representing Network (TRN) of Martinetz and Schulten are employed in the context of competitive market structuring and segmentation analysis. In an empirical study using brands preferences derived from household panel data, we compare the SOM and TRN approach to MULTICLUS, a parametric approach which also simultaneously solves the market structuring and segmentation problem. Our empirical analysis shows several benefits and shortcomings of the three methodologies under investigation, MULTICLUS, SOM, and TRN. As compared to MULTICLUS, we find that the non-parametric neural network approaches show a higher robustness against any kind of data preprocessing and a higher stability of partitioning results. As compared to SOM, we find advantages of TRN which uses a more flexible concept of adjacency structure. In TRN, no rigid grid of units must be specified. A further advantage of TRN lies in the possibility to exploit the information of the neighborhood graph which supports ex-post decisions about the segment configuration at both the micro and the macro level. However, SOM and TRN also have some drawbacks as compared to MULTICLUS. The network approaches are, for instance, not accessible to inferential statistics. Our empirical study indicates that especially TRN may represent a useful expansion of the marketing analysts tool box.
You are warmly invited to the inaugural lecture of Prof. Pietro Biroli: "Genetics and Economics". In his presentation, he will discuss how recent tools and discoveries from molecular genetics can improve our understanding of health and economic inequality, and suggest how nature and nurture interact in the complex process of human capital formation.
Health economists have studied the determinants of the expected value of health status as a function of medical and nonmedical inputs, often finding small marginal effects of the former. This paper argues that both types of input have an additional benefit, viz. a reduced variability of health status. Using OECD health data for 24 countries between 1960 and 2004, medical and nonmedical inputs are found to reduce the variability of life expectancy. While the evidence supports the "flat-of-the-curve medicine" hypothesis with respect to the expected value of life expectancy and its variability, healthcare expenditure is comparatively effective in reducing variability.
Assuming the classic contingent claim setting, a number of financial asset demand tests of Expected Utility have been developed and implemented in experimental settings. However the domain of preferences of these asset demand tests differ from the mixture space of distributions assumed in the traditional binary lottery laboratory tests of von Neumann-Morgenstern Expected Utility preferences. We derive new sets axioms that are necessary and sufficient for preferences over contingent claims to be representable by an Expected Utility function. We also indicate the additional axioms required to extend the representation to the more general case of preferences over risky prospects.
We show that in a consumption-based asset-pricing model with hyperbolic discounting leading to dynamically inconsistent time preferences value premium increases nonlinearly with the degree of discounting and thus affects cross section of returns. To test our model empirically, we relate the size of the value premium in 41 countries to the degree of hyperbolic discounting across those countries. The latter was found in an International Test of Risk Attitudes (INTRA). Our result is robust to the inclusion of other variables from INTRA, such as risk aversion, as well as micro- and macro-economic variables from the 41 countries.
Das deutsche Wirtschaftsmagazin Capital kürt jedes Jahr die "Top 40 unter 40" aus Wirtschaft, Politik, Wissenschaft und öffentlichem Dienst. Als einzige Universität hat die UZH zwei Top-Talente im Ranking: Sven Seuken vom Institut für Informatik und Florian Scheuer vom Institut für Volkswirtschaftslehre.
