Papers by Winfried Pohlmeier
RePEc: Research Papers in Economics, Mar 28, 2007
In this paper we develop a model for the conditional inflated multivariate density of integer cou... more In this paper we develop a model for the conditional inflated multivariate density of integer count variables with domain Z n. Our modelling framework is based on a copula approach and can be used for a broad set of applications where the primary characteristics of the data are: (i) discrete domain, (ii) the tendency to cluster at certain outcome values and (iii) contemporaneous dependence. These kind of properties can be found for high or ultra-high frequent data describing the trading process on financial markets. We present a straightforward method of sampling from such an inflated multivariate density through the application of an Independence Metropolis-Hastings sampling algorithm. We demonstrate the power of our approach by modelling the conditional bivariate density of bid and ask quote changes in a high frequency setup. We show how to derive the implied conditional discrete density of the bid-ask spread, taking quote clusterings (at multiples of 5 ticks) into account.
Ethology, Jan 11, 2021
Zöller et al. (2020) somewhat misinterpret the goal of our paper (Wikelski et al., 2020), which n... more Zöller et al. (2020) somewhat misinterpret the goal of our paper (Wikelski et al., 2020), which neither tries to perform earthquake predictions nor does it claim that the current quality of measurements is sufficient to perform earthquake predictions. The reason for the poor prediction quality found by Zöller et al. can be manifold. Firstly, as stated above, the data are insufficient for a prediction exercise. The predictor variable, that is, the animal anomalies, contains a vast majority of events that are not earthquake related. This includes high activity during milking times, disturbances due to other farming activities, and the impact of the regional/local weather and its immediate manifestations. There is also obvious room for improvement in terms of the number of farms and the
Journal of contextual economics, Feb 1, 1992
In diesem Beitrag stellen wir ein MIMIC-Modell der Gesundheitszustandsmessung für die Bundesrepub... more In diesem Beitrag stellen wir ein MIMIC-Modell der Gesundheitszustandsmessung für die Bundesrepublik Deutschland vor. Die spezielle Formulierung des Modells erlaubt die Berechnung eines Gesundheitsindexes ohne Berücksichtigung schwer zugänglicher Variablen wie Umwelt-oder Arbeitsplatzqualität und die Überprüfung der Erklärungsgüte des Modells bei begrenzter Information auf der Basis weniger Proxy-Variablen. * Hilfreiche Kommentare und Anregungen stammen von Erbsland, M.; Laisney, F.; Ried, W.; Ronning, G. und Wille, E., denen wir an dieser Stelle herzlich danken möchten. Dieser Aufsatz entstand, während sich der erste Autor als John F. Kennedy-Fellow an der Harvard-Universität aufhielt. Eine frühere Version präsentierten wir auf dem Second World Congress on Health Economics in Zürich.
Jahrbucher Fur Nationalokonomie Und Statistik, Feb 1, 2011
This paper reinterprets Maganelli's (2009) idea of "Forecasting with Judg ment" to obtain a dynam... more This paper reinterprets Maganelli's (2009) idea of "Forecasting with Judg ment" to obtain a dynamic algorithm for combining survey data and time series models for macroeconomic forecasting. Unlike existing combination ap proaches which typically assign weights to alternative forecasts, the algorithm uses survey forecasts in estimating the parameter vector of a time series model. The methodology is applied to mid-term forecasts of the three-month Euribor.
De Gruyter eBooks, Dec 31, 2006
This paper surveys the empirical evidence on causal effects of education on earnings for Germany ... more This paper surveys the empirical evidence on causal effects of education on earnings for Germany and compares alternative studies in the light of their underlying identifying assumptions. We work out the different assumptions taken by various studies, which lead to rather different interpretations of the estimated causal effect. In particular, we are interested in the question to what extend causal return estimates are informative regarding educational policy advice. Despite the substantial methodological differences, we have to conclude that the empirical findings for Germany are quite robust and do not deviate substantially from each other. This also holds for the few studies which rely on ignorability conditions, regardless of whether they use educational attainment as a continuous treatment variable or as a discrete treatment indicator. Own estimates based on the matching approach indicate that the selection into upper secondary schooling is suboptimal.
Social Science Research Network, 2016
We propose a novel regression approach for optimizing portfolios by means of Bayesian regularizat... more We propose a novel regression approach for optimizing portfolios by means of Bayesian regularization techniques. In particular, we represent the weight deviations of the global minimum variance portfolio from a reference portfolio (e.g. the naive 1/N portfolio) as coefficients of a linear regression and shrink them towards zero through Bayesian shrinkage priors. By doing so, we aim to robustify the portfolios against estimation risk. Modeling the optimal portfolio weights through Bayesian priors avoids estimating the moments of the asset return distribution and substantially reduces the dimensionality of the estimation problem. We compare the proposed Bayesian shrinkage strategies to popular frequentist approaches and find that the former show better out-of-sample performance based on various performance criteria. They also turn out to be particularly attractive for high-dimensional portfolios.
Ethology, Jul 3, 2020
This is an open access article under the terms of the Creative Commons Attribution-NonCommercial ... more This is an open access article under the terms of the Creative Commons Attribution-NonCommercial License, which permits use, distribution and reproduction in any medium, provided the original work is properly cited and is not used for commercial purposes.
RePEc: Research Papers in Economics, Jun 1, 2015
We propose to apply –norm regularization to address the problem of weak and/or many instruments... more We propose to apply –norm regularization to address the problem of weak and/or many instruments. We observe that the presence of weak instruments, or weak and many instruments is translated into a nearly singular problem in a control function representation. Hence, we show that mean squares error-optimal -norm regularization with a small sample size reduces the bias and variance of the regularized 2SLS estimators with the presence of weak and/or many instruments. A number of different strategies for choosing a regularization parameter are introduced and compared in a Monte Carlo study.
RePEc: Research Papers in Economics, 2018
We propose a novel estimation approach for the covariance matrix based on the l 1-regularized app... more We propose a novel estimation approach for the covariance matrix based on the l 1-regularized approximate factor model. Our sparse approximate factor (SAF) covariance estimator allows for the existence of weak factors and hence relaxes the pervasiveness assumption generally adopted for the standard approximate factor model. We prove consistency of the covariance matrix estimator under the Frobenius norm as well as the consistency of the factor loadings and the factors. Our Monte Carlo simulations reveal that the SAF covariance estimator has superior properties in finite samples for low and high dimensions and different designs of the covariance matrix. Moreover, in an out-of-sample portfolio forecasting application the estimator uniformly outperforms alternative portfolio strategies based on alternative covariance estimation approaches and modeling strategies including the 1/N-strategy.
This paper focuses on the role personality traits play in determining individual unemployment dur... more This paper focuses on the role personality traits play in determining individual unemployment duration. We argue that a worker's job search intensity is decisively driven by her personality traits, reflected in her propensity to motivate and control herself while searching for a job. Moreover, personality traits, in as far as they can be signaled to a potential employer, may also enhance the probability of receiving and accepting a job offer. For our econometric duration analysis, we use the well-accepted taxonomy "Big Five" to classify personality traits. Based on individual unemployment data taken from the German Socio-Economic Panel (SOEP) our empirical findings reveal that the personality traits Conscientiousness and Neuroticism have a strong impact on the instantaneous probability of finding a job, where the former has a positive effect and the latter has a negative effect. The direction of the effect on the subsequent employment duration is the opposite. We do not find any significant effects of the personality traits Extraversion and Agreeableness on the duration of unemployment. The personality trait Openness eases finding a job only for female unemployed workers and workers with migration background
Journal of Institutional and Theoretical Economics-zeitschrift Fur Die Gesamte Staatswissenschaft, 1989
Journal of Business & Economic Statistics, Oct 3, 2022
Index investing has an advantage over active investment strategies, because less frequent trades ... more Index investing has an advantage over active investment strategies, because less frequent trades results in lower expenses, yielding higher long-term returns. Index tracking is a popular investment strategy that attempts to find a portfolio replicating the performance of a collection of investment vehicles. This paper considers index tracking from the perspective of solution space exploration. Three search space heuristics in combination with three portfolio tracking error methods are compared in order to select a tracking portfolio with returns that mimic a benchmark index. Experimental results conducted on real-world datasets show that Widening, a metaheuristic using diverse parallel search paths, finds superior solutions than those found by the reference heuristics. Presented here are the first results using Widening on time-series data.
Uploads
Papers by Winfried Pohlmeier