Online network monitoring

Statistical Methods & Applications - An important problem in network analysis is the online detection of anomalous behaviour. In this paper, we introduce a network surveillance method bringing...     

Piecewise linear approximation of empirical distributions under a Wasserstein distance constraint

Big data applications and Monte Carlo simulation results can nowadays easily contain data sets in the size of millions of entries. We consider the situation when the information on a large univariate data set or sample needs to be preserved, stored or transferred. We suggest an algorithm to approximate a univariate empirical distribution through a piecewise linear distribution which requires significantly less memory to store. The approximation is chosen in a computationally efficient manner, such that it preserves the mean, and its Wasserstein distance to the empirical distribution is sufficiently small.     

Control charts for multivariate spatial autoregressive models

This paper deals with spatial detection of changes in model parameters of spatial autoregressive processes. The respective sequential testing problems are formulated. Moreover, we introduce characteristic quantities to monitor means or covariances of multivariate spatial autoregressive processes. Additionally, we also take into account the simultaneous surveillance of the mean vector and the covariance matrix. The aim is to apply control charts, important tools of sequential analysis, to these quantities. The considered control procedures are based on either cumulative sums or exponential smoothing. Further, we illustrate the methodology of statistical process control studying the spectrum of additive colors in a satellite photograph. Via simulation studies, the proposed control procedures are calibrated for a predefined average run length. In addition, we compare the performance of the control procedures considering the out-of-control situation. Eventually, the control charts are applied, and the signals of the different schemes are visualized. The final results are critically discussed.     

Evidenztriangulation in der Gesundheitsforschung

The contribution starts with weaknesses of a strict quantitative methodology in social research. Especially in health research variable connections are so complex that a broader understanding of research methods seems to be necessary. The dominance of quantitative-experimental ongoing in the sense of randomized controlled trials (RCT) at the top of the evidence hierarchy is criticized and a concept of evidence triangulation in the sense of mixed methods is proposed as alternative. An example study shows the logic of this research design. An institution of drug addicts counseling and therapy is analyzed in its effects through an evaluation study, using four different methodological approaches, an experimental pre-post design, qualitative interviews with the clients, and qualitative and document analysis using qualitative content analysis are combined. Each of them is developed in criticizing and supplementing the other approaches. The mixed methods procedure therefor follows a dialectical theory of science.     

Direct and Indirect Effects of Individualism and Institutions on Homicides

Social Indicators Research - The present paper evaluates whether people in highly individualistic cultures have a lower propensity to commit homicides, using data from 70 countries. Several...     

The impact of investor sentiment on the German stock market

This paper develops a broad-based sentiment indicator for Germany and investigates whether investor sentiment can explain stock returns on the German stock market. Based on a principal component analysis, we construct a sentiment indicator that condenses information of several well-known sentiment proxies. We show that this indicator explains the return spread between sentiment sensitive stocks and stocks that are not sensitive to sentiment fluctuations. Specifically, stocks that are difficult to arbitrage and hard to value are sensitive to the indicator. However, we do not find much predictive power of sentiment for future stock returns.