A mixture of beta–Dirichlet processes prior for Bayesian analysis of event history data

In this paper, we propose a mixture of beta–Dirichlet processes as a nonparametric prior for the cumulative intensity functions of a Markov process. This family of priors is a natural extension of a mixture of Dirichlet processes or a mixture of beta processes which are devised to compromise advantages of parametric and nonparametric approaches. They give most of their prior mass to the small neighborhood of a specific parametric model. We show that a mixture of beta–Dirichlet processes prior is conjugate with Markov processes. Formulas for computing the posterior distribution are derived. Finally, results of analyzing credit history data are given.     

Photographs of disasters. An ethnomethodological approach

The essay analyses the photographs produced and circulated during the March 2011 tsunami and earthquake disaster in Japan, which show destroyed buildings, flooded landscapes, desperate people. Disaster destroys existing order. On first sight, the photographs of disaster depict this dissolution of order. The empirical analysis shows that the disastrousness of disaster is (also) created through the pictures of the disasters. The paper discusses why and in what way certain pictures reveal themselves to be iconographic of disaster and how they enter the visual memory as its representative. To achieve this, the study will invoke ethnomethodology. At the centre of the analysis is the question of the particular means with which these images illustrate the destructive force of the disasters and how pictures showing destruction and pain (‘pictures of pain’) turn into pictures effecting pain in the viewer (‘painful pictures’). The empirical study demonstrates: the photographs show the destruction of order; however, they do this in an orderly manner.

for Jörg Bergmann’s 70th birthday     

Detecting mean increases in Poisson INAR(1) processes with EWMA control charts

Processes of serially dependent Poisson counts are commonly observed in real-world applications and can often be modeled by the first-order integer-valued autoregressive (INAR) model. For detecting positive shifts in the mean of a Poisson INAR(1) process, we propose the one-sided s exponentially weighted moving average (EWMA) control chart, which is based on a new type of rounding operation. The s-EWMA chart allows computing average run length (ARLs) exactly and efficiently with a Markov chain approach. Using an implementation of this procedure for ARL computation, the s-EWMA chart is easily designed, which is demonstrated with a real-data example. Based on an extensive study of ARLs, the out-of-control performance of the chart is analyzed and compared with that of a c chart and a one-sided cumulative sum (CUSUM) chart. We also investigate the robustness of the chart against departures from the assumed Poisson marginal distribution.     

What Works in Group Care? - A Structured Review of Treatment Models for Group Homes and Residential Care

This paper presents findings from a structured review of treatment models that are relevant to group care and residential treatment settings for children involved with the child welfare system. Initiated and guided by The California Evidence-Based Clearinghouse for Child Welfare, five treatment models — Positive Peer Culture, Teaching Family Model, Sanctuary Model, Stop-Gap Model, and Re-ED — were reviewed for effectiveness. In this paper, each model's treatment features are described and relevant outcome studies reviewed in terms of their effectiveness as well as relevance for child welfare practice. Findings indicate that four of the models are either supported or promising in terms of evidence for effectiveness. Implications for group care practice and research are discussed.     

Incentive effects and the income tax treatment of employer-provided workplace benefits

Employers often provide their employees with different kinds of benefits in the workplace to create comfortable working conditions. In order to avoid distortions of the wage-benefit ratio in employee compensation, economic theory suggests that fringe benefits should be subject to income taxation at a value placed on them by employees. This article shows that this approach does not apply to workplace benefits. Since the goal of these benefits is to reduce the employees’ disutility from work, treating them simply as wage substitutes disregards their incentive effects. Therefore, the rules for taxing workplace benefits are derived from an agency model. It is shown that in contrast to the standard economic approach, cost can be a more efficient tax base than willingness to pay, even though this results in higher tax payments. Moreover, with non-distortionary tax rates it is always better to tax the employer rather than the employee.     

Paul Lazarsfelds typologische Methode und die Grounded Theory. Generierung und Qualität von Typologien

The following article deals with the connections between the typological method proposed by Paul Lazarsfeld and the Grounded Theory. The question how good typologies in qualitative social research can be constructed will be raised. It will be argued that formal criteria are necessary but not sufficient in judging whether a typology is good. The typology also needs to be relevant in its contents. The article will show that the Grounded Theory can help to solve this problem by creating attributes for typology construction analogous to the Grounded Theory's process that is used to generate theory. On the other hand, Lazarsfeld's concept of “attribute space” can be of assistance for the process of “theoretical sampling” proposed by the Grounded Theory by providing a systematic scheme for selecting the cases to be studied. The article will conclude with an empirical example illustrating the issues mentioned above.