Sufficiency of variables in discrete discriminant analysis

In discrete discriminant analysis the high dimensional estimation problem makes it necessary to restrict oneself to the most effective variables. Conditions are derived to determine whether subsets of variables yield the same optimal allocation rule as the original set. In the discrete case the conditions turn out to be sufficient but not necessary. Tests are derived in the framework of log-linear models. Based on the concept of adequate (α) discriminant sets two variable selection procedures are considered.     

Demontage oder Revitalisierung?

The controversial assessments of the German employment model in the literature are generally based on analyses focused on individual pillars of the model, such as the production system, or the welfare state. The present paper suggests an alternative view which takes into account the interactions between various elements of the employment model. We argue that, by the implementation of what we call a German variety of lean production, the competitiveness of the manufacturing industry has been boosted over the last few years. However, in contrast to earlier decades, the success of the export machine does not entail a more general employment dynamic. That is, the cranks between manufacturing and the rest of the employment system has been damaged substantially. Most importantly, the state has reduced its anchor role for the whole of the employment model and the potentials for its revitalisation.     

International research master in metropolitan studies

Ohne Zusammenfassung

---

International research master in metropolitan studies

     

Shrinkage and variable selection by polytopes

Constrained estimators that enforce variable selection and grouping of highly correlated data have been shown to be successful in finding sparse representations and obtaining good performance in prediction. We consider polytopes as a general class of compact and convex constraint regions. Well-established procedures like LASSO (Tibshirani, 1996) or OSCAR (Bondell and Reich, 2008) are shown to be based on specific subclasses of polytopes. The general framework of polytopes can be used to investigate the geometric structure that underlies these procedures. Moreover, we propose a specifically designed class of polytopes that enforces variable selection and grouping. Simulation studies and an application illustrate the usefulness of the proposed method.     

Ergonomic risk assessment with DesignCheck to evaluate assembly work in different phases of the vehicle development process

Occupational hazards exist, if the design of the work situation is not in accordance with ergonomic design principles. At assembly lines ergonomics is applied to the design of work equipment and tasks and to work organisation. The ignoring of ergonomic principles in planning and design of assembly work leads to unfavourable working posture, action force and material handling. Disorders of the musculoskeletal system are of a common occurrence throughout Europe. Musculoskeletal disorders are a challenge against the background of disabled workers. The changes in a worker's capability have to be regarded in the conception of redesigned and new assembly lines. In this way ergonomics becomes progressively more important in planning and design of vehicles: The objective of ergonomic design in different stages of the vehicles development process is to achieve an optimal adaptation of the assembly work to workers. Hence the ergonomic screening tool "Design Check" (DC) was developed to identify ergonomic deficits in workplace layouts. The screening-tool is based on the current ergonomic state of the art in the design of physical work and relevant EU legal requirements. It was tested within a federal German research project at selected work stations at the assembly lines at Dr.-Ing. h.c. F. Porsche AG / Stuttgart. Meanwhile the application of the screening-tool DC is transferred in other parts of the Porsche AG, Stuttgart. It is also realized as an ergonomic standard method to perform assembly work in different phases of the vehicle development process.     

The Labour Market for Women in the Old and New Länder of the Federal Republic of Germany

Abstract. As in the former FRG (Federal Republic of Germany), in the former GDR (German Democratic Republic) there was also sex-related segregation of, or within, occupations with less opportunities for development, less income, poorer working conditions and restricted opportunities for advancement for women. The transition from a centrally planned economy in the former GDR to a “social market economy” is still accompanied by reports of a dramatic rise in the unemployed and those working short-time. It is becoming clear that women are affected by unemployment to a greater extent than men in the new German Lander, and that the chances for women in the labour market are likely to deteriorate rapidly.     

Do Simulated Gambling Activities Predict Gambling with Real Money During Adolescence? Empirical Findings from a Longitudinal Study

As technology has developed, the international gambling market has changed markedly in recent years. The supply of internet-based gambling opportunities has become ever more significant. At the same time, the introduction of new gambling opportunities always brings a demand for evidence-based scientific evaluation, with regard to the associated risks of addiction. Simulated internet gambling, which is the focus of this study, represents a relatively new product group located at the interface between gambling and computer gaming. Concerns have been raised in scientific literature, especially with regard to the adolescent age group, as to whether participation in simulated internet gambling directly promotes recruitment to the world of monetary gambling, as defined in the gateway hypothesis. The research design was based on a standardized, representative longitudinal survey (over a 1-year period) with a total of 1178 school pupils from Northern Germany (M = 13.6 years; 47.5% male). It must be borne in mind that 12% of the adolescents belonged to the subgroup of “onset gamblers” and first reported experience with monetary gambling at the second stage of surveying. Logistic regression analysis demonstrates that this migration process is fostered by (1) participation from home in simulated gambling on social networks and (2) significant exposure to advertising (relating to both simulated and monetary gambling). Within the subgroup of simulated internet gamblers, variables such as particular patterns of use (including breadth and depth of involvement with simulated internet gambling, certain motives for participation, and microtransactions) do not serve as significant predictors. Despite this, important needs for action for the purposes of prevention and research can be identified.