A simplified estimation procedure based on the EM algorithm for the power series cure rate model

The family of power series cure rate models provides a flexible modeling framework for survival data of populations with a cure fraction. In this work, we present a simplified estimation procedure for the maximum likelihood (ML) approach. ML estimates are obtained via the expectation-maximization (EM) algorithm where the expectation step involves computation of the expected number of concurrent causes for each individual. It has the big advantage that the maximization step can be decomposed into separate maximizations of two lower-dimensional functions of the regression and survival distribution parameters, respectively. Two simulation studies are performed: the first to investigate the accuracy of the estimation procedure for different numbers of covariates and the second to compare our proposal with the direct maximization of the observed log-likelihood function. Finally, we illustrate the technique for parameter estimation on a dataset of survival times for patients with malignant melanoma.     

Work and mental disorders in a German national representative sample

Abstract

Most previous studies concerning the associations between work and mental ill-health have used dimensional self-report questionnaires for mental health problems (e.g., depressive symptoms). This study contributes to occupational health research by providing standardized clinical diagnoses based on DSM-IV criteria. A total of 2329 employees (age 18–65 years) took part in a structured, computer-assisted clinical interview (DIA-X/M-CIDI). Further, they specified whether their job was characterized by physical workload, overtime, or stress, and evaluated whether they feel impaired by each job characteristic. Results show that substance abuse/dependence (including nicotine dependence) was the highest prevalent mental disorder in German employees (12 month prevalence: 14.4%; only alcohol and illicit substance abuse/dependence: 4.9%) followed by anxiety (12.0%) somatoform (9.7%), and affective (9.3%) disorders. Sequential logistic regression analyses showed significant associations between the presence of stress at work and affective and somatoform disorders. Furthermore, feeling impaired by stress at work was strongly associated with anxiety, affective, somatoform disorders, and substance abuse/dependence. Beside work, personal characteristics, primarily gender, were associated with mental disorders in employees. However, except for affective disorders, gender did not modify the association between job characteristics and mental disorders. Taken together, results corroborate the necessity of considering mental disorders at work. Further studies to define the relation between work and mental disorders in employees are strongly recommended and should include objective analyses of job characteristics.     

Diversity training pitfalls and possibilities: An exploration of small and mid-size US organizations

Abstract

This qualitative, exploratory study examines the development and implementation of diversity training in small and mid-size organizations in a Midwestern region of the United States. The results are contrasted with diversity best practices and found lacking in key elements identified as most likely to yield success. Specifically, the organizations in this study did not provide training beyond awareness level, failed to conduct front-end needs assessment, provided little if any in-depth evaluation of diversity training and showed varying support for diversity endeavors from the leadership and through connecting diversity training with other systemic initiatives. The article concludes with recommendations for additional exploration of adapting effective diversity training practices to minimize pitfalls and maximize possibilities in small and mid-size systems.     

Gender, Financial Risk, and Probability Weights

Women are commonly stereotyped as more risk averse than men in financial decision making. In this paper we examine whether this stereotype reflects gender differences in actual risk-taking behavior by means of a laboratory experiment with monetary incentives. Gender differences in risk taking may be due to differences in valuations of outcomes or in probability weights. The results of our experiment indicate that value functions do not differ significantly between men and women. Men and women differ in their probability weighting schemes, however. In general, women tend to be less sensitive to probability changes. They also tend to underestimate large probabilities of gains more strongly than do men. This effect is particularly pronounced when the decisions are framed in investment terms. As a result, women appear to be more risk averse than men in specific circumstances.     

Ein Ansatz zur Förderung von Reflexionskompetenz: Fallarbeit in 7 Schritten

This article describes a didactical model for higher education purposes focusing on the development of theory driven and self driven ‘case reflection competence’. We (Telse Iwers-Stelljes and Renate Luca) have developed this procedure in the last 6 years and formative evaluated it in different investigations. Starting point of this project were the actual results on studies of antinomical conditions of professional teachers and students in the classroom environment and the intention to find a humanistic psychologically-oriented access to handle them. In the following, we are going to describe 1) the theoretical foundations of our researches to explain the context of our model, 2) its methodical implementation and 3) a case reconstruction based on an example reflected by one of our students.     

(Un)Verst?ndlichkeit des Steuerrechts und Nachfrage nach Steuerberatungsdienstleistungen: Ein Experiment

Although increasing the understandability of tax law is a popular postulation, the consequences for individual decisions and the distribution of the tax burdens are far from clear. For this reason, the effects on the demand for tax advice are analyzed in an experimental setting: the participants had to rank pension plans while the understandability of the tax system was modified. We show that an increasing understandability of tax law significantly decreases the willingness to pay for tax advice and that this relationship is moderated by the individuals?? level of education. In fact, in our experiment only individuals with a high education level benefit from the improved understandability of tax law.     

On the distribution of lrt for testing the equality of exponential distributions

In this paper, an asymptotic expansion of the distribution' of the likelihood ratio criterion for testing the equality of p one-parameter exponential distributions is obtained for unequal sample sizes. The expansion is obtained up to the order of n^-3 with the second term of the order of n^-2 so that the first term of this expansion alone should provide an excellent approximation to the distribution for moderately large values of n, where n is the combined sample size.     

Multivariate Stochastic Volatility Models: Bayesian Estimation and Model Comparison

In this paper we show that fully likelihood-based estimation and comparison of multivariate stochastic volatility (SV) models can be easily performed via a freely available Bayesian software called WinBUGS. Moreover, we introduce to the literature several new specifications that are natural extensions to certain existing models, one of which allows for time-varying correlation coefficients. Ideas are illustrated by fitting, to a bivariate time series data of weekly exchange rates, nine multivariate SV models, including the specifications with Granger causality in volatility, time-varying correlations, heavy-tailed error distributions, additive factor structure, and multiplicative factor structure. Empirical results suggest that the best specifications are those that allow for time-varying correlation coefficients.     

Secular Trends in Substance Use: The Conflict and Young People in Northern Ireland

The resolution of political conflict has led some to suggest that Northern Ireland will now face a range of social problems that have been ignored or suppressed by the Troubles. One such area is adolescent drug use. In this article, a review of a range of data sources shows that drug use, with few exceptions, has increased since the emergence of the ongoing peace process. Social and political changes and enhanced paramilitary involvement in the drugs trade appear to have somehow created an environment where drug use has flourished. In reviewing current drug policy and practice, the article highlights the lack of prevention, treatment, and harm reduction services established in Northern Ireland as a cause for concern .     

Scenario-Based Risk Assessment of Multi-Use Chemicals: Application to Solvents

The risk through chemical exposure is commonly characterized by ratios of exposure concentrations and effect levels (risk quotients). For chemicals with many different applications such as solvents, however, in addition to the risk quotients of different exposure situations it is useful to determine the corresponding numbers of exposed individuals, that is, not only the magnitude but also the extent of the risk. To this end, the Scenario-Based Risk Assessment (SceBRA) method has been developed that makes use of a large set of scenarios, each of which describes a typical situation regarding handling a solvent or solvent-containing product. The scenarios cover the life-cycle steps of production, distribution, and use of solvents. For each scenario, SceBRA provides the risk quotient, r, and the number of exposed individuals, N. This study investigated seven solvents that are used in large amounts in Switzerland. For each solvent, characteristic distributions of r and N values were calculated, making it possible to compare different solvents with respect to their risk profile. Graphical representations of the r, N data provide an informative way for analyzing and communicating the results of SceBRA.