Multivariate Life Testing in Variably Scaled Environments

This paper examines modeling and inference questions for experiments in which different subsets of a set of k possibly dependent components are tested in r different environments. In each environment, the failure times of the set of components on test is assumed to be governed by a particular type of multivariate exponential (MVE) distribution. For any given component tested in several environments, it is assumed that its marginal failure rate varies from one environment to another via a change of scale between the environments, resulting in a joint MVE model which links in a natural way the applicable MVE distributions describing component behavior in each fixed environment. This study thus extends the work of Proschan and Sullo (1976) to multiple environments and the work of Kvam and Samaniego (1993) to dependent data. The problem of estimating model parameters via the method of maximum likelihood is examined in detail. First, necessary and sufficient conditions for the identifiability of model parameters are established. We then treat the derivation of the MLE via a numerically-augmented application of the EM algorithm. The feasibility of the estimation method is demonstrated in an example in which the likelihood ratio test of the hypothesis of equal component failure rates within any given environment is carried out.     

Mixing patterns between age groups in social networks

We present a method for estimating transmission matrices that describe the mixing and the probability of infection between age groups. Transmission matrices can be used to estimate age-dependent forces of infection in age-structured, compartmental models for the study of infectious diseases. We analyze the social network generated by the synthetic population of Portland and extract mixing patterns. Our results show that the mixing within the population consists of two groups, children and adults. Children interact most frequently with other children close to their own age, while adults interact with a wider range of age groups and the durations of typical adult contacts are shorter than typical contacts between children. Furthermore, the transmission matrix shows that children are more likely to acquire infection than adults.     

Sicherheitsäquivalente zur risikoadjustierten Bewertung: Unternehmensexterne Bewertungssicht vs. unternehmensinterne Steuerungssicht Replik zu den Anmerkungen „Zum Verhältnis von Wertadditivität bei Sicherheitsäquivalenten und Risikoanalyse“ von <Emphasis Type="Italic">Reichling et al.</Emphasis> (2008)

Die Forderung nach schwacher Wertadditivit?t von Sicherheits?quivalenten ist in Abh?ngigkeit des jeweiligen Bewertungszwecks zu diskutieren. W?hrend in der unternehmensexternen Bewertungssicht, z.B. bei der Unternehmensbewertung, die Forderung nach schwacher Wertadditivit?t gut begründbar ist, stellt sie im Bereich der unternehmensinternen Steuerungssicht eine „Nice to have“-Anforderung dar. Darüber hinaus werden in der bisherigen Literatur zur Anwendbarkeit von Sicherheits?quivalenten die Kernherausforderungen der unternehmensinternen Steuerung vernachl?ssigt. Insbesondere die ad?quate Berücksichtigung stochastischer Abh?ngigkeiten im Portfolioverbund bei der Bewertung von Einzelgesch?ften mittels Sicherheits?quivalenten stellt eine Forschungslücke dar.     

Discriminating characteristics of union members’ attitudes toward drug testing in the workplace

In this study of the acceptance by union members of drug testing in the workplace, 919 union members from 13 major unions were asked what drug-testing policy, if any, they preferred. Respondents evaluated particular aspects of a hypothetical drug-testing program. The results show that a large majority of union members agree with a limited drug-testing policy. Five theoretical models of union member attitudes were extrapolated to the drug-testing context and were examined by using discriminant function analysis. No support was found for the individual demographics theory, but empirical support was found for some elements of instrumental union, bargaining outcomes, general normative attitude, and workplace conditions theory. The discriminant function was 80.56 percent successful in classifying union members who accept drug testing.     

Facial expression in the presence of friends and strangers

This study investigated the effect of the physical presence of a friend or of a stranger on facial expressiveness. Pairs of friends and pairs of strangers (all women) were unobtrusively videotaped while they viewed together a number of emotional stimulus slides, and rated their individual emotional responses to them. Judges subsequently attempted to identify from the videotapes the emotions reported by each sender subject. Generally, expressions were more readily identified for women videotaped with friends than for those recorded with strangers. These results support the suggestion that the degree to which emotions are expressed depends on the role of an accompanying person. Altemative interpretations of this view are discussed.We thank Alan Fridlund and an anonymous reviewer for comments on a previous version of this paper.     

TEACHING TOOLS: COOPERATIVE LEARNING IN ECONOMICS

Cooperative learning is a structured, systematic instructional technique in which students work together in small groups toward a common goal. We demonstrate the effectiveness of cooperative learning with an illustrative example for teaching the labor supply curve. Recommendations for introducing the technique, forming groups, the instructor's role during group work, grading and extensions of cooperative learning to other topics are discussed.     

A simple recursive estimation method for linear regression models with AR(p) disturbances

An exact transformation that reduces the AR(p) process into white noise is well known in statistics, see Fuller (1976). However, practitioners still use and econometric textbooks still recommend the Cochrane-Orcutt procedure for p>2, see Greene (1990). This paper derives an alternative exact transformation for the AR(p) process which is computationally simple. Based on this transformation, a GLS estimator is proposed, requiring only least squares regressions and recursive computations. This is illustrated for the AR(3) case.