A ratio-to-control Williams-type test for trend

Under certain conditions, many multiple contrast tests based on the difference of treatment means can also be conveniently expressed in terms of ratios. In this paper, a Williams test for trend is defined as ratios-to-control for ease of interpretation and to obtain directly comparable confidence intervals. Simultaneous confidence intervals for percentages are particularly helpful for interpretations in the case of multiple endpoints. Methods for constructing simultaneous confidence intervals are discussed under both homogeneous and heterogeneous error variances. This approach is available in the R extension package mratios. The proposed method is used to test for trend in an immunotoxicity study with several endpoints as an example.     

Activation,Public Employment Services and their Clients: The Role of Social Class in a Continental Welfare State

This article fills a gap in the existing literature by investigating how public employment service (PES) staff actually deal with their clients under a continental regime of activation. The results reported here are based on interviews both with PES staff and their unemployed clients in Germany. We argue that due to its Bismarckian origins as an insurance‐based system of ‘unemployment protection’, Germany's system of unemployment compensation is attractive not only for the marginalized, but also for core workers. As a result, PES staff deal with clients from very heterogeneous class backgrounds. We demonstrate that social class is a significant factor in client outcomes, and that earlier research has perhaps overemphasized the role of frontline staff as ‘street‐level bureaucrats’. While staff do have considerable power, the result of the encounters between the administration and clients also depends on the capabilities of the clients, which, in turn, are strongly related to social class.     

Contrasting Complex with Highly Complex Contact Disputes Between Parents

This article discusses the complexity of seeking a solution to problems associated at times with parental alienation. Two scenarios are presented. Both cases involve a child who does not wish to have contact with an absent parent after the separation of the parents due to implacable hostility between them. In the first case, the child had a good relationship with the now absent parent. In the second case the child never had a close relationship with the absent parent. Each case needs to be assessed on its own merits. Conclusions are drawn and recommendations are made as to how to deal with such issues.     

What if the Custodial Parent Refuses to Cooperate With Child Contact Decisions?

This article considers the failings at present of the judicial system in not being even handed in providing justice for the noncustodial parent, who has for whatever reason been ousted from the relationship and has poor, if any, contact with his or her children. The advice being provided by the current psychologist dealing with such cases is for the judiciary to adopt a much firmer approach. This will lead to the judiciary being respected rather than being considered unjust. The article is concerned with severe parental alienation and provides a solution to the situation to prevent further emotional abuse of children against an absent parent. The author encourages mediation to commence with and then continue when making decisions as to who should have custody of the children who have been emotionally abused via an alienating parent.     

Bayesian inference for generalized additive mixed models based on Markov random field priors

Most regression problems in practice require flexible semiparametric forms of the predictor for modelling the dependence of responses on covariates. Moreover, it is often necessary to add random effects accounting for overdispersion caused by unobserved heterogeneity or for correlation in longitudinal or spatial data. We present a unified approach for Bayesian inference via Markov chain Monte Carlo simulation in generalized additive and semiparametric mixed models. Different types of covariates, such as the usual covariates with fixed effects, metrical covariates with non-linear effects, unstructured random effects, trend and seasonal components in longitudinal data and spatial covariates, are all treated within the same general framework by assigning appropriate Markov random field priors with different forms and degrees of smoothness. We applied the approach in several case-studies and consulting cases, showing that the methods are also computationally feasible in problems with many covariates and large data sets. In this paper, we choose two typical applications.     

A comparison study on modeling of clustered and overdispersed count data for multiple comparisons

Data collected in various scientific fields are count data. One way to analyze such data is to compare the individual levels of the factor treatment using multiple comparisons. However, the measured individuals are often clustered – e.g. according to litter or rearing. This must be considered when estimating the parameters by a repeated measurement model. In addition, ignoring the overdispersion to which count data is prone leads to an increase of the type one error rate. We carry out simulation studies using several different data settings and compare different multiple contrast tests with parameter estimates from generalized estimation equations and generalized linear mixed models in order to observe coverage and rejection probabilities. We generate overdispersed, clustered count data in small samples as can be observed in many biological settings. We have found that the generalized estimation equations outperform generalized linear mixed models if the variance-sandwich estimator is correctly specified. Furthermore, generalized linear mixed models show problems with the convergence rate under certain data settings, but there are model implementations with lower implications exists. Finally, we use an example of genetic data to demonstrate the application of the multiple contrast test and the problems of ignoring strong overdispersion.     

On Hotelling’s T2 test in a special paired sample case

In a special paired sample case, Hotelling’s T² test based on the differences of the paired random vectors is the likelihood ratio test for testing the hypothesis that the paired random vectors have the same mean; with respect to a special group of affine linear transformations it is the uniformly most powerful invariant test for the general alternative of a difference in mean. We present an elementary straightforward proof of this result. The likelihood ratio test for testing the hypothesis that the covariance structure is of the assumed special form is derived and discussed. Applications to real data are given.     

Unverfälschte Variablenprüfpläne für exponentialverteilte Merkmale mit zweiseitigen Toleranzgrenzen

As a well known fact the standard X²-procedures (e.g. confidence intervals for σ², tests of the hypothesis H:″σ=σ_o″ in the case of normal population with variance σ²) are biased. We refer to some useful tables which enable in the case of normal population to procure unbiased confidence intervals or confidence intervals with minimal length for σ², control charts for σ with minimal distance between the limit lines, and unbiased tests of H:″σ=σ_o″. Another important application yields—as main result of the present paper—unbiased sampling plans in the case of an exponential distributed attribute with upper and lower specification limit (two-way-protection). It turns out to be possible, also in the case of exponential distribution, to reduce the sample size by using incomplete prior information about the proportion p of defectives.