Investigation about a screening step in model selection

In many studies a large number of variables is measured and the identification of relevant variables influencing an outcome is an important task. For variable selection several procedures are available. However, focusing on one model only neglects that there usually exist other equally appropriate models. Bayesian or frequentist model averaging approaches have been proposed to improve the development of a predictor. With a larger number of variables (say more than ten variables) the resulting class of models can be very large. For Bayesian model averaging Occam’s window is a popular approach to reduce the model space. As this approach may not eliminate any variables, a variable screening step was proposed for a frequentist model averaging procedure. Based on the results of selected models in bootstrap samples, variables are eliminated before deriving a model averaging predictor. As a simple alternative screening procedure backward elimination can be used. Through two examples and by means of simulation we investigate some properties of the screening step. In the simulation study we consider situations with fifteen and 25 variables, respectively, of which seven have an influence on the outcome. With the screening step most of the uninfluential variables will be eliminated, but also some variables with a weak effect. Variable screening leads to more applicable models without eliminating models, which are more strongly supported by the data. Furthermore, we give recommendations for important parameters of the screening step.     

Uniformly best estimation in linear regression when prior information is fuzzy

Modeling prior information as a fuzzy set and using Zadeh’s extension principle, a general approach is presented how to rate linear affine estimators in linear regression. This general approach is applied to fuzzy prior information sets given by ellipsoidal α-cuts. Here, in an important and meaningful subclass, a uniformly best linear affine estimator can be determined explicitly. Surprisingly, such a uniformly best linear affine estimator is optimal with respect to a corresponding relative squared error approach. Two illustrative special cases are discussed, where a generalized least squares estimator on the one hand and a general ridge or Kuks–Olman estimator on the other hand turn out to be uniformly best.     

Nonsuicidal Self‐Injury in a Community Sample of Adolescents: Subgroups,Stability, and Associations With Psychological Difficulties

Patterns of nonsuicidal self‐injury (NSSI) and their association with other psychological difficulties were studied in a community sample of young Swedish adolescents, by a two‐wave longitudinal design with a 1‐year interval. Hierarchical cluster analysis at T1 identified eight NSSI subgroups in each gender, of which five were clearly replicated at T2. Among these were a subgroup with generalized high‐frequency NSSI, which was associated with both internalizing and externalizing problems, and a subgroup of girls who engaged primarily in cutting and showed mainly internalizing problems. In general, NSSI clusters among girls were more stable over time and associated with more psychological problems. The results indicate that different patterns of NSSI have different developmental and clinical implications.     

Buchbesprechungen

Ohne Zusammenfassung     

The asymptotic unbiasedness of S2 in the linear regression model with AR(1)-disturbances

The OLS-estimator of the disturbance variance in the Linear Regression Model is shown to be asymptotically unbiased in the context of AR(1)-disturbances, although for any given design, E(s²/σ²) tends to zero as correlation increases.     

A global perspective on happiness and fertility

The literature on fertility and happiness has neglected comparative analysis. We investigate the fertility/happiness association using data from the world values surveys for 86 countries. We find that, globally, happiness decreases with the number of children. This association, however, is strongly modified by individual and contextual factors. Most importantly, we find that the association between happiness and fertility evolves from negative to neutral to positive above age 40, and is strongest among those who are likely to benefit most from upward intergenerational transfers. In addition, analyses by welfare regime show that the negative fertility/ happiness association for younger adults is weakest in countries with high public support for families, and the positive association above age 40 is strongest in countries where old-age support depends mostly on the family. Overall these results suggest that children are a long-term investment in well-being, and highlight the importance of the life-cycle stage and contextual factors in explaining the happiness/fertility association.     

Ascribing materiality and agency to strategy in interaction: A language-based approach to the material agency of strategy

Adding to the existent research on strategy as discourse and practice, this paper develops a language-based approach to viewing the agency and materiality of strategy. The study draws insights from the communicative constitution of organization (CCO) approach and linguistic agency to investigate how organizational members ascribe materiality and performative agency to strategy in their talk-in-interaction. The data consist of 14 video-recorded dyadic manager-to-manager conversations from one private and one public Finnish organization. The findings highlight how strategy is habitually spoken of as a material concrete entity and as a nonhuman agent that makes a difference in the course of described actions. The findings thus suggest that the performative position of strategy has been encoded in language and its use, which further suggests that object-like concreteness and agentivity are key elements of the organizational strategy discourse.     

Scheduling with interjob communication on parallel processors

Consider a scheduling problem in which a set of tasks needs to be scheduled on m parallel processors. Each task \(T_i\) consists of a set of jobs with interjob communication demands, represented by a weighted, undirected graph \(G_i\). The processors are assumed to be interconnected by a shared communication channel, which can be used by jobs to communicate among each other while being processed in parallel. In each time step, the scheduler assigns jobs to the processors and allows any processed job to use a certain capacity of the channel in order to satisfy (parts of) its communication demands to adjacent jobs processed in the same step. The goal is to find a schedule with minimum length in which the communication demands of all jobs are satisfied. We show that this problem is NP-hard in the strong sense even if the number of processors is constant and the underlying graph is a single path or a forest with arbitrary constant maximum degree. Consequently, we design and analyze approximation algorithms with asymptotic approximation ratio \(\min \{1.8, 1.5 \frac{m}{m-1}\}+1\) if the underlying graph G, the union of the \(G_i\), is a forest. For general graphs it is \(\min \left\{ 1.8, \frac{1.5m}{m-1}\right\} \cdot \left( \text {arb}(G) + \frac{5}{3}\right) \), where \(\text {arb}(G)\) denotes the arboricity of G.