Irregularly observed time series – some asymptotics and the block bootstrap

We consider time series being observed at random time points. In addition to Parzen's classical modelling by amplitude modulating sequences, we state another modelling using an integer-valued sequence as the observation times. Limiting results are presented for the sample mean and are generalized to the class of functions of smooth means. Motivated by the complicated limiting behaviour, (moving) block bootstrap possibilities are investigated. Conditional on the used modelling for the irregular spacings, one is lead to different interpretations for the block length and hence bootstrap approaches. The block length either can be interpreted as the time (resulting in an observation string of fixed length containing a random number of observations) or as the number of observations (resulting in an observation string of variable length containing a fixed number of values). Both bootstrap approaches are shown to be asymptotically valid for the sample mean. Numerical examples and an application to real-world ozone data conclude the study.     

The effects of propensity score weighting on attrition biases in attitudinal,behavioral, and socio-demographic variables in a short-term web-based panel survey

Propensity score weighting often is used to correct for attrition biases in panel surveys. While methodological literature exists on the logic of propensity score weighting and its practical applications, an in-depth discussion is lacking on the effects of using this weighting to correct for attrition biases in attitudinal, behavioral, and socio-demographic variables. By applying a split panel design, we assessed the effects of weighting on attrition biases in 48 attitudinal, 38 behavioral, and 27 socio-demographic variables. Our findings suggest – while acknowledging the estimate-specific nature of bias – first, that biases vary across these types of variables and second, that the effects of propensity score weighting are not homogeneous across the types. Accordingly, a sole reliance on socio-demographics to evaluate attrition in the present panel survey would have resulted in an underestimation of the biases of attitudinal variables and an overestimation of the ability of weighting to cure the negative effects of attrition in behavioral variables.     

The Portfolio Ideal Worker: Insecurity and Inequality in the New Economy

Qualitative Sociology - Abstract The white-collar ideal worker norm helps to explain why social inequality persists in the workplace, yet the concept reflects corporate workplaces of the...     

Leadership and Stress Orientations of Germans: An Examination Based on Gender, Age, and Government Work Experience

Today??s working adults often display different leadership orientations, as well as moderate to severe levels of stress depending on the situation and various demographic traits. In order to explore the stress, task orientation and relationship orientation variables of German people, this study examined the differences of 232 respondents in Germany based on their gender, age, and public sector work experience. The results showed that respondents had dissimilar scores on their leadership orientations. Younger respondents had significantly lower task and relationship orientation scores. Furthermore, females reported having a significantly higher level of stress perception. These findings are useful for expatriate managers and professionals who work with German-born workers. Besides, relevant literature on the German culture, suggestions and implications for future studies are presented.     

Weshalb die Separierung von Produktivitätseffekten und Diskriminierung bei der studentischen Lehrveranstaltungsbewertung misslingt

In their article “Mein(schöner)Prof.de. The Physical Attractiveness of Academic Staff and Its Influence on Evaluations by Students”, Ulrich Rosar and Markus Klein try to show that attractive teachers don’t perform better in the classroom. There are three objections against their conclusion from the empirical analyses based on data from the online platform MeinProf.de: the high selectivity of the used sample, the missing control for relevant covariates as well as the choice of the modeling strategy and the interpretation of the statistical models. These arguments are also backed with data of “real” students’ evaluations of teaching at the LMU Munich. It is recommended to use such “real” students’ evaluations of teaching instead of selective samples from online platforms and to (consistently) include relevant confounding factors, which seem to be relevant from a theoretical and empirical perspective, such as the students’ prior interest in the topic of the course and the course type into the analyses. Furthermore, it is suggested to clearly separate statistical detectability of effects from their practical relevance.     

Modelling of a thermomechanically coupled forming process based on functional outputs from a finite element analysis and from experimental measurements

In this paper, measurements from experiments and results of a finite element analysis (FEA) are combined in order to compute accurate empirical models for the temperature distribution before a thermomechanically coupled forming process. To accomplish this, Design and Analysis of Computer Experiments (DACE) is used to separately compute models for the measurements and the functional output of the FEA. Based on a hierarchical approach, a combined model of the process is computed. In this combined modelling approach, the model for the FEA is corrected by taking into account the systematic deviations from the experimental measurements. The large number of observations based on the functional output hinders the direct computation of the DACE models due to the internal inversion of the correlation matrix. Thus, different techniques for identifying a relevant subset of the observations are proposed. The application of the resulting procedure is presented, and a statistical validation of the empirical models is performed.     

Does Sexual Orientation Have an Impact on Nonverbal Behavior in Interpersonal Communication?

This study explores the impact of sexual orientation on the nonverbal behavior of individuals in dyadic communication situations. It is hypothesized that the patterns of nonverbal behavior displayed in dyads with and without an individual with an open homosexual orientation are different from those in dyads with heterosexual participants only. An observational study was conducted with a total of 24 participants, 12 with a heterosexual orientation and 12 with a homosexual orientation (6 males and 6 females in each group). Participants were videotaped during a 20-min conversation which took place in dyads that were composed of individuals of the same biological sex with either the same sexual orientation (homosexual or heterosexual) or differing sexual orientations. Results show that in dyads which include a homosexual person nonverbal behavior is different from that displayed in dyads consisting of heterosexual participants only in terms of self-touch, body posture, body orientation, and gaze. Results are interpreted in terms of stereotyping and presentation rules.     

Die Organisation kollektiver Aktionen durch Beeinflussung der individuellen Teilnahmeentscheidung

Computer simulations allow a more optimal organization of collective action. For this purpose, the present study followed an actor-centered approach, in which the actor’s decision to participate in collective action is modeled on the basis of an expansion of the Theory of Planned Behavior. The variables used in the model of the individual’s decision to participate in a collective action are attitude, return, subjective social norm, and perceived behavior control with regard to participation. With these four variables, various social scientific theories are integrated (Elaboration Likelihood Model, Theory of Planned Behavior, Rational Choice Theory). These theories allow a conceptualization of interactions among individuals, and the effect of the active people, who seek to recruit others to participate in a collective action, can be studied. Simulations of a population of 10,000 individuals reveal the influence of the following factors on the effectiveness of collective action campaigns: different forms of recruitment by activators, the amount of contributions to the collective good of the participants, the size of the collective good, and the resources available to activators (training in persuasion methods, possibility to reward participants). Finally, simulation results are summarized in the form of recommendations for implementation when organizing collective action.     

Gathering time-series data for evaluating behavior-change campaigns in developing countries: reactivity of diaries and interviews

Gathering time-series data of behaviors and psychological variables is important to understand, guide, and evaluate behavior-change campaigns and other change processes. However, repeated measurement can affect the phenomena investigated, particularly frequent face-to-face interviews, which are often the only option in developing countries. This article presents three intervention control studies to investigate this issue. Daily diaries in Cuba did not affect behavior or attitudes for persons with intervention but reduced attitudes for persons without intervention. Reactivity of face-to-face interviews in Bolivia was negligible if applied weekly, but strong if applied twice per week. The article concludes with recommendations for gathering time-series data in developing countries.