Bain: a program for Bayesian testing of order constrained hypotheses in structural equation models

This paper presents a new statistical method and accompanying software for the evaluation of order constrained hypotheses in structural equation models (SEM). The method is based on a large sample approximation of the Bayes factor using a prior with a data-based correlational structure. An efficient algorithm is written into an R package to ensure fast computation. The package, referred to as Bain, is easy to use for applied researchers. Two classical examples from the SEM literature are used to illustrate the methodology and software.     

Non-reversible Metropolis-Hastings

The classical Metropolis-Hastings (MH) algorithm can be extended to generate non-reversible Markov chains. This is achieved by means of a modification of the acceptance probability, using the notion of vorticity matrix. The resulting Markov chain is non-reversible. Results from the literature on asymptotic variance, large deviations theory and mixing time are mentioned, and in the case of a large deviations result, adapted, to explain how non-reversible Markov chains have favorable properties in these respects. We provide an application of NRMH in a continuous setting by developing the necessary theory and applying, as first examples, the theory to Gaussian distributions in three and nine dimensions. The empirical autocorrelation and estimated asymptotic variance for NRMH applied to these examples show significant improvement compared to MH with identical stepsize.     

Making the Iceberg Visible Again: Service Delivering Experiences as a Lever for NPOs’ Advocacy Under a Third-Party Government Regime

VOLUNTAS: International Journal of Voluntary and Nonprofit Organizations - Under a third-party government regime, NPOs are largely funded to implement social policies and have open lines of...     

The Attractiveness Halo: Why Some Candidates are Perceived More Favorably than Others

Olivola and Todorov (Elected in 100 milliseconds: appearance-based trait inferences and voting. J Nonverbal Behav, 2010) provide a convincing demonstration that competence ratings based on 1-second exposures to paired photos of US congressional candidates predict election outcomes at better than chance levels. However, they do not account for variation in competence judgments. In their analysis, Olivola and Todorov show that attractiveness, familiarity, babyfacedness and age are proximal predictors of vote choice, but find that after controlling for competence these factors no longer reliably influence the margin of electoral victory. Drawing on well-documented halo effects of attractiveness on character-based inferences and the extensive literature on mere exposure effects, we re-organize Olivola and Todorov’s analysis into a simple path model to explore the causal ordering of these factors. We find that spontaneous assessments of attractiveness and familiarity occur prior to attributions of competence, and thus exert a downstream effect on judgments of competence.     

Bayesian tests on components of the compound symmetry covariance matrix

Complex dependency structures are often conditionally modeled, where random effects parameters are used to specify the natural heterogeneity in the population. When interest is focused on the dependency structure, inferences can be made from a complex covariance matrix using a marginal modeling approach. In this marginal modeling framework, testing covariance parameters is not a boundary problem. Bayesian tests on covariance parameter(s) of the compound symmetry structure are proposed assuming multivariate normally distributed observations. Innovative proper prior distributions are introduced for the covariance components such that the positive definiteness of the (compound symmetry) covariance matrix is ensured. Furthermore, it is shown that the proposed priors on the covariance parameters lead to a balanced Bayes factor, in case of testing an inequality constrained hypothesis. As an illustration, the proposed Bayes factor is used for testing (non-)invariant intra-class correlations across different group types (public and Catholic schools), using the 1982 High School and Beyond survey data.     

Holding the Pencil or Buying Paint: Parental Childcare Versus Children’s Need for Extra Income. The Case of Belgium,Denmark and Spain

This article addresses the influence of child characteristics on couples’ decision-making regarding employment and parental childcare. Through simultaneous equation modeling we are able to separate earnings from care motives in this decision-making process. An empirical exercise on Belgian data illustrates how the earnings motive counteracts the care motive and causes a rise in the probability of a full-time job following an increase of the number of children. However, replication on Danish and Spanish data also suggests that a country’s incentive framework provides important limits to couples’ decision-making.     

Reconciling Perspectives on Clusters: An Integrative Review and Research Agenda

Although our understanding of clusters and their contribution to economic performance has improved over the last three decades, the literature has become host to a wide array of divergent empirical and theoretical claims. We systematically review cluster studies published in top journals, highlighting the lack of integration among prior work. We focus on the ways in which Porter's three cluster dimensions, namely geography, networks, and institutions, have been utilized. None of the studies reviewed fully captured their complex interrelationships, which we argue is an important cause of the key disagreements in the literature. Configurational theorizing and analysis are presented as means by which the different approaches to cluster studies could be reconciled. We discuss how the application of a configurational approach can help explore new scholarly directions that can deepen our understanding of clusters and their performance‐enhancing potential. In doing so, we can move beyond an understanding of independent effects to emphasizing combinations of attributes that can generate multiple pathways to cluster performance outcomes.     

No overall effect of urbanization on nest-dwelling arthropods of great tits (Parus major).

Urbanization has been shown to strongly affect community composition of various taxa with potentially strong shifts in ecological interactions, including those between hosts and parasites. We investigated the effect of urbanization on the composition of arthropods in nests of great tits in Flanders, Belgium. These nests contain taxonomically and functionally diverse arthropod communities including parasites, predators, detritivores and accidental commensals. Using a standardized hierarchical sampling design with subplots (200 m?×?200 m) nested in plots (3 km?×?3 km) of varying urbanization levels, we collected arthropods from nests of resident great tits after the young had fledged. Arthropods were extracted, identified to Primary Taxonomical Groups (PTG) and counted. Using generalized linear mixed models (GLMMs) we found diverging effects of urbanization on PTG occurrences and abundances at various levels, but we did not find an overall signal in arthropod diversity or richness. Also, visual inspection of non-metric multidimensional scaling (NMDS) plots did not reveal any community differences between urbanization levels at plot or subplot scales. Land use and environmental variables at different distances around nestboxes did not contribute much to the variation between communities. Our results indicate that arthropod nestbox communities are generally not adversely affected by urbanization, and even city gardens and parks harbor comparable communities to forests and suburban areas. We thus found no evidence for a parasite release effect due to urbanization, nor an increased risk of parasitism in human-dominated environments.

     

Associations of Internalizing and Externalizing Problems with Facial Expression Recognition in Preschoolers: The Generation R Study

Altered patterns of facial expression recognition (FER) have been linked to internalizing and externalizing problems in school children and adolescents. In a large sample of preschoolers (N = 727), we explored concurrent and prospective associations between internalizing/externalizing problems and FER. Internalizing/externalizing problems were rated by parents at 18 and 36 months using the Child Behavior Checklist. FER was assessed at 36 months using age‐appropriate computer tasks of emotion matching and emotion labeling. Internalizing problems were associated with emotion‐specific differences at both ages: at 18 months they predicted more accurate labeling of sadness; at 36 months they were associated with less accurate labeling of happiness and anger. Externalizing problems at both ages were associated with general FER deficits, particularly for matching emotions. Findings suggest that in preschoolers, internalizing problems contribute to emotion‐specific differences in FER, while externalizing problems are associated with more general FER deficits. Knowledge of the specific FER patterns associated with internalizing/externalizing problems can be proven useful in the refinement of emotion‐centered preventive interventions.