Bayesian inference for comparing two Poisson rates using data subject to underreporting and validation data

We derive a new Bayesian credible interval estimator for comparing two Poisson rates when counts are underreported and an additional validation data set is available. We provide a closed-form posterior density for the difference between the two rates that yields insightful information on which prior parameters influence the posterior the most. We also apply the new interval estimator to a real-data example, investigate the performance of the credible interval, and examine the impact of informative priors on the rate difference posterior via Monte Carlo simulations.     

Larger posterior mode wavelet thresholding and applications

This paper explores the thresholding rules induced by a variation of the Bayesian MAP principle. The MAP rules are Bayes actions that maximize the posterior. The proposed rule is thresholding and always picks the mode of the posterior larger in absolute value, thus the name LPM. We demonstrate that the introduced shrinkage performs comparably to several popular shrinkage techniques. The exact risk properties of the thresholding rule are explored, as well. We provide extensive simulational analysis and apply the proposed methodology to real-life experimental data coming from the field of atomic force microscopy.     

The Diversity Imperative: The Effects of Local Economic Structure and Social Capital on Local Philanthropy

VOLUNTAS: International Journal of Voluntary and Nonprofit Organizations - Philanthropic endeavors are a form of institutionalized collective action that enhances a community’s capacity to...     

The Reorganization of the US Citizenship and Immigration Services (USCIS) and Its Effects

Public Organization Review - Few studies have assessed the consequences of reorganization on the perceptions of employees. The article examines the effects of the reorganization of the US...     

Self‐concept as a mechanism through which parental psychological control impairs empathy development from adolescence to emerging adulthood

We examined the relationship among perceived parental psychological control (PPC), self‐concept, and empathy, from adolescence to emerging adulthood. Child Development Project longitudinal data analyses indicate that, when adolescents notice PPC at age 13, they have poor self‐concept (less competence) at age 16, and they show less empathic concern (EC) toward others at age 24. The indirect effects of self‐concept at age 16 are significant for EC, but not for perspective taking (PT). Moreover, perceived PPC at age 13 does not directly predict their EC at age 24, but it does their PT at age 24, and these results were found regardless of the gender of the parents and adolescents. Our results shed light on poor self‐concept in adolescence as a mechanism by which PPC impairs healthy emotional development from adolescence to emerging adulthood.     

If you plant it,they will come: quantifying attractiveness of exotic plants for winter-active flower visitors in community gardens

Urban community gardens are potentially important sites for urban pollinator conservation because of their high density, diversity of flowering plants, and low pesticide use (relative to agricultural spaces). Selective planting of attractive crop plants is a simple and cost-effective strategy for attracting flower visitors to urban green spaces, however, there is limited empirical data about which plants are most attractive. Here, we identified key plant species that were important for supporting flower visitors using a network-based approach that combined metrics of flower visitor abundance and diversity on different crop species. We included a metric of ‘popularity’ which assessed how frequently a particular plant appeared within community gardens. We also determined the impact of garden characteristics such as size, flower species richness, and flower species density on the abundance and diversity of flower visitors. Two plant species, Brassica rapa and Ocimum basilicum were identified as being particularly important species for supporting flower visitor populations. Flower species richness had a strong positive effect on both the abundance and diversity of flower visitors. We suggest that gardeners can maximise the conservation value of their gardens by planting a wide variety of flowering plants including attractive plants such as B. rapa and O. basilicum.

     

Planning and analyzing clinical trials with competing risks: Recommendations for choosing appropriate statistical methodology

In the analysis of time‐to‐event data, competing risks occur when multiple event types are possible, and the occurrence of a competing event precludes the occurrence of the event of interest. In this situation, statistical methods that ignore competing risks can result in biased inference regarding the event of interest. We review the mechanisms that lead to bias and describe several statistical methods that have been proposed to avoid bias by formally accounting for competing risks in the analyses of the event of interest. Through simulation, we illustrate that Gray's test should be used in lieu of the logrank test for nonparametric hypothesis testing. We also compare the two most popular models for semiparametric modelling: the cause‐specific hazards (CSH) model and Fine‐Gray (F‐G) model. We explain how to interpret estimates obtained from each model and identify conditions under which the estimates of the hazard ratio and subhazard ratio differ numerically. Finally, we evaluate several model diagnostic methods with respect to their sensitivity to detect lack of fit when the CSH model holds, but the F‐G model is misspecified and vice versa. Our results illustrate that adequacy of model fit can strongly impact the validity of statistical inference. We recommend analysts incorporate a model diagnostic procedure and contingency to explore other appropriate models when designing trials in which competing risks are anticipated.     

Two Competing Models of How People Learn in Games

Reinforcement learning and stochastic fictitious play are apparent rivals as models of human learning. They embody quite different assumptions about the processing of information and optimization. This paper compares their properties and finds that they are far more similar than were thought. In particular, the expected motion of stochastic fictitious play and reinforcement learning with experimentation can both be written as a perturbed form of the evolutionary replicator dynamics. Therefore they will in many cases have the same asymptotic behavior. In particular, local stability of mixed equilibria under stochastic fictitious play implies local stability under perturbed reinforcement learning. The main identifiable difference between the two models is speed: stochastic fictitious play gives rise to faster learning.