Correlation in a Bayesian framework

The authors consider the correlation between two arbitrary functions of the data and a parameter when the parameter is regarded as a random variable with given prior distribution. They show how to compute such a correlation and use closed form expressions to assess the dependence between parameters and various classical or robust estimators thereof, as well as between p‐values and posterior probabilities of the null hypothesis in the one‐sided testing problem. Other applications involve the Dirichlet process and stationary Gaussian processes. Using this approach, the authors also derive a general nonparametric upper bound on Bayes risks.     

Perfect samplers for mixtures of distributions

Summary. We consider the construction of perfect samplers for posterior distributions associated with mixtures of exponential families and conjugate priors, starting with a perfect slice sampler in the spirit of Mira and co-workers. The methods rely on a marginalization akin to Rao–Blackwellization and illustrate the duality principle of Diebolt and Robert. A first approximation embeds the finite support distribution on the latent variables within a continuous support distribution that is easier to simulate by slice sampling, but we later demonstrate that the approximation can be very poor. We conclude by showing that an alternative perfect sampler based on a single backward chain can be constructed. This alternative can handle much larger sample sizes than the slice sampler first proposed.     

Influence of Argentine and coastal brown ant (Hymenoptera: Formicidae) invasions on ant communities in Perth gardens,Western Australia

A survey examined the influence of Argentine (Linepithema humile (Mayr)) and coastal brown ant (Pheidole megacephala (Fabricius)) populations on other ants in the Perth metropolitan area, Western Australia. Twelve gardens (yards) were sampled; four infested by Argentine ants, three infested by coastal brown ants, and five controls where these two tramp ants were absent or collected only as isolated strays. Collection methods used were pitfall trapping and hand collection. A total of 27 species was recorded. Eight of these species, including the above two tramp ants, are non-native to the region. Pheidole megacephala was the most abundant species, comprising 95.4% of ants in P. megacephala–infested gardens. Linepithema humile comprised 92.1% of ants in L. humile–infested gardens. Other common ants were the native Iridomyrmex chasei and the introduced species Tetramorium simillimum and Tetramorium bicarinatum. The cryptic introduced species Cardiocondyla nuda and Tetramorium simillimum appear able to persist in small numbers in L. humile–infested gardens, but virtually no other ant species occurred where the coastal brown ant was well established. Mean richness, diversity, and evenness were significantly different between P. megacephala–infested and control gardens, and significantly different between L. humile–infested and control gardens. Diversity and evenness, but not richness, were significantly different between P. megacephala–infested and L. humile–infested gardens. Ordination analysis revealed that the three types of gardens had very different ant community profiles.     

Further Evaluation of the Accuracy of Managerial Prediction of Employee Preference

Previous research (i.e., Wilder, Rost, &; McMahon, 2007 Wilder, D. A., Rost, K. and McMahon, M. 2007. The accuracy of managerial prediction of employee preference: A brief report. Journal of Organizational Behavior Management, 27(2): 1–14. [Taylor &; Francis Online], [Web of Science ®] , [Google Scholar]) has suggested that managers perform poorly when predicting items and activities which their employees state that they might like to earn as part of performance improvement programs. The purpose of the current study was to replicate the earlier study conducted by Wilder et al. (2007 Wilder, D. A., Rost, K. and McMahon, M. 2007. The accuracy of managerial prediction of employee preference: A brief report. Journal of Organizational Behavior Management, 27(2): 1–14. [Taylor &; Francis Online], [Web of Science ®] , [Google Scholar]) with a larger and more diverse sample of managers and employees. One hundred employees and 15 managers were asked to rank order a list of items/activities they thought their employees would most prefer to be incorporated into a performance improvement plan. Next, employee preference for these same items was directly assessed using an employee reinforcer survey. Kendall rank-order correlation coefficients were used to compare the results of the managerial rank with the employee reinforcer survey. Correlations ranged from ?.6 to 1, with a mean of .25.     

A new approach to default priors and robust bayes methodology

Following the developments in DasGupta et al. (2000), the authors propose and explore a new method for constructing proper default priors and a method for selecting a Bayes estimate from a family. Their results are based on asymptotic expansions of certain marginal correlations. For ease of exposition, most results are presented for location families and squared error loss only. The default prior methodology amounts, ultimately, to the minimization of Fisher information, and hence, Bickel's prior works out as the default prior if the location parameter is bounded. As for the selected Bayes estimate, it corresponds to ‘Gaussian tilting’ of an initial reference prior.     

Confidence sets and the stein effect

The problem of improving upon the usual set estimator of a multivariate normal mean has only recently seen significant advances. Improved sets that take advantage of the Stein effect have been constructed. It is shown here that the Stein effect is so powerful that one can construct improved confidence sets that can have zero radius on a set of positive probability. Other, somewhat more sensible, sets which attain arbitrarily small radius are also constructed, and it is argued that one way to eliminate unreasonable confidence sets is through a conditional evaluation.     

Mixture models, latent variables and partitioned importance sampling

Gibbs sampling has had great success in the analysis of mixture models. In particular, the “latent variable” formulation of the mixture model greatly reduces computational complexity. However, one failing of this approach is the possible existence of almost-absorbing states, called trapping states, as it may require an enormous number of iterations to escape from these states. Here we examine an alternative approach to estimation in mixture models, one based on a Rao–Blackwellization argument applied to a latent-variable-based estimator. From this derivation we construct an alternative Monte Carlo sampling scheme that avoids trapping states.     

Punishing dangerousness through preventive detention: illustrating the institutional link between school and prison

Evidence-based observations of how the juvenile justice and educational systems can work together more effectively are presented.