Compliance of biosecurity practices for compartmentalization to foot-mouth disease and classical swine fever viruses in commercial swine companies from southern Brazil.

Classical swine fever (CSF) and foot-mouth disease (FMD) are both highly contagious disease and disruptive to commercial trades, but they are examples of foreign animal diseases that biosecurity-based compartmentalization could be used to support trade in free zones in response to an outbreak. This study aimed to evaluate biosecurity compliance to the Federal Normative Instruction #44 from December 4th, 2017 (BRAZIL, 2017) in commercial swine farms located in southern Brazil. A total of 604 swine farms from 10 commercial swine companies were sampled, from which 28.5% were breeding farms, 29.1% nursery, 32.8% finishing, 6.8% multipliers, and 2.8% farrow-to-finish. Cluster analyses revealed that farms with high compliance (n = 303, Cluster 1) performed 71% of the practices, moderate (n = 219, Cluster 2) 47%, and the low (n = 82, Cluster 3) 33%. A spatial logistic regression model estimated that biosecurity compliance was highest in only one of 10 commercial swine companies, and within a company, multipliers (when present) obtained the highest biosecurity compliance (p-value < 0.01). These results suggest that major improvements in biosecurity practices are needed in breeding herds, nursery, and grow-finish farms to be compliant to the Federal Instruction #44. Based on the combination of these analyses, only one commercial swine company was more suitable to establish compartments for CSF and FMD with minimal investments. Still, this study revealed that the majority of commercial swine companies needs to improve biosecurity practice protocols to then target compartmentalization.

Hierarchical Bayesian non-response models for error rates in forensic black-box studies.

Forensic science plays a critical role in the United States criminal legal system. Historically, however, most feature-based fields of forensic science, including firearms examination and latent print analysis, have not been shown to be scientifically valid. Recently, black-box studies have been proposed as a means of assessing whether these feature-based disciplines are valid, at least in terms of accuracy, reproducibility and repeatability. In these studies, forensic examiners frequently either do not respond to every test item or select an answer equivalent to 'don't know'. Current black-box studies do not account for these high levels of missingness in statistical analyses. Unfortunately, the authors of black-box studies typically do not share the data necessary to meaningfully adjust estimates for the high proportion of missing responses. Borrowing from work in the context of small area estimation, we propose the use of hierarchical Bayesian models that do not require auxiliary data to adjust for non-response. Using these models, we offer the first formal exploration of the impact that missingness is playing in error rate estimations reported in black-box studies. We show that error rates currently reported as low as 0.4% could actually be at least 8.4% in models accounting for non-response where inconclusive decisions are counted as correct, and over 28% when inconclusives are counted as missing responses. These proposed models are not the answer to the missingness problem in black-box studies. But with the release of auxiliary information, they can be the foundation for new methodologies to adjust for missingness in error rate estimations. This article is part of the theme issue 'Bayesian inference: challenges, perspectives, and prospects'.

RESTRICTED SPATIAL REGRESSION METHODS: IMPLICATIONS FOR INFERENCE.

The issue of spatial confounding between the spatial random effect and the fixed effects in regression analyses has been identified as a concern in the statistical literature. Multiple authors have offered perspectives and potential solutions. In this paper, for the areal spatial data setting, we show that many of the methods designed to alleviate spatial confounding can be viewed as special cases of a general class of models. We refer to this class as Restricted Spatial Regression (RSR) models, extending terminology currently in use. We offer a mathematically based exploration of the impact that RSR methods have on inference for regression coefficients for the linear model. We then explore whether these results hold in the generalized linear model setting for count data using simulations. We show that the use of these methods have counterintuitive consequences which defy the general expectations in the literature. In particular, our results and the accompanying simulations suggest that RSR methods will typically perform worse than non-spatial methods. These results have important implications for dimension reduction strategies in spatial regression modeling. Specifically, we demonstrate that the problems with RSR models cannot be fixed with a selection of "better" spatial basis vectors or dimension reduction techniques.

Neighborhoods, Activity Spaces, and the Span of Adolescent Exposures.

Since the inception of urban sociology, the "neighborhood" has served as the dominant context thought to capture developmentally significant youth experiences beyond the home. Yet no large-scale study has examined patterns of exposure to the most commonly used operationalization of neighborhood - the census tract - among urban youth. Using smartphone GPS data from the Adolescent Health and Development in Context study (N=1405), we estimate the amount of time youth spend in residential neighborhoods and consider explanations for variation in neighborhood exposure. On average, youth (ages 11 to 17) spend 5.7% of their waking time in their neighborhood but not at home, 60% at home, and 34.3% outside their neighborhood. Multilevel negative binomial regression models indicate that residence in economically disadvantaged neighborhoods is associated with less time in neighborhood. Higher levels of local violence and the absence of a neighborhood school the youth is eligible to attend are negatively associated with time in neighborhood and mediate the concentrated disadvantage effect. Fractional multinomial logit models indicate that higher violence is linked with increased time at home while school absence is associated with increased outside-neighborhood time. Theoretical development and empirical research on neighborhood effects should incorporate findings on the extent and nature of neighborhood and broader activity space exposures among urban youth.