EXTENDED STOCHASTIC BLOCK MODELS WITH APPLICATION TO CRIMINAL NETWORKS.

Reliably learning group structures among nodes in network data is challenging in several applications. We are particularly motivated by studying covert networks that encode relationships among criminals. These data are subject to measurement errors, and exhibit a complex combination of an unknown number of core-periphery, assortative and disassortative structures that may unveil key architectures of the criminal organization. The coexistence of these noisy block patterns limits the reliability of routinely-used community detection algorithms, and requires extensions of model-based solutions to realistically characterize the node partition process, incorporate information from node attributes, and provide improved strategies for estimation and uncertainty quantification. To cover these gaps, we develop a new class of extended stochastic block models (esbm) that infer groups of nodes having common connectivity patterns via Gibbs-type priors on the partition process. This choice encompasses many realistic priors for criminal networks, covering solutions with fixed, random and infinite number of possible groups, and facilitates the inclusion of node attributes in a principled manner. Among the new alternatives in our class, we focus on the Gnedin process as a realistic prior that allows the number of groups to be finite, random and subject to a reinforcement process coherent with criminal networks. A collapsed Gibbs sampler is proposed for the whole esbm class, and refined strategies for estimation, prediction, uncertainty quantification and model selection are outlined. The esbm performance is illustrated in realistic simulations and in an application to an Italian mafia network, where we unveil key complex block structures, mostly hidden from state-of-the-art alternatives.

Juno spacecraft gravity measurements provide evidence for normal modes of Jupiter.

The Juno spacecraft has been collecting data to shed light on the planet's origin and characterize its interior structure. The onboard gravity science experiment based on X-band and Ka-band dual-frequency Doppler tracking precisely measured Jupiter's zonal gravitational field. Here, we analyze 22 Juno's gravity passes to investigate the gravity field. Our analysis provides evidence of new gravity field features, which perturb its otherwise axially symmetric structure with a time-variable component. We show that normal modes of the planet could explain the anomalous signatures present in the Doppler data better than other alternative explanations, such as localized density anomalies and non-axisymmetric components of the static gravity field. We explain Juno data by p-modes having an amplitude spectrum with a peak radial velocity of 10-50 cm/s at 900-1200 µHz (compatible with ground-based observations) and provide upper bounds on lower frequency f-modes (radial velocity smaller than 1 cm/s). The new Juno results could open the possibility of exploring the interior structure of the gas giants through measurements of the time-variable gravity or with onboard instrumentation devoted to the observation of normal modes, which could drive spacecraft operations of future missions.

The depth of Jupiter's Great Red Spot constrained by Juno gravity overflights.

Jupiter's Great Red Spot (GRS) is the largest atmospheric vortex in the Solar System and has been observed for at least two centuries. It has been unclear how deep the vortex extends beneath its visible cloud tops. We examined the gravity signature of the GRS using data from 12 encounters of the Juno spacecraft with the planet, including two direct overflights of the vortex. Localized density anomalies due to the presence of the GRS caused a shift in the spacecraft line-of-sight velocity. Using two different approaches to infer the GRS depth, which yielded consistent results, we conclude that the GRS is contained within the upper 500 kilometers of Jupiter's atmosphere.

Bayesian cumulative shrinkage for infinite factorizations.

The dimension of the parameter space is typically unknown in a variety of models that rely on factorizations. For example, in factor analysis the number of latent factors is not known and has to be inferred from the data. Although classical shrinkage priors are useful in such contexts, increasing shrinkage priors can provide a more effective approach that progressively penalizes expansions with growing complexity. In this article we propose a novel increasing shrinkage prior, called the cumulative shrinkage process, for the parameters that control the dimension in overcomplete formulations. Our construction has broad applicability and is based on an interpretable sequence of spike-and-slab distributions which assign increasing mass to the spike as the model complexity grows. Using factor analysis as an illustrative example, we show that this formulation has theoretical and practical advantages relative to current competitors, including an improved ability to recover the model dimension. An adaptive Markov chain Monte Carlo algorithm is proposed, and the performance gains are outlined in simulations and in an application to personality data.

Convex mixture regression for quantitative risk assessment.

There is wide interest in studying how the distribution of a continuous response changes with a predictor. We are motivated by environmental applications in which the predictor is the dose of an exposure and the response is a health outcome. A main focus in these studies is inference on dose levels associated with a given increase in risk relative to a baseline. In addressing this goal, popular methods either dichotomize the continuous response or focus on modeling changes with the dose in the expectation of the outcome. Such choices may lead to information loss and provide inaccurate inference on dose-response relationships. We instead propose a Bayesian convex mixture regression model that allows the entire distribution of the health outcome to be unknown and changing with the dose. To balance flexibility and parsimony, we rely on a mixture model for the density at the extreme doses, and express the conditional density at each intermediate dose via a convex combination of these extremal densities. This representation generalizes classical dose-response models for quantitative outcomes, and provides a more parsimonious, but still powerful, formulation compared to nonparametric methods, thereby improving interpretability and efficiency in inference on risk functions. A Markov chain Monte Carlo algorithm for posterior inference is developed, and the benefits of our methods are outlined in simulations, along with a study on the impact of dde exposure on gestational age.

Bayesian network-response regression.

MOTIVATION: There is increasing interest in learning how human brain networks vary as a function of a continuous trait, but flexible and efficient procedures to accomplish this goal are limited. We develop a Bayesian semiparametric model, which combines low-rank factorizations and flexible Gaussian process priors to learn changes in the conditional expectation of a network-valued random variable across the values of a continuous predictor, while including subject-specific random effects. RESULTS: The formulation leads to a general framework for inference on changes in brain network structures across human traits, facilitating borrowing of information and coherently characterizing uncertainty. We provide an efficient Gibbs sampler for posterior computation along with simple procedures for inference, prediction and goodness-of-fit assessments. The model is applied to learn how human brain networks vary across individuals with different intelligence scores. Results provide interesting insights on the association between intelligence and brain connectivity, while demonstrating good predictive performance. AVAILABILITY AND IMPLEMENTATION: Source code implemented in R and data are available at https://github.com/wangronglu/BNRR. CONTACT: rl.wang@duke.edu. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

Is cognitive behavioural therapy an effective complement to antidepressants in adolescents? A meta-analysis.

Calati R, Pedrini L, Alighieri S, Alvarez MI, Desideri L, Durante D, Favero F, Iero L, Magnani G, Pericoli V, Polmonari A, Raggini R, Raimondi E, Riboni V, Scaduto MC, Serretti A, De Girolamo G. Is cognitive behavioural therapy an effective complement to antidepressants in adolescents? A meta-analysis. OBJECTIVE: Evidence on effectiveness of combined treatments versus antidepressants alone in adolescents consists on a few studies in both major depressive and anxiety disorders. A meta-analysis of randomised 12-week follow-up studies in which antidepressant treatment was compared to combined treatment consisting of the same antidepressant with cognitive behavioural therapy has been performed. METHODS: Data were entered into the Cochrane Collaboration Review Manager software and were analysed within a random effect framework. A quality assessment has been performed through Jadad Scale. RESULTS: Higher global functioning at the Children's Global Assessment Scale was found in the combined treatment group (p < 0.0001) as well as higher improvement at the Clinical Global Impressions Improvement Scale (p = 0.04). No benefit of combined treatment was found on depressive symptomatology at the Children's Depression Rating Scale - Revised. CONCLUSION: Combined treatment seems to be more effective than antidepressant alone on global functioning and general improvement in adolescents with major depressive and anxiety disorders.