Explore the vast range of titles available.

Motivated by an original financial network dataset, we develop a statistical methodology to study non-negatively weighted temporal networks. We focus on the characterization of how nodes (i.e. financial institutions) concentrate or diversify the weights of their connections (i.e. exposures) among neighbors. The approach takes into account temporal trends and nodes’ random effects. We consider a family of nested models on which we define and validate a model-selection procedure that can identify those models that are relevant for the analysis. We apply the methodology to an original dataset describing the mutual claims and exposures of Austrian financial institutions between 2008 and 2011. This period allows us to study the results in the context of the financial crisis in 2008 as well as the European sovereign debt crisis in 2011. Our results highlight that the network is very heterogeneous with regard to how nodes send, and in particular receive edges. Also, our results show that this heterogeneity does not follow a significant temporal trend, and so it remains approximately stable over the time span considered.

We create a framework to analyze the timing and frequency of instantaneous interactions between pairs of entities. This type of interaction data is especially common nowadays and easily available. Examples of instantaneous interactions include email networks, phone call networks, and some common types of technological and transportation networks. Our framework relies on a novel extension of the latent position network model: we assume that the entities are embedded in a latent Euclidean space and that they move along individual trajectories which are continuous over time. These trajectories are used to characterize the timing and frequency of the pairwise interactions. We discuss an inferential framework where we estimate the individual trajectories from the observed interaction data and propose applications on artificial and real data.

This paper introduces a novel framework to study default dependence and systemic risk in a financial network that evolves over time. We analyse several indicators of risk, and develop a new latent space model to assess the health of key European banks before, during and after the recent financial crises. We propose a new statistical model that permits a latent space visualisation of the financial system. This provides a clear and interpretable model-based summary of the interaction data, and it gives a new perspective on the topology structure of the network. Crucially, the methodology provides a new approach to assess and understand the systemic risk associated with a financial system, and to study how debt may spread between institutions. Our dynamic framework provides an interpretable map that illustrates the default dependencies between institutions, highlighting the possible patterns of contagion and the institutions that may pose systemic threats.

We analyze the temporal bipartite network of the leading Irish companies and their directors from 2003 to 2013, encompassing the end of the Celtic Tiger boom and the ensuing financial crisis in 2008. We focus on the evolution of company interlocks, whereby a company director simultaneously sits on two ormore boards. We develop a statistical model for this dataset by embedding the positions of companies and directors in a latent space. The temporal evolution of the network is modeled through three levels of Markovian dependence: one on the model parameters, one on the companies’ latent positions, and one on the edges themselves. The model is estimated using Bayesian inference. Our analysis reveals that the level of interlocking, as measured by a contraction of the latent space, increased before and during the crisis, reaching a peak in 2009, and has generally stabilized since then.

We derive properties of latent variable models for networks, a broad class of models that includes the widely used latent position models. We characterize several features of interest, with particular focus on the degree distribution, clustering coefficient, average path length, and degree correlations. We introduce the Gaussian latent position model, and derive analytic expressions and asymptotic approximations for its network properties. We pay particular attention to one special case, the Gaussian latent position model with random effects, and show that it can represent the heavy-tailed degree distributions, positive asymptotic clustering coefficients, and small-world behaviors that often occur in observed social networks. Finally, we illustrate the ability of the models to capture important features of real networks through several well-known datasets.

Latent stochastic blockmodels are flexible statistical models that are widely used in social network analysis. In recent years, efforts have been made to extend these models to temporal dynamic networks, whereby the connections between nodes are observed at a number of different times. In this paper, we propose a new Bayesian framework to characterize the construction of connections. We rely on a Markovian property to describe the evolution of nodes' cluster memberships over time. We recast the problem of clustering the nodes of the network into a model-based context, showing that the integrated completed likelihood can be evaluated analytically for a number of likelihood models. Then, we propose a scalable greedy algorithm to maximize this quantity, thereby estimating both the optimal partition and the ideal number of groups in a single inferential framework. Finally, we propose applications of our methodology to both real and artificial datasets.

Latent stochastic block models are flexible statistical models that are widely used in social network analysis. In recent years, efforts have been made to extend these models to temporal dynamic networks, whereby the connections between nodes are observed at a number of different times. In this paper we extend the original stochas-tic block model by using a Markovian property to describe the evolution of nodes' cluster memberships over time. We recast the problem of clustering the nodes of the network into a model-based context, and show that the integrated completed likelihood can be evaluated analytically for a number of likelihood models. Then, we propose a scalable greedy algorithm to maximise this quantity, thereby estimating both the optimal partition and the ideal number of groups in a single inferential framework. Finally we propose applications of our methodology to both real and artificial datasets.

This work is motivated by an original dataset of reported mumps cases across nine regions of England, and focuses on the modeling of temporal dynamics and time-varying dependency patterns between the observed time series. The goal is to discover the possible presence of latent routes of contagion that go beyond the geographical locations of the regions, and instead may be explained through other non directly observable socio-economic factors. We build upon the recent statistics literature and extend the existing count time series network models by adopting a time-varying latent distance network model. This approach can efficiently capture across-series and across-time dependencies, which are both not directly observed from the data. We adopt a Bayesian hierarchical framework and perform parameter estimation using L-BFGS optimization and Hamiltonian Monte Carlo. We demonstrate with several simulation experiments that the model parameters can be accurately estimated under a variety of realistic dependency settings. Our real data application on mumps cases leads to a detailed view of some possible contagion routes. A critical advantage of our methodology is that it permits clear and interpretable visualizations of the complex relations between the time series and how these relations may evolve over time. The geometric nature of the latent embedding provides useful model based summaries. In particular, we show how to extract a measure of contraction of the inferred latent space, which can be interpreted as an overall risk for the escalation of contagion, at each point in time. Ultimately, the results highlight some possible critical transmission pathways and the role of key regions in driving infection dynamics, offering valuable perspectives that may be considered when designing public health strategies.

Motivated by a dataset of burglaries in Chicago, USA, we introduce a novel framework to analyze time series of count data combining common multivariate time series models with latent position network models. This novel methodology allows us to gain a new latent variable perspective on the crime dataset that we consider, allowing us to disentangle and explain the complex patterns exhibited by the data, while providing a natural time series framework that can be used to make future predictions. Our model is underpinned by two well known statistical approaches: a log-linear vector autoregressive model, which is prominent in the literature on multivariate count time series, and a latent projection model, which is a popular latent variable model for networks. The role of the projection model is to characterize the interaction parameters of the vector autoregressive model, thus uncovering the underlying network that is associated with the pairwise relationships between the time series. Estimation and inferential procedures are performed using an optimization algorithm and a Hamiltonian Monte Carlo procedure for efficient Bayesian inference. We also include a simulation study to illustrate the merits of our methodology in recovering consistent parameter estimates, and in making accurate future predictions for the time series. As we demonstrate in our application to the crime dataset, this new methodology can provide very meaningful model-based interpretations of the data, and it can be generalized to other time series contexts and applications.

This paper introduces a new methodology to analyse bipartite and unipartite networks with nonnegative edge values. The proposed approach combines and adapts a number of ideas from the literature on latent variable network models. The resulting framework is a new type of latent position model which exhibits great flexibility, and is able to capture important features that are generally exhibited by observed networks, such as sparsity and heavy tailed degree distributions. A crucial advantage of the proposed method is that the number of latent dimensions is automatically deduced from the data in one single algorithmic framework. In addition, the model attaches a weight to each of the latent dimensions, hence providing a measure of their relative importance. A fast variational Bayesian algorithm is proposed to estimate the parameters of the model. Finally, applications of the proposed methodology are illustrated on both artificial and real datasets, and comparisons with other existing procedures are provided.