We study the problem of selecting a regularization parameter in penalized Gaussian graphical models. When goal is to obtain model with good predictive power, cross-validation gold standard. present new estimator Kullback–Leibler loss Graphical models which provides computationally fast alternative cross-validation. The obtained by approximating leave-one-out-cross-validation. Our approach demonstrated on simulated data sets for various types graphs. proposed formula exhibits superior...

Italian wine is increasingly appreciated in new world consumer countries and, particular, Russia where consumers associate its consumption with an lifestyle. In this paper, market value for search attributes measured through the estimation of a hedonic price model using online data from Wine Searcher website and information contained labels wines marketed Russia. Results show premium Piedmont Tuscany, particular non-native varieties Indicazione Geografica Tipica Protected Geographical...

Dynamic gene-regulatory networks are complex since the interaction patterns between their components mean that it is impossible to study parts of network in separation. This holistic character poses a real challenge any type modelling. Graphical models class connect with conditional independence relationships random variables. By interpreting these variables as gene activities and functional non-relatedness, graphical have been used describe networks. Whereas literature has focused on static...

Factorial Gaussian graphical Models (fGGMs) have recently been proposed for inferring dynamic gene regulatory networks from genomic high-throughput data. In the search true relationships amongst vast space of possible networks, these models allow imposition certain restrictions on nature relationships, such as Markov dependencies low order - some entries precision matrix are a priori zeros or equal dependency strengths across time lags assumed to be equal. The is then estimated by...

Global Positioning System (GPS) devices afford the opportunity to collect accurate data on unit movements from temporal and spatial perspectives. With a special focus GPS technology in travel surveys, this paper proposes: (1) two algorithms for pre-processing of order deal with outlier identification missing imputation; (2) clustering approach recover main points interest trajectories; (3) weighted-directed network, which incorporates most relevant characteristics trajectories at an...

We analyse the spatio-temporal distribution of visitors' stops by touristic attractions in Palermo (Italy), using theory stochastic point processes living on linear networks. first propose an inhomogeneous Poisson process model with a separable parametric first-order intensity. account for spatial interaction among points given network, fitting Gibbs mixed effects purely component. This allows us to study and second-order properties pattern, accounting both clustering scale at which they...

Abstract European anchovies and round sardinella play a crucial role, both ecological commercial, in the Mediterranean Sea. In this paper, we investigate distribution of their larval stages by analyzing dataset collected over time (1998–2016) spaced along area Strait Sicily. Environmental factors are also integrated. We employ hierarchical spatio-temporal Bayesian model approximate spatial field Gaussian Markov Random Field to reduce computation effort using Stochastic Partial Differential...

Abstract Dynamic network models describe many important scientific processes, from cell biology and epidemiology to sociology finance. Estimating dynamic networks noisy time series data is a difficult task since the number of components involved in system very large. As result, parameters be estimated typically larger than observations. However, characteristic real life that they are sparse. For example, molecular structure genes make interactions with other highly-structured and, therefore,...

The purpose of this study was to determine the probability soccer players having best genetic background that could increase performance, evaluating polymorphism are considered Performance Enhancing Polymorphism (PEPs) distributed on five genes: PPARα, PPARGC1A, NRF2, ACE e CKMM. Particularly, we investigated how each works directly or through another distinguish elite athletes from non-athletic population. Sixty professional (age 22.5 ± 2.2) and sixty healthy volunteers 21.2± 2.3) were...

We consider latent Gaussian fields for modelling spatial dependence in the context of both point patterns and areal data, providing two different applications. The inhomogeneous Log-Gaussian Cox Process model is specified to describe a seismic sequence occurred Greece, resorting Stochastic Partial Differential Equations. Besag-York-Mollie fitted disease mapping Covid-19 infection North Italy. These models belong class Bayesian hierarchical with whose posterior not available closed form....

Graphical lasso is one of the most used estimators for inferring genetic networks. Despite its diffusion, there are several fields in applied research where limits detection modern measurement technologies make use this estimator theoretically unfounded, even when assumption a multivariate Gaussian distribution satisfied. Typical examples data generated by polymerase chain reactions and flow cytometer. The combination censoring high-dimensionality inference underlying networks from these...

Abstract European anchovies and round Sardinella play a crucial role, both ecological commercial in the Mediterranean Sea.In this paper, we investigate distribution of their larval stages by analyzing dataset collected over time (1998 - 2016) spaced along area Strait Sicily. Environmental factors are also integrated. We employ hierarchical spatio-temporal Bayesian model approximate spatial field Gaussian Markov Random Field (GMRF) to reduce computation effort using Stochastic Partial...