Search for: All records

One of the first steps in applications of statistical network analysis is frequently to produce summary charts of important features of the network. Many of these features take the form of sequences of graph statistics counting the number of realized events in the network, examples of which are degree distributions, edgewise shared partner distributions, and more. We provide conditions under which the empirical distributions of sequences of graph statistics are consistent in the L-infinity-norm in settings where edges in the network are dependent. We accomplish this task by deriving concentration inequalities that bound probabilities of deviations of graph statistics from the expected value under weak dependence conditions. We apply our concentration inequalities to empirical distributions of sequences of graph statistics and derive non-asymptotic bounds on the L-infinity-error which hold with high probability. Our non-asymptotic results are then extended to demonstrate uniform convergence almost surely in selected examples. We illustrate theoretical results through examples, simulation studies, and an application. 

Reciprocity, or the stochastic tendency for actors to form mutual relationships, is an essential characteristic of directed network data. Existing latent space approaches to modelling directed networks are severely limited by the assumption that reciprocity is homogeneous across the network. In this work, we introduce a new latent space model for directed networks that can model heterogeneous reciprocity patterns that arise from the actors' latent distances. Furthermore, existing conditionally edge‐independent latent space models are nested within the proposed model class, which allows for meaningful model comparisons. We introduce a Bayesian inference procedure to infer the model parameters using Hamiltonian Monte Carlo. Lastly, we use the proposed method to infer different reciprocity patterns in an advice network among lawyers, an information‐sharing network between employees at a manufacturing company and a friendship network between high school students. 

In this work, we explore the extent to which the spectrum of the graph Laplacian can characterize the probability distribution of random graphs for the purpose of model evaluation and model selection for network data applications. Network data, often represented as a graph, consist of a set of pairwise observations between elements of a population of interests. The statistical network analysis literature has developed many different classes of network data models, with notable model classes including stochastic block models, latent node position models, and exponential families of random graph models. We develop a novel methodology which exploits the information contained in the spectrum of the graph Laplacian to predict the data-generating model from a set of candidate models. Through simulation studies, we explore the extent to which network data models can be differentiated by the spectrum of the graph Laplacian. We demonstrate the potential of our method through two applications to well-studied network data sets and validate our findings against existing analyses in the statistical network analysis literature. 

At 18:08 on August 4, 2020, a large explosion occurred at Hangar 12 in the Port of Beirut. The size of the explosion was equivalent to that of an earthquake with a local magnitude (ML) of 3.3 according to the USGS. As one of the largest nonmilitary explosions to ever impact an urban region, this event provides unprecedented opportunities to document explosion impacts on urban infrastructure. To facilitate this data collection, the Geotechnical Extreme Events Reconnaissance (GEER) Association coordinated a multiagency response directed toward the collection of perishable data of engineering interest. Two main categories of infrastructure systems were impacted: the Port of Beirut and the Beirut building stock. Within the Port, the explosion triggered a quay wall failure and flow slide, and strongly impacted grain silo structures that were in close proximity to Hangar 12. Within the city, historical masonry structures, older reinforced concrete structures, and modern high-rise structures were impacted. Through a combination of in-person inspections and street-view surveys, we collected data on structural performance (including damage to load-bearing elements) and building façades. Performance levels were classified according to procedures applied following earthquakes (for structural performance) and newly proposed procedures (for façades). We describe spatial distributions of these damage types and dependencies on source distance and location-to-explosion direction. We demonstrate that physical damages correlated with damage proxy maps produced by the Jet Propulsion Laboratory and the Earth Observatory of Singapore based on Copernicus Sentinel-1 satellite synthetic aperture radar data, with a stronger correlation with structural damage than with façade damage. 

The Samos Island (Aegean Sea) Earthquake occurred on 30 October 2020. It produced a tsunami that impacted coastal communities, ground shaking that was locally amplified in some areas and that led to collapse of structures with 118 fatalities in both Greece and Turkey, and wide-ranging geotechnical effects including rockfalls, landsliding, and liquefaction. As a result of the global COVID-19 pandemic, the reconnaissance of this event did not involve the deployment of international teams, as would be typical for an event of this size. Instead, following initial deployments of separate Greek and Turkish teams, the reconnaissance and documentation efforts were managed in a coordinated manner with the assistance of international partners. This coordination ultimately produced a multi-agency joint report published on the 2-month anniversary of the earthquake, and this special issue. This paper provides an overview of the reconnaissance activities undertaken to document the effects of this important event and summarizes key lessons spanning topic areas from seismology to emergency response. 

Statistical inference for exponential-family models of random graphs with dependent edges is challenging. We stress the importance of additional structure and show that additional structure facilitates statistical inference. A simple example of a random graph with additional structure is a random graph with neighborhoods and local dependence within neighborhoods. We develop the first concentration and consistency results for maximum likelihood and M-estimators of a wide range of canonical and curved exponentialfamily models of random graphs with local dependence. All results are nonasymptotic and applicable to random graphs with finite populations of nodes, although asymptotic consistency results can be obtained as well. In addition, we show that additional structure can facilitate subgraph-to-graph estimation, and present concentration results for subgraph-to-graph estimators. As an application, we consider popular curved exponential-family models of random graphs, with local dependence induced by transitivity and parameter vectors whose dimensions depend on the number of nodes. 

Abstract On October 30, 2020 14:51 (UTC), a moment magnitude (M w ) of 7.0 (USGS, EMSC) earthquake occurred in the Aegean Sea north of the island of Samos, Greece. Turkish and Hellenic geotechnical reconnaissance teams were deployed immediately after the event and their findings are documented herein. The predominantly observed failure mechanism was that of earthquake-induced liquefaction and its associated impacts. Such failures are presented and discussed together with a preliminary assessment of the performance of building foundations, slopes and deep excavations, retaining structures and quay walls. On the Anatolian side (Turkey), and with the exception of the Izmir-Bayrakli region where significant site effects were observed, no major geotechnical effects were observed in the form of foundation failures, surface manifestation of liquefaction and lateral soil spreading, rock falls/landslides, failures of deep excavations, retaining structures, quay walls, and subway tunnels. In Samos (Greece), evidence of liquefaction, lateral spreading and damage to quay walls in ports were observed on the northern side of the island. Despite the proximity to the fault (about 10 km), the amplitude and the duration of shaking, the associated liquefaction phenomena were not pervasive. It is further unclear whether the damage to quay walls was due to liquefaction of the underlying soil, or merely due to the inertia of those structures, in conjunction with the presence of soft (yet not necessarily liquefied) foundation soil. A number of rockfalls/landslides were observed but the relevant phenomena were not particularly severe. Similar to the Anatolian side, no failures of engineered retaining structures and major infrastructure such as dams, bridges, viaducts, tunnels were observed in the island of Samos which can be mostly attributed to the lack of such infrastructure.