With a rise in the amount of network data comes increased need for flexible and interpretable network models. Exponential-family random graph models (ERGM) are widely used to analyze small- to medium-sized networks, but suffer from model degeneracy which detracts from their application. In Part I of this dissertation we address this problem by developing novel statistics for ERGM. We focus on the modeling of transitivity in networks as it is a key feature of many real-world networks, but most attempts to account for it within ERGM have induced model degeneracy. The statistics we propose combine the strategies of the transformed statistics proposed by Horvat et al. (2015) and the regularized statistics proposed by Fellows (2012b). They include statistics to capture transitivity, clustering, and a new class of moment statistics to improve goodness of fit. We characterize our newly introduced statistics along with those of Horvat et al. (2015) and Fellows (2012a) using recent theoretical developments regarding ERGM degeneracy. We also compare them theoretically and in practice to the geometrically weighted statistics of Snijders et al. (2006) that are currently the most commonly used to model transitivity in ERGM.

In Part II of this dissertation we develop models to rate and rank items based on network data, and demonstrate many advantageous properties of these models. The impetus for this work came from research on ranking statistics journals by Varin et al. (2016). They present a quasi-Stigler model that is a great improvement over the commonly used but statistically indefensible Impact Factor, especially in the quantification of ratings uncertainty. However, the quasi-Stigler model does not fully leverage the network structure of the data and underestimates uncertainty. In addition to applying latent space models to the network rating problem, we identify a fast computational method for fitting the models. We also develop a new latent network model that leverages the symmetric and asymmetric patterns in directed relational data. This model has many potential applications beyond item rating.

Transportation planners in cities across the country are trying to increase bicycling to achieve mobility, public health, and environmental goals. For bicycling to become a mainstream travel mode, however, riders must feel safe and comfortable in the bicycling environment. Thus, cities are changing transportation infrastructure to provide more bicycling-friendly streets.

It remains unclear exactly how much infrastructure change is needed to make potential cyclists feel comfortable enough to bicycle regularly. To better understand what road characteristics contribute to more comfortable bicycling, researchers at UC Davis surveyed 3,089 travelers to the UC Davis campus to measure perceived comfort of bicycling in different road environments using video recordings of 25 urban and rural roads from the San Francisco Bay Area. This policy brief summarizes findings from that research, which provide guidance for communities aiming to increase bicycling.

View the NCST Project Webpage

In this study, researchers use survey data to analyze bicycling comfort and its relationship with socio-demographics, bicycling attitudes, and bicycling behavior. An existing survey of students, faculty, and staff at UC Davis (n=3089) who rated video clips of bicycling environments based on their perceived comfort as a part of the UC Davis annual Campus Travel Survey (CTS) is used. The video clips come from a variety of urban and semi-rural roads (designated California state highways) around the San Francisco Bay Area where bicycling rates vary. Results indicate considerable effects of socio-demographics and attitudes on absolute video ratings, but relative agreement about which videos are most comfortable and uncomfortable across population segments. In addition, presence of bike infrastructure and low speed roads are the strongest video factors generating more comfortable ratings. However, the results suggest that even the best designed on-road bike facilities are unlikely to provide a comfortable bicycling environment for those without a predisposition to bicycle. This suggests that protected and separated bike facilities may be required for many people to consider bicycling. Nonetheless, the results provide guidance for improving roads with on-street bike facilities where protected or separated facilities may not be suitable.

View the NCST Project Webpage