The structure of social networks, and people's position within these networks, are important predictors of many individual and group-level outcomes. One type of social networks that is regularly studied are the mutually interdependent relations of friends. This thesis focusses on friendship networks between adolescents in the context of schools. Arguably the most important and consistently found regularities in adolescent friendship networks are i) the tendency of friendships to be mutual, called reciprocity; ii) their tendency to cluster in groups, known as transitivity; and iii) the tendency of friendships to be present between those that are similar to one another, called homophily. Various social theories originating in different disciplines have theoretically proposed and empirically found micro-mechanisms that explain the regular occurrence of these substructures in friendship networks. This thesis introduces a framework of how the relation between these different networks tendencies can be understood. I propose that each of the three network evolution mechanisms can be connected to a type of social situation in which friends interact to form and maintain their friendships. Social situations that are dyadic and only involve two persons are connected to reciprocal friendships. Group-based social situations, on the other hand, are related to transitivity and homophily, where the groups are either defined socially or through common characteristics. Starting from this proposition, I suggest that when two adolescents share one forum for interaction with one another, i.e. they regularly meet within one of the social situations, meeting in additional other situations does not increase the likelihood of a friendship tie existing as much as could be expected from the sum of the effect of meeting in either situation. Consequently, I expect a negative interaction between the different network mechanisms. After a series of empirical analyses that support the outlined reasoning, I use the developed perspective to investigate how the micro-mechanisms contribute differentially to the creation of newly formed friendships and to the maintenance of already existing friendships. Finally, I show how a situational understanding of friendship can be used to differentiate which friendships are most important for social influence and for peer pressure.

The study of complex brain networks, where the brain can be viewed as a system with various interacting regions that produce complex behaviors, has grown tremendously over the past decade. With both an increase in longitudinal study designs, as well as an increased interest in the neurological network changes that occur during the progression of a disease, sophisticated methods for dynamic brain network analysis are needed. We first propose a paradigm for longitudinal brain network analysis over patient cohorts where we adapt the Stochastic Actor Oriented Model (SAOM) framework and model a subject's network over time as observations of a continuous time Markov chain. Network dynamics are represented as being driven by various factors, both endogenous (i.e., network effects) and exogenous, where the latter include mechanisms and relationships conjectured in the literature. We outline an application to the resting-state fMRI network setting, where we draw conclusions at the subject level and then perform a meta-analysis on the model output. As an extension of the models, we next propose an approach based on Hidden Markov Models to incorporate and estimate type I and type II error (i.e., of edge status) in our observed networks. Our model consists of two components: 1) the latent model, which assumes that the true networks evolve according to a Markov process as they did in the original SAOM framework; and 2) the measurement model, which describes the conditional distribution of the observed networks given the true networks. An expectation-maximization algorithm is developed for estimation. Lastly, we focus on the study of percolation - the sudden emergence of a giant connected component in a network. This has become an active area of research, with relevance in clinical neuroscience, and it is of interest to distinguish between different percolation regimes in practice. We propose a method for estimating a percolation model from a given sequence of observed networks with single edge transitions. We outline a Hidden Markov Model approach and EM algorithm for the estimation of the birth and death rates for the edges, as well as the type I and type II error rates. / 2018-07-25T00:00:00Z

The international community routinely implements embargoes in an effort to restrict the flow of small arms and light weapons into politically unstable regions. The effectiveness of sanctions fall into question when reports indicate that weapons continue to pour into embargoed territories. Using stochastic actor-based modeling, the current study investigates how shipment patterns change over time, and how trade patterns evolve in the presence of endogenous influences, such as embargoes, while controlling for corruption levels and national wealth (e.g., gross domestic product). The analysis here indicated that embargoes did have an effect in diverting illicit weapons trade through indirect ties. This was seen highest during the embargo implementation period and post embargo implementation period. The results stand to improve our understanding of this complex illegal global market and the role national control of corruption and gross domestic product play in the enforceability of these sanctions. In the final analysis what was discovered was that embargoes do effect change in the illegal arms trade network. This effect is seen in the form of indirect ties to end user countries. This suggests that improvements to policies and regulation on transshipment points need to be highly scrutinized.