| A social network perspective can bring important insight into the processes that shape human behavior. Longitudinal social network data, measuring relations between individuals over time, has become increasingly common --- as have the methods available to analyze such data. Adding to these methods, a modeling framework utilizing discrete-time multilevel survival analysis is proposed in this dissertation to answer questions about temporal characteristics of friendships, such as the processes leading to friendship dissolution or how long it takes an individual to reciprocate a friendship. While the modeling framework is introduced in terms of understanding friendships, it can be used to understand micro-level dynamics of a social network more generally, such as the duration of reciprocated ties (or undirected relations) and the timing of reciprocal actions. Similar to the model proposed by de Nooy (2011), these models can be fit with standard generalized linear mixed model software, after transforming the data from a network representation to a pair-period dataset. Two main models are introduced as part of the framework, and a simulation study and empirical example are proposed for each. The first empirical example concerns friendship duration in high school students and the second concerns the timing of reciprocal "following" actions on the social network site Twitter. Advantages of the modeling framework are highlighted, and potential limitations and future directions are discussed. |
