Like other quantitative social scientists, network researchers benefit from pooling information from multiple observed variables to infer underlying (latent) attributes or social processes. Appropriate network data for this task is increasingly available. The inherent dependencies in relational data, however, pose unique challenges. This is especially true for the ascendant tasks of cross-network comparisons and multilevel network analysis. The author draws on item response theory and multilevel (mixed effects) modeling to propose a methodological approach that accounts for these dependencies and allows the analyst to model variation of latent dyadic traits across relations, actors, and groups precisely and parsimoniously. Examples demonstrate the approach’s utility for three important research areas: tie strength in adolescent friendships, group differences in how discussing personal problems relates to tie strength, and the analysis of multiple relations.

像其他定量社会科学家一样，网络研究人员受益于从多个观察到的变量中汇总信息以推断出潜在的（潜在）属性或社会过程。越来越多的适用于此任务的网络数据可用。但是，关系数据中固有的依赖性带来了独特的挑战。对于跨网络比较和多级网络分析的繁重任务尤其如此。作者利用项目响应理论和多级（混合效应）模型来提出一种方法论方法，以解决这些依赖性问题，并使分析人员能够准确而简约地对关系，参与者和群体之间潜在的二进特性的变化进行建模。实例说明了该方法在三个重要研究领域的效用：青少年友谊中的领带强度，