Network Psychometrics with R-Harvard University, USA

Reference textbook:Network Psychometrics with R: A Guide for Behavioral and Social Scientists
Author(s): Adela-Maria Isvoranu

Description:
This textbook is organized into four parts:
I. Network Science in R. The first part provides the basic knowledge needed to understand and work through the remainder of this book. This includes theoretical foundations of network analysis, the programming background and skills necessary to independently carry out the practical exercises and analyses in R, chapters to introduce descriptive analyses of network structures and the fundamentals of constructing and drawing networks using R, as well as basic statistical knowledge about independence and conditional independence as central concepts in the estimation of psychometric network models.
II. Estimating Undirected Network Models. The second part focuses on estimating undirected networks, usually from cross-sectional data. The chapters introduce the reader to the class of statistical models most commonly used to infer network structures (i.e., pairwise Markov random fields), to the multitude of existing estimation methods, network comparison, as well as post-hoc stability and accuracy checks.
III. Network Models for Longitudinal Data. The third part moves the focus from cross-sectional data sets to data sets of one or more people measured repeatedly over time. In addition to discussing ways to estimate (time-varying) network models from longitudinal data, the chapters extensively discuss the difference between within- and between-subject effects and the generalizability of results based on cross-sectional data.
IV. Theory and Causality. The last part concludes the book with network approaches that explicitly go beyond statistically descriptive analysis tools. Two such approaches are discussed. First causal models, which represent causal relations between variables in directed acyclic graphs, and second Ising models, which are based on symmetric interactions between variables.