Textbook in PDF format

This book provides readers with a comprehensive guide to designing rigorous and effective network science tools using the statistical software platforms Stata, R, and Python. Network science offers a means to understand and analyze complex systems that involve various types of relationships. This text bridges the gap between theoretical understanding and practical application, making network science more accessible to a wide range of users. It presents the statistical models pertaining to individual network techniques, followed by empirical applications that use both built-in and user-written packages, and reveals the mathematical and statistical foundations of each model, along with demonstrations involving calculations and step-by-step code implementation. In addition, each chapter is complemented by a case study that illustrates one of the several techniques discussed. The introductory chapter serves as a roadmap for readers, providing an initial understanding of network science and guidance on the required packages, the second chapter focuses on the main concepts related to network properties. The next two chapters present the primary definitions and concepts in network science and various classes of graphs observed in real contexts. The final chapter explores the main social network models, including the family of exponential random graph models. Each chapter includes real-world data applications from the social sciences, using at least one of the platforms Stata, R, and Python, providing a more comprehensive understanding of the availability of network science methods across different software platforms. The underlying computer code and data sets are available online. The networkX Python package will be covered in this book. NetworkX is a Python library designed specifically for the creation, manipulation, and study of complex networks. If networkX is not currently installed on your machine, you must first install it. NetworkX uses Python’s rich and expanding ecosystem of packages to provide additional capabilities like numerical linear algebra and graphics, such as Pandas, NumPy, and Matplotlib. In this book, all codes are generated with Spyder from Anaconda Navigator, a free Python distribution that comes with all the tools you will need to run the codes. Python is mostly used to investigate networks from a statistical mechanics perspective, due to its versatility and extensive range of libraries tailored for scientific computing. Additionally, Python’s libraries, such as NetworkX, offer robust tools for modeling and analyzing complex networks, enabling researchers to delve into statistical mechanics principles like percolation theory and Markov processes. Moreover, some integrations with other scientific libraries like NumPy, SciPy, and Seaborn facilitate efficient numerical computations and Machine Learning algorithms essential for simulating and analyzing network dynamics. R is a statistical computing and graphics environment that is free to use. For Network Science research, it offers a wide range of statistical and graphical techniques. All of the offered functions may be executed via RStudio, which is an integrated development environment (IDE) for the R programming language. It runs on all platforms: Windows, Mac OS X, and Linux. The igraph library provides useful options for descriptive network analysis and visualization in RStudio. install.packages(“igraph”) is the command you use to install the latest version of igraph for RStudio. There are many other excellent packages that are not part of the igraph, because they solve problems in a different domain, or are designed with a different set of underlying principles. As we tackle more network data projects with RStudio, we will also use complementary packages depending on the analysis domain, such as statnet, netsis, sna, readr, readxl, haven, Matrix, dplyr, tidytext, janeaustenr, ggraph. The book will appeal to graduate students, researchers and data scientists, mainly from the social sciences, who seek theoretical and applied tools to implement network science techniques in their work.

• Provides theoretical, methodological and applied tools for network science
• Presents applications and case studies using Stata, R, and Python
• Serves as a valuable resource for students, researchers and data scientists Prefsce Introduction Network Science: Concepts and Definitions Network Metrics Theoretical Models of Networks Statistical Social Network Models