Session 1: Introduction to network analysis
In this session, we cover how to install R and RStudio, how to subset and manipulate data sets, and how to visualize simple networks using the packages: ggraph and igraph.
Corporate strategy in a network perspective
Course description
This course introduces students to the fundamentals of business strategy through a network perspective, emphasizing how organizations connect and interact with their environments. Students explore key theories on network-based business strategy, gain hands-on experience with conducting network analysis using the R programming language, and apply these insights to real-world cases. The course integrates theoretical frameworks, methodological tools, and practical applications, enabling students to analyze how internal and external networks impact organizational strategy.
Teaching methods include lectures, practical exercises, and diverse learning materials such as readings, podcasts, and videos. Students will work with real-world data, including Danish business networks, and apply their learning through case analyses and exercises. Assessment is project-based, requiring students to conduct an independent network analysis, combining theory and method to address practical organizational challenges. By the end of the course, students will have developed analytical skills and a nuanced understanding of how networks influence business strategy. You can read more about the course here.
Sessions
Session 2: Network components, density and paths
In this session, you will learn how to select components of a network, and how to calculate network density, shortest paths, and the diameter of a network.
Session 3: Collecting network data
In this session, You will learn how to subset the data set den17 by tags, and how to collect network data from Orbis. Last, we cover how to visualize a two-mode network and to add network attributes
Session 4 - Analysis of node centrality measures
The focus of this session is on node centrality measures. We will cover several metrics including degree centrality, betweenness centrality, closeness and eigenvector centrality.
Session 5 - Brokerage and assortativity
This session will focus on two topics. First, we will look at Burts constraint as a measure for brokerage. Second, we will cover assortativity as a measure of homophily in a network.
Session 6 - Communities and cliques
This session will focus on the Louvain community detection algorithm and the visualization of communities in a network. We will also discover what cliques are, and how they differ from communities.
Session 7 - Visualization
This session will focus advanced network visualizations with the ggraph() package. This will be the last session of this course.