Correlations, hierarchies and networks of the world’s automotive companies

• We analyzed the correlation structures of automotive companies.
• We constructed networks by using hierarchical structure methods.
• The reliabilities of the links between automotive companies have been investigated.
• We used average linkage cluster analysis to observe cluster structures much better.
• We found that some companies are important in the world automotive industry.

We investigate, within the scope of econophysics, the correlations, hierarchies and networks of the world’s automotive companies over the 2003–2010 period by using the concept of a minimal spanning tree (MST) and hierarchical tree (HT). We derive a hierarchical organization and construct the MSTs and HTs for the 2003–2010 period and illustrate how the MSTs and their associated HTs developed over time. These periods are divided into two subperiods, such as 2003–2006 and 2007–2010, in order to test various time-windows and understand the temporal evolution of the correlation structure over time. We perform the bootstrap techniques to investigate a value of the statistical reliability to the links of the MSTs. We also use average linkage cluster analysis (ALCA) to observe the cluster structure more clearly in HTs. From the structural topologies of these trees, we identify different clusters of companies according to their geographical proximity and economic ties. Our results show that some companies are more important within the network, due to a tighter connection with other companies. We also find that these important companies play a predominant role in the world’s automotive industry.