Sub-dominant ultrametric hierarchical structures of NYSE 100 stocks

In stock networks analysis sub-dominant ultrametric (SDU) is used to understand the economic hierarchical clustering among stocks. There are two different approaches to obtain SDU. First, which is usually used in stock networks analysis, is to construct a minimal spanning tree (MST) by using Kruskal´s algorithm or Prim´s and then derive the SDU. The second approach is to construct directly the SDU such as given by Johnson´s algorithm. In this paper we examine the performance of the first approach based on Kruskal´s algorithm and the second approach based on Johnson´s algorithm in terms of computational complexity and their running times by using NYSE 100 stocks daily prices data.