Choi Sun-Yong
Department of Financial Mathematics, Gachon University, Gyeoggi 13120, Republic of Korea.
Heliyon. 2023 Sep 6;9(9):e19726. doi: 10.1016/j.heliyon.2023.e19726. eCollection 2023 Sep.
We investigate the topology of sectoral returns in the US stock market using minimum spanning tree (MST) analysis. We examine four distinct time periods: the full period, the Global Financial Crisis (GFC), the COVID-19 pandemic, and the Russia-Ukraine war period. By comparing the static results across these periods, we identify differences in the network structure. Additionally, a rolling window analysis is conducted to explore the time-varying nature of the MST. We employ a TVP-VAR based connectedness framework to ensure a robust analysis of the sectoral return linkages. Our main findings are summarized as follows: First, the structure of the MST varies in different periods, with distinct crisis period structures. During the GFC, the industrial sector dominated clustering, whereas COVID-19 affected the financial, IT, and industrial sectors. The Russia-Ukraine war period showed clustering centered on materials, except in the industrial sector. These varying structures may explain the different characteristics of each crisis. Second, both static and rolling window analyses highlight the significance of the industrial sector in the US stock market. Third, the utilities sector exhibits the lowest centrality measures, indicating its minimal importance and lack of relationships with other industries. These findings provide valuable insights into the interrelationships among industries in the US stock market. Market participants can leverage these findings to enhance their understanding and improve their portfolio management. By utilizing this information, investors can develop optimal diversification strategies to maximize returns and minimize risk.
我们使用最小生成树(MST)分析来研究美国股票市场中行业回报的拓扑结构。我们考察了四个不同的时间段:整个时期、全球金融危机(GFC)、新冠疫情时期以及俄乌战争时期。通过比较这些时期的静态结果,我们识别出网络结构的差异。此外,还进行了滚动窗口分析以探究MST的时变性质。我们采用基于时变参数向量自回归(TVP-VAR)的连通性框架来确保对行业回报联系进行稳健的分析。我们的主要发现总结如下:第一,MST的结构在不同时期有所不同,具有不同的危机时期结构。在全球金融危机期间,工业部门主导聚类,而新冠疫情影响了金融、信息技术和工业部门。俄乌战争时期的聚类以材料行业为中心,工业部门除外。这些不同的结构可能解释了每次危机的不同特征。第二,静态和滚动窗口分析均突出了工业部门在美国股票市场中的重要性。第三,公用事业部门的中心性指标最低,表明其重要性最小且与其他行业的关系较少。这些发现为美国股票市场中各行业之间的相互关系提供了有价值的见解。市场参与者可以利用这些发现来增强他们的理解并改善他们的投资组合管理。通过利用这些信息,投资者可以制定最优的多元化策略以实现回报最大化和风险最小化。