International Conference on Engineering and Business Management (EBM 2010 PAPERBACK)

Chengdu,China,China,3.24-3.26,2010

ISBN: 978-1-935068-05-1 Scientific Research Publishing, USA

Paperback 6066pp Pub. Date: March 2010

Category: Engineering

Price: $280

Title: Correlation Analysis of SSE 50 Components Within Different Trend Channels
Source: International Conference on Engineering and Business Management (EBM 2010 PAPERBACK) (pp 4031-4035)
Author(s): Li MA, International School of Software, Wuhan University, Wuhan, China, 430079
H. J. CAI, International School of Software, Wuhan University, Wuhan, China, 430079
Abstract: Abstract: This paper uses the ultrametric clustering method to explore the correlation of SSE 50 components in time series. The time period from 2005 to 2009 is divided into 4 stages, namely up-trend channel, top-forming channel, down-trend channel, and bottom-forming channel, according to the wave theories. For each stage, the correlation distance matrix of the stocks in SSE50 Index is calculated, and Minimal Spanning Tree (MST) which shows the characteristics of ultrametric clustering is presented. It is shown from MST diagrams that industry groups, capital structures, the regionality and enterprise performances determine the characteristics of topological relation among these 50 stocks in each stage. The factors mentioned above are stable to some extend, and the characteristics have changed not that much overall. The ultrametric clustering is effective in stock classification and can be used as reference for institution and retail investors.
Free SCIRP Newsletters
Copyright © 2006-2024 Scientific Research Publishing Inc. All Rights Reserved.
Top