利用粗粒化的方法，将1973年至2014年黄金价格日数据转化为由4个字符｛R，r，D，d｝表示的符号序列，以连续4个字符作为一个模态单元，将模态定义为网络的节点，以模态之间的转换定义边的连接，从而构建有向有权的黄金价格波动模态网络，用复杂网络的方法分析了其拓扑特征。研究结果表明，该网络的点权分布很不均匀，部分节点点权很大，是黄金价格波动的“常规模态”；网络具有较短的平均路径长度和较大的聚集系数，表现出小世界网络的特征，模态之间的平均转换距离较短；网络的同配系数为正，核心节点之间具有择优连接性，一些模态之间转换频繁，是黄金价格波动的“核心模态”；少数节点承担了网络中大部分的中介中心性，是黄金价格波动的“中转模态”。%Through coarse graining method,gold price from 1974 to 2014 was transformed into symbolic sequences consisting of four characters{R,r,D,d}. Four continuous symbols are combined into a fluctuation mode,which is defined as the node of the network,and the transitions between these modes were considered as the links of the network. Arrordingly gold price fluctuation network is a directed and weighted network,and the network’s topologic properties were analyzed by complex network method. Research showed that the strength of the nodes is not uniform , some nodes have very large strength,which were considered as the conventional modes. The short path length and large clustering coefficient indicated that the gold price fluctuation network is a small world network,and the average distance between modes is relatively short. The positive assortative coefficients means preferential connectivity between the core nodes of the network,some modes switching frequently between each other,are the core modes of the network. Small number of the nodes undertake most of the network’s betweenness centrality, which are considered as the transit modes of the gold price fluctuation network.
展开▼
