|
幂率分布(Power law distributions),有时也被称为 肥尾分布(heavy-tail distributions)、帕雷托分布(Pareto distributions)、Zipf分布(Zipfian distributions)越来越引起大家的关注。
胡海波先生作了一个很好的综述 [ http://www.cos.name/view.php?id=35&tid=56 ] 。
对于幂率分布的估计问题是个很复杂的问题(..., the empirical detection and characterization of power laws is made difficult by the large fluctuations that occur in the tail of the distribution. In particular, standard methods such as least-squares fitting are known to produce systematically biased estimates of parameters for power-law distributions and should not be used in most circumstances. [ A. Clauset, C.R. Shalizi, and M.E.J. Newman, "Power-law distributions in empirical data" E-print (2007). arXiv:0706.1062 ])。
这里分享其中的幂率拟合和绘图的程序(附件),并给出实际操作的例子。
下载附件解压,在Matlab中进入该文件目录,在命令行输入: pl_demo 。即可得到结果。
有兴趣地可以参考Aaron Clauset 的网站: http://www.santafe.edu/~aaronc/powerlaws/
power law distribution estimation (matlab)
Archiver|手机版|科学网 ( 京ICP备07017567号-12 )
GMT+8, 2024-11-22 21:35
Powered by ScienceNet.cn
Copyright © 2007- 中国科学报社