Some Remarks on Unexpected Scaling Exponents Matthew Roughan School of Mathematical Science University of Adelaide SA 5005, Australia Darryl Veitch Department of E&E Engineering The University of Melbourne Victoria 3010, Australia matthew.roughan@adelaide.edu.au d.veitch@ee.unimelb.edu.au This article is an editorial note submitted to CCR. It has NOT been peer reviewed. Authors take full responsibility for this article s technical content. Comments can be posted through CCR Online. Categories and Subject Descriptors G.3 [PROBABILITY AND STATISTICS]: Stochastic processes General Terms Traf c Models scales. In each case, correct estimates of the Hurst parameter can be made using the LD if the analysis is made over the appropriate range of scales. Given the space restrictions of this note, we will give an intuitive description here, and direct readers to [6, 9] for a more detailed mathematical treatment. Keywords Fractal Renewal Process, Long-range dependence, wavelet estimator, Hurst parameter, sampling, discontinuities. 2. TWO PHENOMENA A process is long-range dependent when its autocorrelation does not decay quickly in time. That is, points separated by long intervals can still be signi cantly correlated. LRD has been observed in many network data sets, and is of enduring interest as its presence is robust, and it often
/lp/association-for-computing-machinery/some-remarks-on-unexpected-scaling-exponents-0mv8pGbGpl