Robustness of the rescaled range R/S in the measurement of noncyclic long run statistical dependence
- 1 October 1969
- journal article
- Published by American Geophysical Union (AGU) in Water Resources Research
- Vol. 5 (5) , 967-988
- https://doi.org/10.1029/wr005i005p00967
Abstract
The rescaled range R(t, s) / S(t, s) is shown by extensive computer simulation to be a very robust statistic for testing the presence of noncyclic long run statistical dependence in records and, in cases where such dependence is present, for estimating its intensity. The processes examined in this paper extend to extraordinarily non‐Gaussian processes with huge skewness and/or kurtosis (that is, third and/or fourth moments).This publication has 14 references indexed in Scilit:
- Some long‐run properties of geophysical recordsWater Resources Research, 1969
- Computer Experiments With Fractional Gaussian Noises: Part 1, Averages and VariancesWater Resources Research, 1969
- Long-Run Linearity, Locally Gaussian Process, H-Spectra and Infinite VariancesInternational Economic Review, 1969
- Fractional Brownian Motions, Fractional Noises and ApplicationsSIAM Review, 1968
- How Long Is the Coast of Britain? Statistical Self-Similarity and Fractional DimensionScience, 1967
- On the range of cumulative sumsAnnals of the Institute of Statistical Mathematics, 1964
- New Methods in Statistical EconomicsJournal of Political Economy, 1963
- The Variation of Certain Speculative PricesThe Journal of Business, 1963
- ON THE RANGE OF PARTIAL SUMS OF A FINITE NUMBER OF INDEPENDENT NORMAL VARIATESBiometrika, 1953
- The Asymptotic Distribution of the Range of Sums of Independent Random VariablesThe Annals of Mathematical Statistics, 1951