Nonstationarity of the mean and the hurst Phenomenon
- 1 February 1978
- journal article
- Published by American Geophysical Union (AGU) in Water Resources Research
- Vol. 14 (1) , 135-143
- https://doi.org/10.1029/wr014i001p00135
Abstract
Hurst (1957), Klemeš (1974, 1975), and Potter (1975, 1976a, 1976b) show that nonstationarity of the mean provides a possible explanation of the so‐called Hurst phenomenon; O'Connell (1971) and Wallis and O'Connell (1973 )show that this phenomenon can also be explained with a mixed autoregressive‐ moving average (Arma) process. These two alternate explanations can be quite similar; in fact, both Hurst's (1957) model and a model suggested by Klemeš (1974) and Potter (1975) have correlation structure identical to an Arma (1,1) process. A mixture model for shifting levels is proposed, and it is shown that the models of Hurst and Klemeš and Potter are special cases.This publication has 8 references indexed in Scilit:
- The asymptotic distribution of the range and other functions of partial sums of stationary processesWater Resources Research, 1976
- Evidence for nonstationarity as a physical explanation of the Hurst PhenomenonWater Resources Research, 1976
- Reply [to “Comment on ‘The Hurst Phenomenon: A puzzle?’ by V. Klemeš”]Water Resources Research, 1975
- Comment on ‘The Hurst Phenomenon: A puzzle?’ by V. KlemešWater Resources Research, 1975
- The Hurst Phenomenon: A puzzle?Water Resources Research, 1974
- FIRM RESERVOIR YIELD—HOW RELIABLE ARE HISTORIC HYDROLOGICAL RECORDS?Hydrological Sciences Bulletin, 1973
- A Suggested Statistical Model of some Time Series which occur in NatureNature, 1957
- Long-Term Storage Capacity of ReservoirsTransactions of the American Society of Civil Engineers, 1951