| V. Klemes, "The Hurst phenomenon: A Puzzle?," Water Resources Research 10, pp. 675--688, 1974. |
....conclusions and build wrong models. In order to avoid such pitfalls we address this problem in this paper and give analytical and simulation investigations of the effects of different non stationarity phenomena in the data. The issue is not new and also addressed in the hydrology literature (e.g. [9]) after the application of LRD processes in the modeling of natural storage systems by Hurst [7] Mandelbrot and others [11] However, after the invent and first application of LRD processes in the teletraffic research a number of papers have been published just by blind application of some LRD ....
.... Local stationarity with traditional models can also be used to capture the observed characteristics [17] An alternative but rather difficult approach is to use nonstationary models,e.g. 5] Some authors argue that this topic is somewhat philosophical from an application point of view [6] [9]. Indeed, if the modeling alternative can provide useful practical tools to dimension our networks then this can be a non questionable proof for a proposed model. However, if more alternatives can work then we may prefer the parsimonious one which is a nice feature of fractal models. We believe ....
V. Klemes, "The Hurst phenomenon: A Puzzle?," Water Resources Research 10, pp. 675--688, 1974.
....for example, that the otherwise masterful surveys by Robinson (1994a) Beran (1994) and Baillie (1996) don t so much as mention the issue. The possibility of confusing long memory and structural change has of course arisen occasionally, in a number of literatures including applied hydrology (Klemes, 1974), econometrics (Hidalgo and Robinson, 1996, Lobato and Savin, 1997) and mathematical statistics (Bhattacharya, Gupta and Waymire, 1983, Knsch, 1986, Teverovsky and Taqqu, 1997) but those warnings have had little impact. We can only speculate as to the reasons, but they are probably linked to the ....
....Lobato and Savin, 1997) and mathematical statistics (Bhattacharya, Gupta and Waymire, 1983, Knsch, 1986, Teverovsky and Taqqu, 1997) but those warnings have had little impact. We can only speculate as to the reasons, but they are probably linked to the facts that (1) simulation examples such as Klemes (1974) are interesting, but they offer neither theoretical justification nor Monte Carlo evidence, and (2) theoretical work such as Bhattacharya, Gupta and Waymire (1983) often seems highly abstract and lacking in 2intuition. In this paper we provide both rigorous theory and Monte Carlo evidence to ....
Klemes, V. (1974), "The Hurst Phenomenon: A Puzzle?," Water Resources Research, 10, 675688.
.... in the 1970s, after Mandelbrot and his co workers had introduced long range dependent processes to model natural storage systems (e.g. water flows in rivers) For an enlightening exchange of arguments between the traditional school of modeling and the Mandelbrot school, see the article by Klemes [10]. In particular, Klemes reminds the reader that stationarity can be formulated with uncompromising (mathematical) strictness, and yet there is probably not a single historical time series of which mathematicians can tell with certainty whether it is stationary or not. He then goes on stating ....
V. Klemes, "The Hurst Phenomenon: A Puzzle?", Water Resources Research 10, pp. 675--688, 1974.
No context found.
Klemes, V. (1974): "The Hurst Phenomenon: A Puzzle?", Water Resources Research, 10, 675-688.
No context found.
V. Klemes, "The Hurst Phenomenon: A Puzzle?", Water Resources Research 10, 675-688, 1974.
Online articles have much greater impact More about CiteSeer.IST Add search form to your site Submit documents Feedback
CiteSeer.IST - Copyright Penn State and NEC