2006
DOI: 10.1027/1614-2241.02.4.135
|View full text |Cite
|
Sign up to set email alerts
|

Sample Size and Accuracy of Estimation of the Fractional Differencing Parameter

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

0
5
0

Year Published

2009
2009
2020
2020

Publication Types

Select...
4

Relationship

1
3

Authors

Journals

citations
Cited by 4 publications
(5 citation statements)
references
References 0 publications
0
5
0
Order By: Relevance
“…Using the lag-1 autocorrelation function (ACF), it is possible to determine the relationship between successive tetragram sequences and identify whether dependency lasts beyond the tetragram set (Bailey & Thompson, 2006 ). ACFs that rapidly decay, fluctuating around zero, are indicative of a completely random, or memoryless process (Stadnytska & Werner, 2006 ), i.e. a Markovian process (Reynolds, 2010 ).…”
Section: Methodsmentioning
confidence: 99%
“…Using the lag-1 autocorrelation function (ACF), it is possible to determine the relationship between successive tetragram sequences and identify whether dependency lasts beyond the tetragram set (Bailey & Thompson, 2006 ). ACFs that rapidly decay, fluctuating around zero, are indicative of a completely random, or memoryless process (Stadnytska & Werner, 2006 ), i.e. a Markovian process (Reynolds, 2010 ).…”
Section: Methodsmentioning
confidence: 99%
“…In addition, DFA has been evaluated as reliable and robust (Eke et al, 2002), does not require the arbitrary setting of parameters, and is not susceptible to most statistical artifacts, but it can falsely classify certain types of signals as fractal (see Rangarajan & Ding, 2000, for details). Stadnytska and Werner (2006) demonstrated that the conditional sum of squares (CSS) procedure, a computationally convenient technique available in current versions of SAS for Windows, and the exact maximum likelihood (EML) approach of Sowell (1992) provide very accurate estimates of d for sample sizes of 1,000-1,600 observations. Taqqu and Teverovsky (1998) and Taqqu, Teverovsky, and Willinger (1995) described and evaluated various methods for estimating d and H for models with different innovation structures.…”
Section: Modeling Long-range Dependencementioning
confidence: 99%
“…Simulation studies on fractal analysis have demonstrated that the performance of the various methods depends very much on aspects such as the complexity of the underlying process or the parameterizations (Stadnytska and Werner, 2006). As a result, comprehensive strategies are required to Granger and Joyeux (1980) and Hosking (1981Hosking ( , 1984.…”
Section: Fractal Analysis Approachmentioning
confidence: 99%
“…Its main disadvantages are that it is valid only for stationary series and needs a sufficiently large sample size for acceptable measurement accuracy (Stadnitski, 2012;Stadnytska and Werner, 2006). Its validness only for stationary series can lead to situations where nonstationary processes are classified as having long memory.…”
Section: Fractal Parameter Estimation For Conditional Meanmentioning
confidence: 99%