1998
DOI: 10.1111/1467-9892.00117
|View full text |Cite
|
Sign up to set email alerts
|

Change‐Point Estimation of Fractionally Integrated Processes

Abstract: In this paper we analyze the least-squares estimator of the change point for fractionally integrated processes with fractionally differencing parameter À0X5 , d , 0X5. When there is a one-time change, we show that the least-squares estimator is consistent and that the rate of convergence depends on d. When there is no change, we ®nd that the least-squares estimator converges in probability to the set f0, 1g for À0X5 , d < 0 but is likely to suggest a spurious change for 0 , d , 0X5. Simulations are also used t… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

0
33
0

Year Published

2004
2004
2019
2019

Publication Types

Select...
6
4

Relationship

0
10

Authors

Journals

citations
Cited by 62 publications
(33 citation statements)
references
References 12 publications
0
33
0
Order By: Relevance
“…Beran and Terrin, 1996;Bos et al, 2001;Ohanissian et al, 2008). Also in the I(d) context, many authors consider the possibility of mean shifts and split deterministic terms (Hidalgo and Robinson, 1996;Kuan and Hsu, 1998;Kramer and Sibbertsen, 2002) but they impose the same degree of integration across regimes. In this section we will implement a procedure developed by Gil-Alana (2008) in the context of fractional integration with structural breaks at unknown periods of time, allowing for different degrees of integration across subsamples.…”
Section: Additional Issuesmentioning
confidence: 99%
“…Beran and Terrin, 1996;Bos et al, 2001;Ohanissian et al, 2008). Also in the I(d) context, many authors consider the possibility of mean shifts and split deterministic terms (Hidalgo and Robinson, 1996;Kuan and Hsu, 1998;Kramer and Sibbertsen, 2002) but they impose the same degree of integration across regimes. In this section we will implement a procedure developed by Gil-Alana (2008) in the context of fractional integration with structural breaks at unknown periods of time, allowing for different degrees of integration across subsamples.…”
Section: Additional Issuesmentioning
confidence: 99%
“…A series of contributions have proposed testing procedures for evaluating changing parameters in presence of long memory. Kuan and Hsu (1998) analyze the least-squares estimator of the change point for fractionally integrated processes with fractional differencing parameter −0:5 < d < 0:5: When there is a one-time change, the authors show that the least-squares estimator is consistent and that the rate of convergence depends on d. When there is no change, they find that the least-squares estimator converges in probability to the set {0; 1} for−0:5 < d < 0 but is likely to suggest a spurious change for 0 < d < 0:5. Simulations are also used to illustrate the asymptotic analysis.…”
Section: Long Memory and Breaks In Time Seriesmentioning
confidence: 99%
“…For example, Bhattacharya et al (1983), Teverovsky and Taqqu (1997), Diebold and Inoue (2001), Granger and Hyung (2004) and Ohanissian et al (2008) among others show that fractional integration may be a spurious phenomenon caused by the existence of breaks in short-memory I(0) contexts. Similarly, Kuan and Hsu (1998), Wright (1998) and Kr€ amer and Sibbertsen (2002) showed that evidence of structural change might be spurious since most commonly employed tests for breaks are biased towards an over-rejection of the null of no change when the process exhibits long memory. In this paper we employ a recent technique developed by Gil-Alana (2008) that allows for breaks at unknown periods of time with different orders of integration across subsamples.…”
Section: Resultsmentioning
confidence: 99%