Home > Research > Publications & Outputs > Bootstrapping long memory tests: Some Monte Car...

Research

Associated organisational units

Links

Text available via DOI:

View graph of relations

Bootstrapping long memory tests: Some Monte Carlo results

Research output: Contribution to Journal/Magazine › Journal article › peer-review

Published

Standard

Bootstrapping long memory tests: Some Monte Carlo results. / Izzeldin, Marwan; Murphy, Anthony.
In: Computational Statistics and Data Analysis, Vol. 53, No. 6, 15.04.2009, p. 2325-2334.

Research output: Contribution to Journal/Magazine › Journal article › peer-review

Harvard

Izzeldin, M & Murphy, A 2009, 'Bootstrapping long memory tests: Some Monte Carlo results', Computational Statistics and Data Analysis, vol. 53, no. 6, pp. 2325-2334. https://doi.org/10.1016/j.csda.2008.07.040

APA

Izzeldin, M., & Murphy, A. (2009). Bootstrapping long memory tests: Some Monte Carlo results. Computational Statistics and Data Analysis, 53(6), 2325-2334. https://doi.org/10.1016/j.csda.2008.07.040

Vancouver

Izzeldin M, Murphy A. Bootstrapping long memory tests: Some Monte Carlo results. Computational Statistics and Data Analysis. 2009 Apr 15;53(6):2325-2334. Epub 2008 Aug 5. doi: 10.1016/j.csda.2008.07.040

Author

Izzeldin, Marwan ; Murphy, Anthony. / Bootstrapping long memory tests: Some Monte Carlo results. In: Computational Statistics and Data Analysis. 2009 ; Vol. 53, No. 6. pp. 2325-2334.

Bibtex

@article{b0e2071a63d24743b820d21bfcf5887a,
title = "Bootstrapping long memory tests: Some Monte Carlo results",
abstract = "The bootstrapped size and power properties of six long memory tests the modified R/S, KPSS, V/S, GPH, Robinson's H and the recently proposed Sk tests are investigated. Even in samples of size 100, the moving block bootstrap controls the empirical size of the tests in the DGPs examined. The H test appears to be the most powerful. Moreover, compared with asymptotic tests, the bootstrap tests suffer little loss of power against fractionally integrated processes in samples with 250 or more observations. This is true both for distributions with heavy tails and with stochastic volatility.",
author = "Marwan Izzeldin and Anthony Murphy",
year = "2009",
month = apr,
day = "15",
doi = "10.1016/j.csda.2008.07.040",
language = "English",
volume = "53",
pages = "2325--2334",
journal = "Computational Statistics and Data Analysis",
issn = "0167-9473",
publisher = "Elsevier",
number = "6",

}

RIS

TY - JOUR

T1 - Bootstrapping long memory tests: Some Monte Carlo results

AU - Izzeldin, Marwan

AU - Murphy, Anthony

PY - 2009/4/15

Y1 - 2009/4/15

N2 - The bootstrapped size and power properties of six long memory tests the modified R/S, KPSS, V/S, GPH, Robinson's H and the recently proposed Sk tests are investigated. Even in samples of size 100, the moving block bootstrap controls the empirical size of the tests in the DGPs examined. The H test appears to be the most powerful. Moreover, compared with asymptotic tests, the bootstrap tests suffer little loss of power against fractionally integrated processes in samples with 250 or more observations. This is true both for distributions with heavy tails and with stochastic volatility.

AB - The bootstrapped size and power properties of six long memory tests the modified R/S, KPSS, V/S, GPH, Robinson's H and the recently proposed Sk tests are investigated. Even in samples of size 100, the moving block bootstrap controls the empirical size of the tests in the DGPs examined. The H test appears to be the most powerful. Moreover, compared with asymptotic tests, the bootstrap tests suffer little loss of power against fractionally integrated processes in samples with 250 or more observations. This is true both for distributions with heavy tails and with stochastic volatility.

U2 - 10.1016/j.csda.2008.07.040

DO - 10.1016/j.csda.2008.07.040

M3 - Journal article

VL - 53

SP - 2325

EP - 2334

JO - Computational Statistics and Data Analysis

JF - Computational Statistics and Data Analysis

SN - 0167-9473

IS - 6

ER -