# zbMATH — the first resource for mathematics

Wavelets and estimation of long memory in nonstationary models: does anything beat the exact local Whittle estimator? (English) Zbl 1422.62364
Summary: In this article, we analyze the performance of five estimation methods for the long memory parameter $$d$$. The goal of our article is to construct a wavelet estimate for the fractional differencing parameter in nonstationary long memory processes that dominate the well-known estimate of K. Shimotsu and P. C. B. Phillips [Ann. Stat. 33, No. 4, 1890–1933 (2005; Zbl 1081.62069)]. The simulation results show that the wavelet estimation method of J. Lee [Econ. Lett. 87, No. 2, 207–210 (2005; Zbl 1254.91673)] with several tapering techniques performs better under most cases in nonstationary long memory. The comparison is based on the empirical root mean squared error of each estimate.
##### MSC:
 62P20 Applications of statistics to economics 91B84 Economic time series analysis
##### Keywords:
long memory; nonstationary models; wavelets
Full Text:
##### References:
 [1] Abadir K. M., 2007 141 pp 1353– [2] Andrews D., 2003 71 pp 675– [3] Alekseev V., 1996 41 pp 137– [4] Beran J., 1994 [5] Boubaker H., 2011 20 pp 201– [6] Boutahar M., 2011 [7] Boutahar M., 2007 34 pp 261– [8] Brillinger D. R., 1981 [9] Cooley J., 1965 19 pp 297– [10] Daubechies I., 1992 [11] Geweke J., 1983 4 (4) pp 221– [12] Granger C. W. J., 1980 1 pp 15– [13] Guegan D., 2012 [14] Hosking J., 1981 68 pp 165– [15] Hsu N. J., 2006 16 pp 1255– [16] Hurvich C., 1998 19 pp 1095– [17] Jensen M., 1999 18 (1) pp 17– [18] Lee J., 2005 87 pp 207– [19] Mallat S., 1989 11 (7) pp 674– [20] McCloskey A., 2013 34 (3) pp 285– [21] Meyer I., 1993 [22] Moulines E., 2008 4 (36) pp 1925– [23] Shimotsu K., 2005 20 pp 87– [24] Tokutsu Y., 2008 [25] Tsay W. J., 2009 28 (1) pp 129– [26] Veitch D., 1999 45 pp 878– [27] Velasco C., 1999 91 (2) pp 325–
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. It attempts to reflect the references listed in the original paper as accurately as possible without claiming the completeness or perfect precision of the matching.