Monotone spectral density estimation
Anevski, Dragi ; Soulier, Philippe
Ann. Statist., Tome 39 (2011) no. 1, p. 418-438 / Harvested from Project Euclid
We propose two estimators of a monotone spectral density, that are based on the periodogram. These are the isotonic regression of the periodogram and the isotonic regression of the log-periodogram. We derive pointwise limit distribution results for the proposed estimators for short memory linear processes and long memory Gaussian processes and also that the estimators are rate optimal.
Publié le : 2011-02-15
Classification:  Limit distributions,  spectral density estimation,  monotone,  long-range dependence,  Gaussian process,  linear process,  62E20,  62G05,  62M15
@article{1297779852,
     author = {Anevski, Dragi and Soulier, Philippe},
     title = {Monotone spectral density estimation},
     journal = {Ann. Statist.},
     volume = {39},
     number = {1},
     year = {2011},
     pages = { 418-438},
     language = {en},
     url = {http://dml.mathdoc.fr/item/1297779852}
}
Anevski, Dragi; Soulier, Philippe. Monotone spectral density estimation. Ann. Statist., Tome 39 (2011) no. 1, pp.  418-438. http://gdmltest.u-ga.fr/item/1297779852/