Asymptotics and optimal bandwidth selection for highest density region estimation
Samworth, R. J. ; Wand, M. P.
Ann. Statist., Tome 38 (2010) no. 1, p. 1767-1792 / Harvested from Project Euclid
We study kernel estimation of highest-density regions (HDR). Our main contributions are two-fold. First, we derive a uniform-in-bandwidth asymptotic approximation to a risk that is appropriate for HDR estimation. This approximation is then used to derive a bandwidth selection rule for HDR estimation possessing attractive asymptotic properties. We also present the results of numerical studies that illustrate the benefits of our theory and methodology.
Publié le : 2010-06-15
Classification:  Density contour,  density level set,  kernel density estimator,  plug-in bandwidth selection,  62G07,  62G20
@article{1269452654,
     author = {Samworth, R. J. and Wand, M. P.},
     title = {Asymptotics and optimal bandwidth selection for highest density region estimation},
     journal = {Ann. Statist.},
     volume = {38},
     number = {1},
     year = {2010},
     pages = { 1767-1792},
     language = {en},
     url = {http://dml.mathdoc.fr/item/1269452654}
}
Samworth, R. J.; Wand, M. P. Asymptotics and optimal bandwidth selection for highest density region estimation. Ann. Statist., Tome 38 (2010) no. 1, pp.  1767-1792. http://gdmltest.u-ga.fr/item/1269452654/