Quasi-concave density estimation
Koenker, Roger ; Mizera, Ivan
Ann. Statist., Tome 38 (2010) no. 1, p. 2998-3027 / Harvested from Project Euclid
Maximum likelihood estimation of a log-concave probability density is formulated as a convex optimization problem and shown to have an equivalent dual formulation as a constrained maximum Shannon entropy problem. Closely related maximum Renyi entropy estimators that impose weaker concavity restrictions on the fitted density are also considered, notably a minimum Hellinger discrepancy estimator that constrains the reciprocal of the square-root of the density to be concave. A limiting form of these estimators constrains solutions to the class of quasi-concave densities.
Publié le : 2010-10-15
Classification:  Density estimation,  unimodal,  strongly unimodal,  shape constraints,  convex optimization,  duality,  entropy,  semidefinite programming,  62G07,  62H12,  62G05,  62B10,  90C25,  94A17
@article{1282315406,
     author = {Koenker, Roger and Mizera, Ivan},
     title = {Quasi-concave density estimation},
     journal = {Ann. Statist.},
     volume = {38},
     number = {1},
     year = {2010},
     pages = { 2998-3027},
     language = {en},
     url = {http://dml.mathdoc.fr/item/1282315406}
}
Koenker, Roger; Mizera, Ivan. Quasi-concave density estimation. Ann. Statist., Tome 38 (2010) no. 1, pp.  2998-3027. http://gdmltest.u-ga.fr/item/1282315406/