Estimating a Density under Order Restrictions: Nonasymptotic Minimax Risk
Birge, Lucien
Ann. Statist., Tome 15 (1987) no. 1, p. 995-1012 / Harvested from Project Euclid
Let us consider the class of all unimodal densities defined on some interval of length $L$ and bounded by $H$; we shall study the minimax risk over this class, when we estimate using $n$ i.i.d. observations, the loss being measured by the $\mathbb{L}^1$ distance between the estimator and the true density. We shall prove that if $S = \operatorname{Log}(HL + 1)$, upper and lower bounds for the risk are of the form $C(S/n)^{1/3}$ and the ratio between those bounds is smaller than 44 when $S/n$ is smaller than 220$^{-1}$.
Publié le : 1987-09-14
Classification:  Unimodal densities,  nonasymptotic minimax risk,  rates of convergence of estimates,  62G05,  41A46
@article{1176350488,
     author = {Birge, Lucien},
     title = {Estimating a Density under Order Restrictions: Nonasymptotic Minimax Risk},
     journal = {Ann. Statist.},
     volume = {15},
     number = {1},
     year = {1987},
     pages = { 995-1012},
     language = {en},
     url = {http://dml.mathdoc.fr/item/1176350488}
}
Birge, Lucien. Estimating a Density under Order Restrictions: Nonasymptotic Minimax Risk. Ann. Statist., Tome 15 (1987) no. 1, pp.  995-1012. http://gdmltest.u-ga.fr/item/1176350488/