Adaptive demixing in Poisson mixture models
Hengartner, Nicolas W.
Ann. Statist., Tome 25 (1997) no. 6, p. 917-928 / Harvested from Project Euclid
Let $X_1, X_2, \dots, X_n$ be an i.i.d. sample from the Poisson mixture distribution $p(x) = (1/x!) \int_0^{\infty} s^x e^{-s}f(s) ds$. Rates of convergence in mean integrated squared error (MISE) of orthogonal series estimators for the mixing density f supported on $[a, b]$ are studied. For the Hölder class of densities whose rth derivative is Lipschitz $\alpha$, the MISE converges at the rate $(\log n/ \log \log n)^{-2(r +\alpha)}$. For Sobolev classes of densities whose rth derivative is square integrable, the MISE converges at the rate $(\log n/ \log \log n)^{-2r}$. The estimator is adaptive over both these classes. ¶ For the Sobolev class, a lower bound on the minimax rate of convergence is $(\log n/ \log \log n)^{-2r}$, and so the orthogonal polynomial estimator is rate optimal.
Publié le : 1997-06-14
Classification:  Poisson mixtures,  demixing,  optimal rates of convergence,  orthonormal polynomial estimator,  adaptive estimation,  62G07,  62G20
@article{1069362730,
     author = {Hengartner, Nicolas W.},
     title = {Adaptive demixing in Poisson mixture models},
     journal = {Ann. Statist.},
     volume = {25},
     number = {6},
     year = {1997},
     pages = { 917-928},
     language = {en},
     url = {http://dml.mathdoc.fr/item/1069362730}
}
Hengartner, Nicolas W. Adaptive demixing in Poisson mixture models. Ann. Statist., Tome 25 (1997) no. 6, pp.  917-928. http://gdmltest.u-ga.fr/item/1069362730/