On the Asymptotic Information Bound
van der Vaart, Aad
Ann. Statist., Tome 17 (1989) no. 1, p. 1487-1500 / Harvested from Project Euclid
This paper discusses several lower bound results for the asymptotic performance of estimators of smooth functionals in i.i.d. models. The key idea is to look at a set of local limiting distributions of an estimator sequence, rather than to impose regularity conditions, or to consider limits of maximum risk. Special attention is paid to situations where the tangent cone is not a linear space. As an example, the local asymptotic minimax risk in mixture models is computed.
Publié le : 1989-12-14
Classification:  Convolution theorem,  asymptotic efficiency,  local asymptotic minimax risk,  local asymptotic normality,  tangent cone,  mixture model,  62G20,  62F12,  62C20
@article{1176347377,
     author = {van der Vaart, Aad},
     title = {On the Asymptotic Information Bound},
     journal = {Ann. Statist.},
     volume = {17},
     number = {1},
     year = {1989},
     pages = { 1487-1500},
     language = {en},
     url = {http://dml.mathdoc.fr/item/1176347377}
}
van der Vaart, Aad. On the Asymptotic Information Bound. Ann. Statist., Tome 17 (1989) no. 1, pp.  1487-1500. http://gdmltest.u-ga.fr/item/1176347377/