Stochastic Approximation and Newton’s Estimate of a Mixing Distribution
Martin, Ryan ; Ghosh, Jayanta K.
Statist. Sci., Tome 23 (2008) no. 1, p. 365-382 / Harvested from Project Euclid
Many statistical problems involve mixture models and the need for computationally efficient methods to estimate the mixing distribution has increased dramatically in recent years. Newton [Sankhyā Ser. A 64 (2002) 306–322] proposed a fast recursive algorithm for estimating the mixing distribution, which we study as a special case of stochastic approximation (SA). We begin with a review of SA, some recent statistical applications, and the theory necessary for analysis of a SA algorithm, which includes Lyapunov functions and ODE stability theory. Then standard SA results are used to prove consistency of Newton’s estimate in the case of a finite mixture. We also propose a modification of Newton’s algorithm that allows for estimation of an additional unknown parameter in the model, and prove its consistency.
Publié le : 2008-08-15
Classification:  Stochastic approximation,  empirical Bayes,  mixture models,  Lyapunov functions
@article{1233153064,
     author = {Martin, Ryan and Ghosh, Jayanta K.},
     title = {Stochastic Approximation and Newton's Estimate of a Mixing Distribution},
     journal = {Statist. Sci.},
     volume = {23},
     number = {1},
     year = {2008},
     pages = { 365-382},
     language = {en},
     url = {http://dml.mathdoc.fr/item/1233153064}
}
Martin, Ryan; Ghosh, Jayanta K. Stochastic Approximation and Newton’s Estimate of a Mixing Distribution. Statist. Sci., Tome 23 (2008) no. 1, pp.  365-382. http://gdmltest.u-ga.fr/item/1233153064/