scientific article; zbMATH DE number 1336714
A mixture model with varying concentrations is considered. It means that there are independent observations \(\xi_1,\dots,\xi_n\), such that \( \text{Pr}\{\xi_j\in A\}=\sum_{k=1}^M w^k(j)H_k(A) \), where \(H_k\) are distributions of mixture components (unknown) and \(w^k(j)\) (known) are probabilities to choose the \(k\)-th component at the \(j\)-th moment (concentrations). The problem is to define to which component the observation \(\xi\) belongs if apriori probabilities \(w^k\) are given. Weighted empirical measures constructed by \(\xi_j\) are used to define some modifications of the kernel and the nearest neighbour estimates for densities of \(H_k\). Asymptotic properties of such estimates are investigated. It is proved that the classificators based on these estimates are asymptotically Bayesian. For the entire collection see [Zbl 0896.00028].
This page was built for publication:
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4258792)
