Estimating a Distribution Function Based on Nomination Sampling

From MaRDI portal





Nomination sampling is a sampling process in which every observation is the maximum of a random sample from some population. Assuming that all samples are taken from a single underlying distribution F, data may be viewed as consisting of pairs \((X_ i\), \(K_ i)\), where \(K_ i\) is the size of the ith sample and, given \(K_ i=k_ i\), \(X_ i\) is distributed according to \(F^{k_ i}\). \textit{T. R. Willemain} [ibid. 75, 908-911 (1980)], who discussed nomination sampling in the context of health care delivery, proposed an estimator for the median of F under the assumption that \(K_ i\equiv N\), a fixed integer. In this article, the assumption of a fixed sample size N from each population is relaxed; with K taken as random, the problem of nonparametric estimation of the distribution function F is considered. The nonparametric maximum likelihood estimator of F is derived, its consistency is demonstrated, and its asymptotic behavior as a stochastic process is identified. Conditions are given under which these asymptotic results hold for nonrandom K.




Cited in
(23)








This page was built for publication: Estimating a Distribution Function Based on Nomination Sampling

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q3805643)