Nonparametric estimation of distribution function in the presence of additional information based on two unit-parallel system
P. Y. Patil · 2011
Nonparametric inference is becoming more popular because of its wide applicability and computational facilities. Vardi (The Annals of Statistics, S10, 2, 616 { 620) has considered nonparametric estimation of the distribution function in the presence of length biased additional information. In this paper we consider a similar problem when additional information is on parallel system of two identi- cal independent units, each having a common cumulative distribution function F. The nonparametric maximum likelihood estimator (NPMLE) of F, not necessarily continuous, is obtained and based on extensive simulations some of its properties are discussed.