Asymptotic properties of the balanced repeated replication method for sample quantiles (Q1206725): Difference between revisions

This paper deals with the estimation of variance of sample quantiles from complex survey data. The main purpose is to prove the asymptotic consistency of a general class of variance estimators based on a balanced selection of subsamples, which includes as special cases e.g. the method of \textit{M. Gurney} and \textit{R. S. Jewett} [J. Am. Stat. Assoc. 70, 819- 821 (1975; Zbl 0322.62014). The consistency results also hold when balanced subsampling is replaced by random subsampling. As a key technical prerequisite, a Bahadur-type representation for sample quantiles in stratified random sampling is proved.