Abstract
A general procedure is considered for estimating the population mean of a study variate using double sampling for stratification based on auxiliary information. Expressions for bias and variance of the proposed classes of estimators up to the first degree of approximation are derived. An asymptotically optimum estimator in the classes is identified with their approximate variance formulae. The proposed classes of estimators are compared with the corresponding class of estimators based on unstratified double sampling.
Get full access to this article
View all access options for this article.