Inverse Adaptive Stratified Random Sampling

Abstract

In this article, we have proposed a new sampling design which is a combination of stratified random sampling and general inverse adaptive cluster sampling designs. From each stratum, an initial sample of fixed size is drawn. By using the condition of adaptation, we decide the number of successes, and if it includes prefixed number of successes then sampling is stopped and applies the adaptation procedure. Otherwise, sampling will continue till to get prefixed number of successes or reached a fixed upper bound for each stratum. The estimator of the population total is proposed and Monte Carlo study is presented for the sample survey.