On The Efficiency of Some Techniques For Optimum Allocation In Multivariate Stratified Survey.

Abstract

In multivariate stratified sampling, the major concern is on the problem of estimation of more than one population characteristics which often make conflicting demands on sampling technique. In this type of survey, an allocation which is optimum for one characteristic may not be optimum for other characteristics. In such situations a compromise criterion is needed to work out a usable allocation which is optimum for all characteristics in some sense. This study is focuses on the efficiency of some techniques for optimum sample allocation which are Yates/Chatterjee, Booth and Sedransk and Vector maximum criterion (VMC) on the set of real life data stratified into six strata and two variates with desired variances using: (i) method of minimum variance with fixed sample size and (ii) an arbitrary fixing of variances. The stratum sample sizes  among the classes were obtained to examine the criterion that will produce the smallest n. In this paper, it was discovered that VMC and Booth and Sedransk are superior to Yates/Chatterjee. Even though, no universal conclusion can be drawn, the work clearly brings out the fact that the best allocation is not always obvious and that sufficient care is necessary in the choice of allocation of the sample sizes to different strata with several items.

Keywords:- Stratified Survey; Optimum Allocation; Vector Maximum Criterion (VMC); Yates/Chatterjee;Booth and Sedransk