Estimation for Domains in Double Sampling with Probabilities Proportional to Know Size

Abstract

Available publications show that the variance of an estimator of a domain parameter depends variance of the study variable for the domain elements and on the variance of the mean of that variable for element of the domain in each constituent stratum. In this article, we show that the variance of an estimator of a domain total for a small domain of study in double sampling with probabilities proportional to size (pps) when the size, Xn' is know before the start of the survey depends only on the variance of the estimator by knowledge of X is greater when both the proportion of non-domain elements and the deviation of mean of the study variable for the domain elements in each stratum form the population mean for the domain are large while the study variable varies little among the domain elements in each stratum.
Key Words: Domain, Double, Sampling, Unequal, Probabilities.


(Global Journal of Mathematical Sciences: 2002 1 (1&2): 67-74)