Accession Number : AD0660045

Title :   BAYESIAN DESIGN OF SINGLE, DOUBLE, AND SEQUENTIAL STRATIFIED SAMPLING FOR ESTIMATING PROPORTION IN FINITE POPULATIONS.

Descriptive Note : Technical rept.,

Corporate Author : STANFORD UNIV CALIF DEPT OF STATISTICS

Personal Author(s) : Zacks,S.

Report Date : 22 SEP 1967

Pagination or Media Count : 39

Abstract : The problem of optimal allocation in stratified sampling to estimate a vector of proportions is studied from the Bayesian point of view. A linear function of the proportions is analyzed to make the problem more manageable. In particular, an investigation of double and sequential Bayes stratified sampling is performed. The methodology is outlined and two special cases are worked out: the cases of binomial and of uniform prior distributions of the number of elements in the strata having a certain attribute. The Bayesian efficiency of inverse sequential stratified sampling is studied in relation to the Bayesian stratified simple random sampling. (Author)

Descriptors :   (*SAMPLING, MATHEMATICAL MODELS), OPTIMIZATION, RANDOM VARIABLES, DISTRIBUTION THEORY, MATHEMATICS

Subject Categories : Statistics and Probability

Distribution Statement : APPROVED FOR PUBLIC RELEASE