Journal of Official Statistics, Vol.6, No.4, 1990. pp. 437–449
Prediction Theory Approach to Multistage Sampling When Cluster Sizes Are Unknown
Elizabeth J. Kelly and William G. Cumberland
Abstract:A model for two-stage cluster sampling when sample cluster sizes are unknown is used to derive an optimal estimator for the population total and to determine robust sampling strategies. In an empirical study using a real population, comparisons were made between the model-based estimator and conventional estimators. The results favored the new model-based estimator over traditional estimators derived from randomization theory. In the empirical study robust sampling strategies suggested by the theory reduced biases, improved efficiency, and decreased the frequencies of large errors.
Keywords:Model-based estimation; robust estimators; two-stage cluster sampling; prediction; empirical study; bias.
Copyright © Statistics Sweden 1996-2018. Open AccessISSN 0282-423XCreated and Maintained by OKS Group