Summary
The two sufficiency conditions, one for πPS to be better than probability proportional to size with replacement (PPSWR) sampling due to Des Raj (1968) and other for non-negativity of variance estimator due to Yates and Grundy (1953) are known to be opposite of each other. In this paper a new sufficient condition has been proposed for πPS to be better than PPSWR and also for non-negativity of variance estimator.
Similar content being viewed by others
References
Des Raj (1968): Sampling Theory. McGraw Hill, New York.
Horvitz, D. G. and Thompson, D. J. (1952): A generalization of sampling without replacement from a finite universe. Jr. Amer. Stat. ASSOC. 47, 663–685.
Yates, F. and Grundy, P. M. (1953): Selection without replacement from within strata with probability proportional to size. Jr. Roy. Stat. SOC., Series B, 15, 253–261.
Rights and permissions
About this article
Cite this article
Singh, G. A note on inclusion probability proportional to size sampling. Statistische Hefte 23, 128–130 (1982). https://doi.org/10.1007/BF02932828
Issue Date:
DOI: https://doi.org/10.1007/BF02932828