Conclusion
The results obtained in this note are subject to many limitations. We have considered a very simple rule of subdivision of a bivariate population. It is quite natural to think that there may exist other rules of stratification leading to a considerable decrease of the standard error of the estimates. In practical situations the stratification variables are generally different from the estimation variables. Moreover by considering a hypothetical population it has been possible to neglect the finite population correction. The utility of the result is also handicapped due to computational difficulties.
Similar content being viewed by others
References
I. M. Chakravarti, “On the problem of planning a multistage survey for multiple correlated characters,”Sankhyā, 14 (1954), 211–216.
W. G. Cochran,Sampling Techniques, John Wiley & Sons, Inc., 1953, p. 86.
T. Dalenius, “The problem of optimum stratification,”Skandinavisk Aktuarietidskrift, 33 (1950), 203–213.
S. P. Ghosh, “A note on stratified random sampling with multiple characters,”Calcutta Statistical Association Bulletin, 8 (1958), 81–90.
S. P. Ghosh, “Optimum stratification with two characters,”Ann. Math. Statist., 34 (1963), 866–872.
D. B. Owen, “Tables for computing bivariate normal probabilities,”Ann. Math. Statist., 27 (1956), 1075–1090.
About this article
Cite this article
Samanta, M. A Note on the problem of optimum truncation of a bivariate population in stratified random sampling. Ann Inst Stat Math 17, 363–375 (1965). https://doi.org/10.1007/BF02868180
Received:
Published:
Issue Date:
DOI: https://doi.org/10.1007/BF02868180