“How many units to take in a sample to choose” is a classical problem in sample surveys addressed by numerous predecessors. Chebyshev’s inequality provides a tool in simple random sampling as may as well be extended to varying probability sampling. Two approaches are presented. But critically, in indirect surveys to cover sensitive issues, problems seem to be insurmountable, as illustrated.
ChaudhuriADuttaT.Determining the size of a sample to take from a finite population. Stat Method Appl. 2018a; 16(I; New Series), 37–44.
5.
ChaudhuriADuttaT.Pursuing further with an innovative approach the issue to settle the size of a sample to draw from a finite survey population. Stat Method Appl. 2018b; 16(II; New Series).
6.
RR:Warner SL.A survey technique for eliminating evasive answer bias. J Am Stat Assoc. 1965; 60: 63–69.
7.
ChaudhuriA. Randomized response and indirect questioning techniques in surveys. Boca Raton, FL: Taylor & Francis, CRC; 2011.
8.
HansenMHHurwitzWN. On the theory of sampling from finite populations. Ann Math Stat. 1943; 14: 333–362.
9.
HorvitzDGThompsonDJ.A generalization of sampling without replacement from a finite universe. J Am Stat Assoc. 1952; 77: 89–96.
10.
RaoJNKHartleyHOCochranWG.On a simple procedure of unequal probability sampling without replacement. J Roy Stat Soc B. 1962; 24: 482–491.
11.
HartleyHORossA.Unbiased ratio estimators. Nature. 1954; 174: 270–271.
