Simple Random Sampling Equivalent Survey Design for the Elimination of Undesirable Samples
In this article, we have shown that for any finite population of size N and any sample of size n, we can have a survey plan of size n that assigns a zero selection probability to those samples which contain all the undesirable units. Further, applying certain conditions, it has been shown that the proposed plan is equivalent to simple random sampling plan (SRS) of size n without replacement in terms of first and second order inclusion probabilities. After eliminating the samples containing all undesirable units, we have also tried to maximize the probability of those samples which contain maximum number of desirable units. Utility of the proposed procedure is demonstrated with the help of real examples.
AMS Subject Classification62D05
Key-wordsControlled sampling Linear programming approach Non-preferred samples Simple random sampling
Unable to display preview. Download preview PDF.
- Goodman, R., Kish, L., 1950. Controlled selection - a technique in probability sampling. Journal of American Statistical Association, 45, 350–372.Google Scholar