Estimating Prevalence of a Trait
When sampling units selected from a population and measurements indicate presence or absence of a trait, it is possible to either classify every sampling unit as positive/negative or estimate the prevalence of the trait. The former is desired when the interest is in identifying all sampling units that test positive (and hence possess the trait). The latter is useful when the interest is not in the status of individual sampling units that possess the trait. The problem, then, is to estimate the sampling units in the population that possess the trait, when presence. Absence measurements are obtained on composite samples. Here, the values on the individual sampling units in the population are assumed to be independent and identically distributed random variables.
KeywordsComposite Sample Maximum Likelihood Estimator Sampling Unit Unbiased Estimator Taylor Series Expansion
- Bartlett, M. S. (1935). Mathematical appendix to a paper, by G. E. Blackman, entitled “A study by statistical methods of the distribution of species in grassland associations.” Ann. Bot. 49:749–777.Google Scholar
- Chiang, C. L. and Reeves, W. C. (1962). Statistical estimation of virus infection rates in mosquito vector populations. Am. J. Hygiene 75:377–391.Google Scholar
- Fisher, R. A. (1921). On the mathematical foundations of theoretical statistics. Phil. Trans. (A) 222:309–368.Google Scholar
- Garner, F. C., Stapanian, M. A., and Williams, L. R. (1988). Composite sampling for environmental monitoring. In Principles of Environmental Sampling, L. H. Keith, ed. American Chemical Society, Washington, DC. pp. 363–374.Google Scholar
- Garner, F. C., Stapanian, M. A., Yfantis, E. A., and Williams, L. R. (1990). Probability estimation with sample compositing techniques. MS.Google Scholar