Sampling the Difficult-to-Sample

Publisher Website
Google Scholar
Abstract
Difficult-to-sample populations are defined as rare populations or populations that are difficult to locate, enumerate or interview. This definition includes subgroups of the United States population that are at increased risk of adverse health effects associated with malnutrition. Examples include persons who are rare (pregnant women), difficult to locate (migrant farm workers), difficult to enumerate (homeless individuals) or difficult to interview (substance abusers). Probability methods to sample rare and elusive populations are reviewed briefly. Methods include disproportionately allocated sampling, multiplicity sampling and the use of multiple frames. The advantages and disadvantages of nonprobability sampling methods are compared using criteria typically applied to assess alternative probability sampling methods. The cost of data collection alone may prohibit consideration of probability sampling methods, but caution is urged before abandoning this statistically sound approach to sample selection. Considerations for sampling the difficult-to-sample are illustrated for one such population, the homeless.

This publication has 2 references indexed in Scilit: