On Finding and Interviewing the Needles in the Haystack: The Use of Multiplicity Sampling

Abstract

A multiplicity sample of a relatively rare population—Vietnam eraveterans—provides insight into the following field issues: yield, location problems, coverage bias, and the effect of inclusion rule, i.e., eligible kin nominators. Here, the latter included parents, siblings, aunts and uncles. The resultant yield was double that of a conventional sample but was much higher for black and Mexican-American veterans than for whites. Location problems (on which there was little prior knowledge) were less serious than anticipated, requiring persistence but not extravagant expenditures to solve. Undercoverage bias was reduced by “nonselective” screening; this raised location cost, however. Relative yield, an indicator of selection bias, varied by kin category. Parents showed a higher relative yield than did siblings, while aunts and uncles were strikingly low in nominations relative to their numbers.