Sampling Rare and Elusive Populations

The sampling of rare and elusive populations is difficult because the costs of locating such populations are substantial and can exceed actual interviewing costs. There are efficient probability methods that have been developed recently that reduce these costs. If the special populations are geograp...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Science (American Association for the Advancement of Science) 1988-05, Vol.240 (4855), p.991-996
Hauptverfasser: Sudman, Seymour, Sirken, Monroe G., Cowan, Charles D.
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:The sampling of rare and elusive populations is difficult because the costs of locating such populations are substantial and can exceed actual interviewing costs. There are efficient probability methods that have been developed recently that reduce these costs. If the special populations are geographically clustered, efficient sampling involves the rapid location of segments in which no members of the special population are located with the use of Census data, telephone screening, or incomplete lists. Populations that are not geographically clustered can be located by network sampling and use of large previously gathered samples. Characteristics of mobile populations such as the homeless can be estimated by capture-recapture methods. Some may be surprised by the attention that has been paid to costs in this paper, but efficient use of scarce resources is at the heart of all sampling techniques and is critical for rare populations. Even among rare populations there are varying levels of difficulty. Rare populations that are geographically clustered are the easiest to sample of this difficult group. Once the zero segments have been eliminated, or samples with low levels of the eligible population sampled at a lower rate, costs are substantially reduced. Where there is little or no geographic clustering, obtaining data from social networks outside the household substantially increases the number of members of the rare population reported for only minor increases in costs. The key assumption is the network informants are able to provide the required screening information. Most difficult of all are the rare mobile human populations. As was pointed out, fairly strong assumptions are necessary before estimates of the population size can be made with capture-recapture methods. The problems are far from solved at the present time, but, given the current interest in capture-recapture methods, it is reasonable to expect that new theoretical developments and applications of procedures will be forthcoming in the next decade.
ISSN:0036-8075
1095-9203
DOI:10.1126/science.240.4855.991