L'uso delle reti sociali per la costruzione di campioni probabilistici: possibilità e limiti per lo studio di popolazioni senza lista di campionamento

digital

Articolo

Rivista	STUDI DI SOCIOLOGIA
Fascicolo	STUDI DI SOCIOLOGIA - 2010 - 3
Titolo	L'uso delle reti sociali per la costruzione di campioni probabilistici: possibilità e limiti per lo studio di popolazioni senza lista di campionamento
Autore	Alberto Vitalini
Editore	Vita e Pensiero
Formato	Articolo \| Pdf
Online da	03-2010
Issn	0039-291X (stampa) \| 1827-7896 (digitale)

€ 6,00

Ebook in formato Pdf leggibile su questi device:

Computer
con Software:
- Adobe PDF Reader
Android
iPhone/Ipad
con App:
- Adobe PDF Reader
E-Book Reader
Ibs Tolino
Kobo

Descrizione
A. VITALINI, The use of social networks for the construction of probability samples: opportunities and limitations for the study of populations without sampling frame Populations without sampling frame, usually called hidden populations, are inherently hard to sample by conventional sampling designs. Often the only practical methods of obtanining the sample involve following social links from some initially identified respondents to add more research partecipants to the sample. These kinds of link-tracing designs make the sample liable to various forms of bias and make extremely difficult to generalize the results to the population studied. This article describes some attempts to build a statistical theory of link-tracing designs and illustrates, deeply, the Respondent-Driven Sampling, a link-tracing sampling design that should allow researchers to make, in hidden populations, asymptotically unbiased estimates under certain conditions. Last, the article discusses some features and problems of the Respondent-Driven Sampling which deserve further investigation and study. Key words: snowball sampling, link-tracing sampling, sampling hidden populations, responentdriven sampling, Markov chain.

Descrizione

A. VITALINI, The use of social networks for the construction of probability samples: opportunities and limitations for the study of populations without sampling frame
Populations without sampling frame, usually called hidden populations, are inherently hard to sample by conventional sampling designs. Often the only practical methods of obtanining the sample involve following social links from some initially identified respondents to add more research partecipants to the sample. These kinds of link-tracing designs make the sample liable to various forms of bias and make extremely difficult to generalize the results to the population studied. This article describes some attempts to build a statistical theory of link-tracing designs and illustrates, deeply, the Respondent-Driven Sampling, a link-tracing sampling design that should allow researchers to make, in hidden populations, asymptotically unbiased estimates under certain conditions. Last, the article discusses some features and problems of the Respondent-Driven Sampling which deserve further investigation and study.
Key words: snowball sampling, link-tracing sampling, sampling hidden populations, responentdriven sampling, Markov chain.