Journal article

Publication year: 2012

Pages: 1-10

Journal: Survey Methodology

Volume number: 38

Issue number: 1

ISSN: 0714-0045

URL: https://tinyurl.com/2e9zlyjw

Publisher: STATISTICS CANADA

Abstract: 
Survey data are potentially affected by interviewer falsifications with data fabrication being the most blatant form. Even a small number of fabricated interviews might seriously impair the results of further empirical analysis. Besides reinterviews, some statistical approaches have been proposed for identifying this type of fraudulent behaviour. With the help of a small dataset, this paper demonstrates how cluster analysis, which is not commonly employed in this context, might be used to identify interviewers who falsify their work assignments. Several indicators are combined to classify 'at risk' interviewers based solely on the data collected. This multivariate classification seems superior to the application of a single indicator Benford's law.

Harvard Citation style: Bredl, S., Winker, P. and Kötschau, K. (2012) A statistical approach to detect interviewer falsification of survey data, Survey Methodology, 38(1), pp. 1-10. https://tinyurl.com/2e9zlyjw

APA Citation style: Bredl, S., Winker, P., & Kötschau, K. (2012). A statistical approach to detect interviewer falsification of survey data. Survey Methodology. 38(1), 1-10. https://tinyurl.com/2e9zlyjw