| Summary: | Falsified interviews represent a serious threat to empirical research based on survey data. The identification of such cases is important to ensure data quality. Applying cluster analysis to a set of indicators helps to identify suspicious interviewers when a substantial share of all of their interviews are complete falsifications, as shown by previous research. This analysis is extended to the case when only a share of questions within all interviews provided by an interviewer is fabricated. The assessment is based on synthetic datasets with a priori set properties. These are constructed from a unique experimental dataset containing both real and fabricated data for each respondent. Such a bootstrap approach makes it possible to evaluate the robustness of the method when the share of fabricated answers per interview decreases. The results indicate a substantial loss of discriminatory power in the standard cluster analysis if the share of fabricated answers within an interview becomes small. Using a novel cluster method which allows imposing constraints on cluster sizes, performance can be improved, in particular when only few falsifiers are present. This new approach will help to increase the robustness of survey data by detecting potential falsifiers more reliably.
|
|---|
