View Complete Reference

Schräpler, J-P (2010)

Benford's Law as an instrument for fraud detection in surveys using the data of the Socio-Economic Panel (SOEP)

Socio-Economic Panel (SOEP) paper No. 273, March 2, 2010..

ISSN/ISBN: Not available at this time. DOI: 10.2139/ssrn.1562574



Abstract: This paper focuses on fraud detection in surveys using Socio-Economic Panel (SOEP) data as an example for testing newly methods proposed here. A statistical theorem referred to as Benford's Law states that in many sets of numerical data, the signi cant digits are not uni-formly distributed, as one might expect, but rather adhere to a certain logarithmic probability function. To detect fraud we derive several requirements that should, according to this law, be fulfi lled in the case of survey data. We show that in several SOEP subsamples, Benford's Law holds for the available continuous data. For this analysis, we have developed a measure that reflects the plausibility of the digit distribution in interviewer clusters. We are able to demonstrate that several interviews that were known to have been fabricated and therefore deleted in the original user data set can be detected using this method. Furthermore, in one subsample, we use this method to identify a case of an interviewer falsifying ten interviews who had not been detected previously by the fi eldwork organization. In the last section of our paper, we try to explain the deviation from Benford's distribution empirically, and show that several factors can influence the test statistic used. To avoid misinterpretations and false conclusions, it is important to take these factors into account when Benford's Law is applied to survey data.


Bibtex:
@techreport{, title={Benford's Law as an instrument for fraud detection in surveys using the data of the Socio-Economic Panel (SOEP)}, author={Schr{\"a}pler, J{\"o}rg-Peter}, year={2010}, institution ={DIW Berlin}, type={SOEPpapers on Multidisciplinary Panel Data Research}, DOI={10.2139/ssrn.1562574 }, }


Reference Type: Technical Report

Subject Area(s): Social Sciences