PhD Dissertation Technische Universität Ilmenau.
ISSN/ISBN: Not available at this time. DOI: Not available at this time.
Note - this is a foreign language paper: GER
Abstract: Fraud as a criminal offense can be found in several economic areas: Incorrect tax statements and balance sheets, the manipulation of macroeconomic data or fraud in damage declarations to insurance companies are just three of thousand possible examples. One method to detect fraud in those data is the method of digital analysis based on Benford’s law. The Benford method is based on a mathematical law of specific logarithmic distribution attributes of first digits. According to this approach, the data of a Benford set confirm with the expected digit distribution, if the data is not manipulated, whereas fraudulent interventions lead to a deviation from Benford’s law. This dissertation deals with three different areas of research: The first investigation aims to identify the best approach to detect a deviation from Benford’s law in empiric data. For this reason ten statistical test measures are compared, whereby a special focus is on their variance regarding the sample size and the relative amount of manipulated data contained in datasets. Those findings are then used in two empirical investigations: The first one applies the Benford test on historic macroeconomic data of Germany during the period between 1919 and 1990 and compares data quality of the Weimar Republic, the Nazi regime, the German Democratic Republic as well as the Federal Republic of Germany. For the purposes of this investigation, economic performance data of Germany’s official statistical yearbook was used. The second examination investigated the ability of Benford‘s law to identify fraud in car damage declarations to insurance companies. Furthermore the probability of fraud regarding different criteria of car damages, such as repairing the car in an independent or authorized repair shop or the car brand, has been analysed. In addition the plausibility of obtained results was examined in both empiric investigations. In the end, all results were sumamrised and further potential areas of research identified.
Bibtex:
@PhdThesis{,
author = {Brinkert, Daniel},
title = {Benford's Law - eine numerische Untersuchung zur Anwendbarkeit statistischer Anpassungstests und praktische Anwendung auf volkswirtschaftliche Zahlen Deutschlands sowie Kfz-Versicherungssch{\"a}den},
year = {2016},
month = {Dec},
day = {20},
address = {Ilmenau},
url = {https://www.db-thueringen.de/receive/dbt_mods_00031018},
file = {:https://www.db-thueringen.de/servlets/MCRFileNodeServlet/dbt_derivate_00037170/ilm1-2016000669.pdf:PDF},
language = {de}
}
Reference Type: Thesis
Subject Area(s): Accounting