Preprint, submitted for publication.
ISSN/ISBN: Not available at this time. DOI: Not available at this time.
Abstract: We develop new statistical tests to uncover strategic data manipulation, and we apply these methods to a World Bank project in Kenya. Data produced by humans follow different patterns than naturally occurring data, which motivates an analysis of digit distributions. These new tests unmask profitable data fabrication and suggest efforts to subvert detection. We find evidence consistent with higher levels of fraud in poorly monitored sectors and in a Kenyan election year when graft also had political value. These methods are validated with results from a forensic audit of the same project, which found extensive levels of suspected fraudulent transactions.
Bibtex:
@misc{,
author = {Jean Ensminger and Jetson Leder-Luis},
title = {Measuring Strategic Data Manipulation: Evidence from a World Bank Project}.
year = {2022},
url = {https://ensminger.caltech.edu/documents/1255/Ensminger_and_Leder-Luis.pdf},
}
Reference Type: Preprint
Subject Area(s): Accounting, Statistics