An informed forensics approach to detecting vote irregularities

Jacob M. Montgomery, Santiago Olivella, Joshua D. Potter, Brian F. Crisp

Research output: Contribution to journalArticle

8 Citations (Scopus)

Abstract

Electoral forensics involves examining election results for anomalies to efficiently identify patterns indicative of electoral irregularities. However, there is disagreement about which, if any, forensics tool is most effective at identifying fraud, and there is no method for integrating multiple tools. Moreover, forensic efforts have failed to systematically take advantage of country-specific details that might aid in diagnosing fraud. We deploy a Bayesian additive regression trees (BART) model-a machine-learning technique-on a large cross-national data set to explore the dense network of potential relationships between various forensic indicators of anomalies and electoral fraud risk factors, on the one hand, and the likelihood of fraud, on the other. This approach allows us to arbitrate between the relative importance of different forensic and contextual features for identifying electoral fraud and results in a diagnostic tool that can be relatively easily implemented in cross-national research.

Original languageEnglish (US)
Article numbermpv023
Pages (from-to)488-505
Number of pages18
JournalPolitical Analysis
Volume23
Issue number4
DOIs
StatePublished - Oct 1 2015

Fingerprint

fraud
voter
election result
diagnostic
regression
learning

ASJC Scopus subject areas

  • Sociology and Political Science

Cite this

Montgomery, J. M., Olivella, S., Potter, J. D., & Crisp, B. F. (2015). An informed forensics approach to detecting vote irregularities. Political Analysis, 23(4), 488-505. [mpv023]. https://doi.org/10.1093/pan/mpv023

An informed forensics approach to detecting vote irregularities. / Montgomery, Jacob M.; Olivella, Santiago; Potter, Joshua D.; Crisp, Brian F.

In: Political Analysis, Vol. 23, No. 4, mpv023, 01.10.2015, p. 488-505.

Research output: Contribution to journalArticle

Montgomery, JM, Olivella, S, Potter, JD & Crisp, BF 2015, 'An informed forensics approach to detecting vote irregularities', Political Analysis, vol. 23, no. 4, mpv023, pp. 488-505. https://doi.org/10.1093/pan/mpv023
Montgomery JM, Olivella S, Potter JD, Crisp BF. An informed forensics approach to detecting vote irregularities. Political Analysis. 2015 Oct 1;23(4):488-505. mpv023. https://doi.org/10.1093/pan/mpv023
Montgomery, Jacob M. ; Olivella, Santiago ; Potter, Joshua D. ; Crisp, Brian F. / An informed forensics approach to detecting vote irregularities. In: Political Analysis. 2015 ; Vol. 23, No. 4. pp. 488-505.
@article{c11ce145a2d044f0abe504d0133ac74e,
title = "An informed forensics approach to detecting vote irregularities",
abstract = "Electoral forensics involves examining election results for anomalies to efficiently identify patterns indicative of electoral irregularities. However, there is disagreement about which, if any, forensics tool is most effective at identifying fraud, and there is no method for integrating multiple tools. Moreover, forensic efforts have failed to systematically take advantage of country-specific details that might aid in diagnosing fraud. We deploy a Bayesian additive regression trees (BART) model-a machine-learning technique-on a large cross-national data set to explore the dense network of potential relationships between various forensic indicators of anomalies and electoral fraud risk factors, on the one hand, and the likelihood of fraud, on the other. This approach allows us to arbitrate between the relative importance of different forensic and contextual features for identifying electoral fraud and results in a diagnostic tool that can be relatively easily implemented in cross-national research.",
author = "Montgomery, {Jacob M.} and Santiago Olivella and Potter, {Joshua D.} and Crisp, {Brian F.}",
year = "2015",
month = "10",
day = "1",
doi = "10.1093/pan/mpv023",
language = "English (US)",
volume = "23",
pages = "488--505",
journal = "Political Analysis",
issn = "1047-1987",
publisher = "Oxford University Press",
number = "4",

}

TY - JOUR

T1 - An informed forensics approach to detecting vote irregularities

AU - Montgomery, Jacob M.

AU - Olivella, Santiago

AU - Potter, Joshua D.

AU - Crisp, Brian F.

PY - 2015/10/1

Y1 - 2015/10/1

N2 - Electoral forensics involves examining election results for anomalies to efficiently identify patterns indicative of electoral irregularities. However, there is disagreement about which, if any, forensics tool is most effective at identifying fraud, and there is no method for integrating multiple tools. Moreover, forensic efforts have failed to systematically take advantage of country-specific details that might aid in diagnosing fraud. We deploy a Bayesian additive regression trees (BART) model-a machine-learning technique-on a large cross-national data set to explore the dense network of potential relationships between various forensic indicators of anomalies and electoral fraud risk factors, on the one hand, and the likelihood of fraud, on the other. This approach allows us to arbitrate between the relative importance of different forensic and contextual features for identifying electoral fraud and results in a diagnostic tool that can be relatively easily implemented in cross-national research.

AB - Electoral forensics involves examining election results for anomalies to efficiently identify patterns indicative of electoral irregularities. However, there is disagreement about which, if any, forensics tool is most effective at identifying fraud, and there is no method for integrating multiple tools. Moreover, forensic efforts have failed to systematically take advantage of country-specific details that might aid in diagnosing fraud. We deploy a Bayesian additive regression trees (BART) model-a machine-learning technique-on a large cross-national data set to explore the dense network of potential relationships between various forensic indicators of anomalies and electoral fraud risk factors, on the one hand, and the likelihood of fraud, on the other. This approach allows us to arbitrate between the relative importance of different forensic and contextual features for identifying electoral fraud and results in a diagnostic tool that can be relatively easily implemented in cross-national research.

UR - http://www.scopus.com/inward/record.url?scp=84944394596&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84944394596&partnerID=8YFLogxK

U2 - 10.1093/pan/mpv023

DO - 10.1093/pan/mpv023

M3 - Article

AN - SCOPUS:84944394596

VL - 23

SP - 488

EP - 505

JO - Political Analysis

JF - Political Analysis

SN - 1047-1987

IS - 4

M1 - mpv023

ER -