Statistical detection of systematic election irregularities

Abstract

Democratic societies are built around the principle of free and fair elections, and that each citizen's vote should count equally. National elections can be regarded as large-scale social experiments, where people are grouped into usually large numbers of electoral districts and vote according to their preferences. The large number of samples implies statistical consequences for the polling results, which can be used to identify election irregularities. Using a suitable data representation, we find that vote distributions of elections with alleged fraud show a kurtosis substantially exceeding the kurtosis of normal elections, depending on the level of data aggregation. As an example, we show that reported irregularities in recent Russian elections are, indeed, well-explained by systematic ballot stuffing. We develop a parametric model quantifying the extent to which fraudulent mechanisms are present. We formulate a parametric test detecting these statistical properties in election results. Remarkably, this technique produces robust outcomes with respect to the resolution of the data and therefore, allows for cross-country comparisons.

Regression Discontinuity diagnostics reveal statistical anomalies in Turkish elections

“…Electoral manipulation is a potential explanation (Snyder, 2005;Listokin, 2008;Lehoucq, 2003;Klimek, Yegorov & Thurner, 2012). In fact, the drop in turnout in close governing party wins is consistent with voter suppression and ballot removal both of which are common manipulation methods (Lehoucq, 2003).…”

Bipartisanship Breakdown, Functional Networks, and Forensic Analysis in Spanish 2015 and 2016 National Elections

“…Our second analysis is inspired by a recent study [5] that explore the cooccurring statistics of vote and turnout numbers and the associated double mechanism of incremental and extreme fraud by plotting two-dimensional histograms (heat maps) reporting, for a given political party, the percentage of vote (vote share) it got as compared to the percentage of participation. According to Klimek and coauthors, incremental fraud occurs when, with a given rate, ballots for one party are added to the urn and/or votes for other parties are taken away, and this mechanism is revealed when the histograms smear out towards the topright corner of the histograms.…”

“…This type of analysis only flags the existence of such irregularities and gives no judgment on what was the cause for such irregularity. To complement this study, we then explore the presence and detection of sources of incremental and extreme fraud from the cooccurring statistics of vote and turnout numbers, following a recent study [5].…”

Identifying Odometer Fraud: Evidence from the Used Car Market in the Czech Republic

“…More specifically, it looks at whether and how digitbased tests could be used for this purpose. These techniques have been established in the literature as tools for the detection of accounting fraud and election fraud (Beber and Scacco 2012;Debreceny and Gray 2010;Klimek, Yegorov, Hanel, and Thurner 2012;Mebane 2010). 4 However, selection concerns and the practice of rounding odometer readings in ads, which may possibly be strategic yet innocent in terms of the damage, substantially reduce the usability of these tests.…”