Everest, FloydBlom, MichelleB. Stark, PhilipStuckey, Peter J.Teague, VanessaVukcevic, Damjan2022-09-292022-09-292022http://hdl.handle.net/10062/84319https://doi.org/10.15157/diss/021Ranked voting systems, such as instant-runo voting (IRV) and single transferable vote (STV), are used in many places around the world. They are more complex than plurality and scoring rules, pre- senting a challenge for auditing their outcomes: there is no known risk- limiting audit (RLA) method for STV other than a full hand count. We present a new approach to auditing ranked systems that uses a sta- tistical model, a Dirichlet-tree, that can cope with high-dimensional pa- rameters in a computationally e cient manner. We demonstrate this ap- proach with a ballot-polling Bayesian audit for IRV elections. Although the technique is not known to be risk-limiting, we suggest some strategies that might allow it to be calibrated to limit risk.enginfo:eu-repo/semantics/openAccessAttribution-NonCommercial-NoDerivatives 4.0 InternationalAuditingInstant-Runoff VotingRisk-Limiting Auditinfo:eu-repo/semantics/article