Auditing Ranked Voting Elections with Dirichlet-Tree Models: First Steps

TL;DR

This paper introduces a novel statistical approach using Dirichlet-tree models to audit complex ranked voting systems like IRV and STV, aiming to improve efficiency and explore risk-limiting capabilities.

Contribution

It presents the first application of Dirichlet-tree models for auditing ranked voting systems, enabling efficient analysis of high-dimensional election data.

Findings

Demonstrated a Bayesian ballot-polling audit for IRV elections

Proposed strategies for calibrating the method to be risk-limiting

Showed the approach handles high-dimensional parameters efficiently

Abstract

Ranked voting systems, such as instant-runoff voting (IRV) and single transferable vote (STV), are used in many places around the world. They are more complex than plurality and scoring rules, presenting 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 statistical model, a Dirichlet-tree, that can cope with high-dimensional parameters in a computationally efficient manner. We demonstrate this approach 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.