Percentage-based versus SAFE Vote Tabulation Auditing: A Graphic Comparison

Trustworthy elections require comprehensive auditin g and corrective action to eliminate major errors i n counting votes. In this paper, we address just one component of electoral audits: specifying how many randomly selected precincts should undergo hand-cou nted audits to decide whether the winner determined by an electronic tally should be confirm ed. Several pending electoral-integrity bills speci fy hand audits of 2% to 10% of all precincts. However, percentage-based audits are usually inefficient, because they use large samples for large jurisdicti ons, even though the sample needed to achieve good accuracy is much more affected by the closeness of the race than the size of the population. Percentag ebased audits can also be ineffective, since close r aces may require auditing a large fraction of the t otal ‐ even a 100% hand recount ‐ to provide confidence in the outcome. This paper presents the SAFE (Statistically Accurate, Fair and Efficient) altern ative to percentage-based sampling, based on the sa me statistical principles that inform audits in busine ss and finance. In recent federal elections, highly reliable SAFE audits would have required about the same tota l effort and resources as the percentage-based audits now being considered. However, SAFE audits e nsure high confidence in all electoral outcomes by using auditing resources more efficiently and emplo ying large samples only when necessary.