Post-Election Audit Efforts in Iowa Successes and Challenges Luke - - PowerPoint PPT Presentation

Post-Election Audit Efforts in Iowa

Successes and Challenges

Luke Fostvedt* Iowa State University Survey Workgroup September 15, 2009

*Jon Hobbs did most of the work Statistics in the Community 1 / 25

Outline

Background Iowa Legislation Methodologies Horizon

Statistics in the Community 2 / 25

ASA Policy

• 2008 ASA Board of Directors endorsements
• March position on electoral integrity

It is critical that the integrity of central vote tabulations be confirmed by audits

• f voter-verified hard-copy records in
• rder to provide high – and clearly

specified – levels of confidence in electoral outcomes.

• September endorsement of election auditing

principles

Statistics in the Community 3 / 25

Transparency

• Ohio Joint Audit Working Group definition

Transparency entails that the public should have the opportunity to observe the audit and to ensure that all phases have been conducted correctly. . . Everyone should understand what the procedure requires and why, with little room or need for subjective interpretation during the audit.

• How is this interpreted?

Statistics in the Community 4 / 25

Audit Terminology

• True result is a full hand recount
• Risk-limiting audits reduce the risk of confirming

an incorrect outcome

• Risk - probability of certifying a result different

than what a full recount would reveal

• Methodologies vary in their efficiency

Statistics in the Community 5 / 25

IA Bill

• HF682 introduced in 2009
• Based on a Minnesota law implemented in 2008
• Passed House 98-0 on March 24, 2009
• Did not leave Senate State Government

Committee

• Plans to introduce in 2010

Statistics in the Community 6 / 25

A Look at HF682

• Counties select precincts for audit by lot
• “Tiered” audit protocol
• One precinct if county has 7 or fewer precincts
• Two precincts if county has 50,000 or fewer registered voters
• Three precincts if county has 50,001-100,000 registered voters
• Four precincts if county has over 100,000 registered voters
• President and governor always audited
• One additional race randomly selected

Statistics in the Community 7 / 25

A Look at HF682

• No computerized randomization
• Escalation mandated when hand count reveals a

discrepancy of at least 0.5%

• Additional two precincts selected in second

round

• State commissioner of elections may mandate

further escalation

• Precinct requirements are minimums

Statistics in the Community 8 / 25

Registered Voters

Iowa Registered Voters

5.6 3.3 10.3 9.5 4.7 18.2 87.3 19.1 18.2 14.1 12.4 10 7.3 14.8 10.7 12.7 32.2 8.8 9.2 6.2 12.4 12.2 33.1 10.2 43 5.3 6 12.4 29.1 13.4 64.4 7.6 11.8 11.4 7.5 6 7 9 8 11.1 8.3 12.2 9.3 14 6.4 7 5.3 12 14.9 26.5 12.9 100.5 13.9 7.6 12.1 23.7 145.9 7.5 6.3 8.5 11.3 15.2 24.3 27.3 10.5 7.3 6.8 5.3 7.8 28.6 10.5 4.7 10.8 6.9 17.5 5.7 279.5 61.4 13.9 3.2 8.1 118.9 9.5 19.7 64.3 12.2 4.5 8.7 5.2 23.6 31.9 14.8 4.1 26.4 7.7 14.8 62.2 5.6 9.4 Voters (1000) 50 100 150 200 250

Statistics in the Community 9 / 25

Assessing Iowa Bill

Precincts Audited Under Current Bill

Audit 1 2 3 4

Statistics in the Community 10 / 25

Assessing Iowa Bill

Proportion Sampled

Prop Audited 0.05 0.1 0.15 0.2 0.25

Statistics in the Community 11 / 25

StatCom Team Analysis

• ISU StatCom team assessing proposed

methodology

• Using 2006 Iowa election data
• Actual risk depends on apparent margin of

victory

• Method seems inefficient for large margins
• Risk can be high for close races
• Handling varying precinct sizes

Statistics in the Community 12 / 25

Precinct Sizes

Precinct Sizes by Congressional District

Precinct Size count

20 40 60 80 20 40 60 80 1 4 500 1000 1500 2000 2500 2 5 500 1000 1500 2000 2500 3 500 1000 1500 2000 2500

Statistics in the Community 13 / 25

How Good is the Tiered Method

• when the apparent margin of victory is 0.5% but

the outcome of the election was wrong, the method only detected a miscount around 80%

• f the time.
• The loser was confirmed the winner 20% of the

time

Statistics in the Community 14 / 25

Benefits of Risk-Limiting Procedures

• Based on Power and Margin of Victory
• X = number of miscounted precincts in sample
• Power = P(X > 0|Bmin miscounted precincts)
• Bmin = minimum number of miscounted precincts to overturn

election

• Power set at 99%
• Efficient
• Samples as few Precincts as necessary

Statistics in the Community 15 / 25

Sample Randomly McCarthy et. al. 2008

• Method 1: Randomly Sample Precincts
• Based on Margin of Victory and Desired Power
• Assumes equal precinct sizes
• Uses a Hypergeometric Distribution to classify

miscounts

Statistics in the Community 16 / 25

Sample Randomly McCarthy et.al. 2008

• Within Precinct Miscount (WPM) is somewhat

controversial (Stark 2009)

• sets a maximum of a 40-pt shift in the percentage margin

within that precinct (it seems rather arbitrary)

• Bmin =
• N ·

m 2 WPM

• Statistics in the Community

17 / 25

Weight Precincts by Size Aslam & Aslam 2007

• Method 2: Sample Proportional to Size
• There is an ”adversary” who wants to tamper with as

few precincts as necessary

• Assigns each precinct a probability of being sampled

proportional to its size

• Assumes tampering would happen to larger precincts
• requires the use of a computer

Statistics in the Community 18 / 25

Ballot Based Auditing

• Method 3: Sample Ballots
• Randomly sample individual ballots
• Must have a way to cross examine ballots with the

results

• Would voting still be completely anonymous?
• Logistical nightmare to execute

Statistics in the Community 19 / 25

Problems in Iowa

• Precincts Sampled at County Level
• The Size and Number of Precincts Varies heavily among

Counties

• This seems like ”Stratifying by County”
• Does it make any sense to Stratify by County?
• What are possible solutions for this problem?

Statistics in the Community 20 / 25

Current Ideas

• 1. Aggregate precincts (from entire state) into

groups of equal size

• How do you aggregate the Precincts?
• Minimize L = n

j=1

n

k>j(pk − pj)2

• 2. Randomly sample from these new ”Precincts”
• Ideally the precincts being sampled would be spread across the

state

Statistics in the Community 21 / 25

Escalation Procedures

• Given a miscount is detected, what next?
• Do Nothing?
• Full recount?
• Statistically how should we proceed?
• Suggestions from the audience?

Statistics in the Community 22 / 25

Summary

• Where is balance between ”Transparency” and

”Risk”?

• Logistics of a Risk-Limiting Method must be

simple

• must be comparable to the Tiered method

Statistics in the Community 23 / 25

Iowa Statisticians

• Participation from statisticians across Iowa
• Faculty
• Drake University: Rahul Parsa
• Iowa State University: Alicia Carriquiry, Dianne Cook, Heike

Hofmann

• University of Iowa: Russell Lenth
• Iowa State StatCom Team
• Lisa Bramer, Luke Fostvedt, Randy Griffiths, Jonathan Hobbs,

Eunice Kim, Adam Pintar, David Rockoff

Statistics in the Community 24 / 25

Suggestions

• Questions?
• Comments?
• Suggestions?

Statistics in the Community 25 / 25