By Theodore de Macedo Soares
The recent New Hampshire Democratic Party Primary computerized vote count results differ significantly from the results projected by the exit poll conducted by Edison Research and published by CNN at poll’s closing. The disparities exceed the exit poll’s margin of error. Of all presidential candidates Buttigieg’s vote count exhibited the largest disparity from his exit poll projection. His unverified computer-generated vote totals represented a 12% increase of his projected exit poll share. Exit polls are widely recognized—such as by, for example, the United States Agency for International Development (USAID)—as a means for checking the validity of unobservable computerized vote counts.
Another United States’ presidential election cycle is upon us and this country remains one of the few major democracies in the world that continue to allow computerized vote counting—not observable by the public—to determine the results of its elections. Countries such as Germany, Norway, Netherlands, France, Canada, United Kingdom, Ireland, Italy, Denmark, Sweden, Finland and many other countries protect the integrity of their elections with publicly observable hand-counting of paper ballots.
Fittingly, according to a recent Gallup World Poll, only 40% of Americans say they are confident in the honesty of U.S. elections. Finland and Norway with 89% of their citizens expressing confidence in the honesty of their elections along with the citizens of 25 other countries have greater confidence in their elections than do Americans.
The United States’ long ballots–containing federal, state, and local races–are commonly cited as being unwieldy for hand-counting. The use of Sweden’s method of providing different colored paper ballots for federal, state, and local races that are then sorted prior to hand-counting addresses this objection and would facilitate the hand-counting of, at least, federal elections with only three races per ballot.
The 2020 New Hampshire Democratic Party presidential primary—the first in the nation—was held on February 11, 2020. Presidential candidate Buttigieg’s saw a 12% increase of his exit poll projection with the computerized vote count. Given the 298,100 voters in this election, he gained approximately 8,000 more votes than predicted by the exit poll. This gain came at the expense of other candidates—mainly candidates Klobuchar and Biden.
The disparities between the exit poll data and computer-generated vote totals for Buttigieg and each candidate all exceed the exit poll margin of error for each pair. This despite the almost certain probability that the exit poll results, prior to first publication at 8:00 PM on election night, were altered to match the incoming vote tabulations in this NH primary.
NH has two poll closing times. Most of NH polls closed at 7:00 PM with just a few polls closing an hour later. Edison Research has stated that they use the incoming computerized vote counts from the earlier closed polls, to alter the exit poll data prior to first publication. This fact should not be surprising as after all, one of the main purposes of the exit polls is to predict the computerized results so television networks could announce the winners of an election as early as possible. Without access to the raw polling data it is impossible to know if presidential candidate Sanders, for example, as in many of the 2016 state primaries did much better in this NH primary exit poll than his computer-generated vote totals.
 Exit poll downloaded from CNN’s website by TDMS on election night, February 11, 2020 at 8:01 PM. Candidates’ exit poll percentage/proportion derived from the gender category. Number of respondents: 2606. As this first published exit poll was subsequently adjusted towards conformity with the final computerized vote count, the currently published exit poll differs from the results above.
 Candidates’ percentage/proportion of the total computer-generated vote counts derived from reported counts updated on February 14, 2020 and published by The Washington Post. Total number of voters: 298,100
 The difference between the exit poll proportion and reported vote proportion for each candidate (subtracting values in column two from the values in column three). A positive value indicates the candidate did better and received a greater share of the total reported count than projected by the exit poll. For example, candidate Buttigieg, reported percentage/proportion of the total vote increased by 2.6% compared to his exit poll share.
 This column shows the percentage increase or decrease from the candidate’s exit poll projection (difference in column four divided by exit poll proportion in column two). For a detailed example: there were 298,100 voters in this election and according to the exit poll Buttigieg should have received approximately 21.7% of the total votes or 64,718 votes. His reported computerized vote count, however, was 72,438 for a difference of 7,720 votes over his exit poll projection. This difference represents a substantial 12% increase of votes from his exit poll projection of 64,718 votes (7,720 ÷ 64,718).
 This column presents a distinct Margin of Error (MOE) of the exit poll (EP) for the differences between candidate Buttigieg and each of the other candidate’s EP results. The exit poll MOE, for example, between Buttigieg and Klobuchar is 2.5%. The difference between Buttigieg and Klobuchar EP results is only 0.6% which is smaller than their MOE. Therefore, this difference is not significant—either one could have come in second in the EP. The exit poll difference between candidates Buttigieg and Sanders is 4.2% which is greater that their MOE at 2.6% therefore Sanders lead is significant. MOE calculated according to multinomial formula in: Franklin, C. The ‘Margin of Error’ for Differences in Polls. University of Wisconsin, Madison, Wisconsin. October 2002, revised February 2007. Available at: https://abcnews.go.com/images/PollingUnit/MOEFranklin.pdf
 The disparities between the exit poll and the reported computer-generated vote counts comparing Buttigieg and each of the other candidates (subtracting Buttigieg’s 2.6% difference between exit poll and computer count from each of such differences for the other candidates). All disparities shown in column seven exceed their respective MOE. For example, candidate Buttigieg’s unverified computerized vote count exceeded his EP projected vote proportion by 2.6% while Klobuchar’s computerized count understated her EP projected vote proportion by 1.4 % for at total discrepancy of 4%. This 4% disparity, exceeding the statistical 2.5% margin of error based on their exit poll proportions, is significant as it cannot be attributed to the MOE.
New Hampshire 2020 Democratic Party Primary Exit Poll. Published by CNN at polls’ closing on election night.
Note: The exit poll vote proportions for each candidate was derived from the gender category. Candidate’s share of the male vote was multiplied with the total male proportion and added to the candidate’s proportion of the female vote multiplied with the total female vote to arrive at the candidate’s exit poll share in the state.