There was “widespread but minor frauds” in the now annulled August 8 election which benefited both President Uhuru Kenyatta and Raila Odinga, an American statistics professor has said.
Professor Walter Mebane of the University of Michigan who was called in by a NASA official who has not been named on August 14 to look at the Kenyan election data. The professor has been analyzing election results from around the world.
In an earlier analysis reported in the New York Times, Mebane had initially said that his team had found patterns that showed widespread manipulation.
“It was unlike any data set I had ever seen,” he said. “Every single indicator came up signaling anomalies. It’s a huge red flag that something weird is going on,” he was quoted saying on the report.
He stated at the time that President Kenyatta benefited irregularly by over 500,000 votes.
However Mebane’s initial assessment seems to have changed with the moderation of his new draft paper on Anomalies and Frauds (?) in the Kenya 2017 Presidential Election.
“Election forensics analysis suggests that frauds may have been widespread throughout Kenya in the August 8 presidential election but that the magnitude of frauds was small. Only a few per cent of votes, at most, are likely to have been produced by frauds,” he writes.
Mebane however notes that it is difficult to analyse Kenya election results as the country is “extremely polarized” which can “distort election forensic results” especially when combined with strategic voting.
He scarpped data from 40818 polling stations from the IEBC website and compared the results from what had been gazetted with the Kenya Gazette.
The results from his analysis showed found warning signs on the numbers for both Uhuru (Jubilee Party) and Raila (National Super Alliance).
“Every indicator of anomalies is triggered for the votes for Kenyatta or Odinga,” he says.
“Such excesses may be interpreted as symptoms of excesses occurring due to coordination problems among agents manipulating votes, for example through vote buying”, he says.
The most problematic counties were Kisumu, Migori, Tana River, Nyandarua and Lamu.
His analysis indicated no particular problem with Form 34B.
“Spike frauds are not generally more frequent in polling stations included in problematic Forms 34B than they are in polling stations that do not have problematic Forms 34B,” he states.
He said he analysed each county twice as academic forensic analysis of elections does not yet have models where multiple candidates benefit from fraud.
He found “18 times when Kenyatta is specified to benefit from any frauds and 11 times when Odinga is specified to benefit from any frauds”.
“The total number of votes due to incremental frauds across the counties, for which estimates could be produced, is 36,907 for Kenyatta and 25,093 for Odinga.”