Which election prediction models can you trust?

WASHINGTON — As voters look to polls and political analysts to figure out who could win the presidency on Tuesday, a feud between two of the country's leading election forecasters, Allan Lichtman and Nate Silver, will soon be put to the test.

Lichtman, an American university professor who correctly predicted nine out of 10 of the last presidential elections, has predicted a victory for Vice President Kamala Harris.

Silver, the statistician and pollster who founded FiveThirtyEight, recently wrote in the New York Times that it's effectively a draw, but his “gut feeling” tells him that former President Donald Trump is likely to win.

Lichtman and Silver argue about methods

The couple have argued on social media about the validity of their respective methods.

In September, Silver questioned whether Lichtman had correctly assessed the “13 keys” he used to predict election results, arguing that the professor's system actually favored Trump. Lichtman responded that Silver, who has a background in economics, is “not a historian or a political scientist” and has made mistakes in the past.

“At least 7 of the keys, maybe 8, are clearly pro-Trump. Sorry bro, but that's what the keys say. “Unless you admit they are completely arbitrary?” Silver posted on social media.

So whose prediction is more accurate? And how do they even come to these conclusions?

Forecasting approaches

Lichtman developed the metrics he uses for his election forecasting more than three decades ago with the help of an earthquake specialist and mathematician from Moscow named Vladimir Keilis-Borok.

Dubbed the “13 Keys to the White House,” the system uses—you guessed it—thirteen true or false statements based on historical analysis about the state of the country, the parties, and the candidates to determine who will win.

It includes questions about whether there is a third challenger, whether “the White House party is avoiding a primary” and whether any of the candidates are charismatic.

The method does not take into account how campaign messages or major events such as debates influence voter sentiment. Lichtman often makes his assessment several months before the election and does not change it unless major foreign policy events occur.

If six or more of the statements are true, the challenging party is expected to win. If five or fewer are incorrect, the incumbent party is expected to win. In 2024, Lichtman said at least eight of the keys favor Harris.

But Silver uses a completely different strategy and set of data points to examine the state of an election.

He creates probabilistic statistical models based on national and state polls, economic data points, likely voter turnout, and other factors. The model also corrects for discrepancies in the polls it aggregates and gives greater weight to the pollsters it deems more reliable.

Prediction records

Lichtman correctly predicted the outcome of nine of the last ten presidential elections, dating back to 1984. Which one was he wrong about? The 2000 presidential race in which George W. Bush defeated Al Gore.

Silver gained national recognition in 2008 when his statistical model correctly predicted the outcome of the presidential election in 49 of the 50 states. His model has since predicted the outcome of presidential elections in 2012 and 2020. In the 2016 election, Silver's model suggested a likely victory for Hillary Clinton, but gave Trump about a 30% chance of victory – much higher than most other forecasters.

Which model is better?

That depends on who you ask.

Thomas Miller, director of Northwestern University's data science program, argued that both Silver's and Lichtman's strategies were “wrong in different ways.” Miller has developed his own election forecasting system that combines 60 years of historical analysis and data from the Predict It betting market.

He suggested that Lichtman's model does not take into account how campaign messages and major events change public sentiment in the final months of an election.

“According to Lichtman, nothing the campaigns do really matters. “The message doesn't matter, the positioning doesn't matter… because everything is predetermined in some way by the story,” Miller said. He also questioned whether the economic metrics used by Lichtman, which relate to U.S. gross domestic product, provide accurate perceptions about the economy.

This year, for example, inflation is a big issue for many voters. The US economy is doing relatively well, but voters aren't necessarily feeling that.

But Lichtman pushed back against those claims, saying his economic analysis was objective and rooted in history dating back to 1860. Each key is precisely defined based on this analysis, Lichtman said. He argued that the lack of campaign events in his constituencies was one of the reasons they were so successful.

“What some say is the weakness of the keys … is the strength of the keys because they deal with the fundamentals and not the short-lived events of the campaign,” Lichtman said. He said the structural model reflects how American presidential elections actually work.

Miller also saw flaws in Silver's approach, namely that he relied too heavily on polling data, which was variable and fallible. If the polls are inaccurate, Silver's predictions will also be inaccurate.

Weighting surveys based on groups of people who are more likely to vote can also be complicated, Lichtman emphasized. For example, polls can and have underestimated the number of Democrats and Republicans voting in an election.

David Wasserman, an election analyst for the Cook Political Report, said that despite the variability, he found Silver's approach “methodologically more rigorous.”

“Lichtman is comically cocky and oblivious to the subjectivity of his method,” Silver said in late September, “but by reading his work you actually learn a lot about presidential elections, and he at least puts himself out there to make testable predictions.”

Wasserman said he believes Silver's approach is better suited to “conveying the state of the election to the public,” in part because it “recognizes that polls and future events are subject to uncertainty.”

“I believe that campaigns matter … and that the candidate's decisions influence the way voters think,” he said. “I value Silver’s approach more because it can take these factors into account.”

At their core, however, the models are completely different.

While Lichtman's model draws on the established patterns of past elections to predict future presidential elections, Silver's model provides insight into how the American electorate's views are changing over weeks and months.

Lichtman and Silver argue about methods

Forecasting approaches

Prediction records

Which model is better?

Related Posts

Alphabet outperforms in both revenue and profit, boosted by cloud sales

Talen Energy Statement on FERC Order Rejecting Susquehanna ISA | Sun, November 3rd, 2024

How the Texans are adjusting to the loss of Stefon Diggs as they wait for final clarity on his medical outlook, a right knee injury

Leave a Reply Cancel reply