Nate Silver vs. Allan Lichtman: Who will correctly predict the winner of the 2024 US presidential election?

As voters prepare to cast their ballots on November 5, the rivalry between leading US election forecasters Allan Lichtman and Nate Silver is likely to be put to the test. Lichtman, a professor at American University, has accurately predicted nine of the last 10 presidential elections and predicts a victory for Vice President Kamala Harris. In contrast, Silver, founder of FiveThirtyEight, believes former President Donald Trump is likely to prevail.

Poll expert Nate Silver explained that some pollsters may be changing their numbers to anticipate a close race that is actually close.

Silver's initial prediction was a mistake, but in October he said his “gut feeling” was that Trump would win. On the other hand, American university professor Allan Lichtman, known for correctly predicting nine of the last ten presidential elections, predicts a Harris victory.

US election 2024: forecasting methods

Lichtman and Silver use different methods to predict election results. Lichtman uses the “13 Keys to the White House,” a system based on thirteen true or false statements about the state of the country, the parties, and the candidates. This method does not take into account campaign messages or key events that influence voter sentiment close to the election. Lichtman claims that at least eight key factors favor Harris in 2024.

Silber, on the other hand, creates probabilistic statistical models using national and state polls, economic data and likely voter turnout. His model takes into account inconsistencies in the polls and gives more weight to reliable pollsters. Silver's approach suggests a close race, but his “gut feeling” leans toward a Trump win.

US Election 2024: Prediction Records

Lichtman has a strong track record, having accurately predicted nine out of 10 presidential elections since 1984. The only exception was the 2000 election, in which George W. Bush defeated Al Gore. Silver gained national recognition in 2008 when his model correctly predicted the outcome in 49 out of 50 states. His model also accurately predicted the 2012 and 2020 elections. In 2016, Silver's model gave Trump a 30% chance of winning, more than most other forecasters. Experts have assessed the accuracy of Lichtman and Silver's methods. Thomas Miller, director of Northwestern University's Data Science School, argues that both approaches have flaws. Lichtman's model does not take into account how campaign messages and major events change public opinion in the final months of an election. Silver's strategy relies heavily on survey data, which can be inconsistent and error-prone. David Wasserman, an analyst at the Cook Political Report, believes Silver's method is more “methodologically rigorous” even though it relies on polling data.