At least one political forecaster got it right, and he’s been doing so for years. Let’s have a look into his methodology.
Prof. Allan J. Lichtman, a history professor at American University, didn’t rely on polling when he picked Trump to win in the recent presidential election. Rather, he used 13 key factors that are integral to a model based on the study of every U.S. presidential election from 1860 to 1980.
“I developed it in 1981 in collaboration with the distinguished mathematician Vladimir Keilis-Borok and have since used it to predict nine elections in a row,” he stated. You could quibble that he didn’t nail the outcome in the Bush versus Gore election, but we won’t go down that particular scholarly rabbit hole here.
The 13 key factors are boiled down to questions that can be answered true or false.
- After the midterm election, the incumbent party holds more seats in the U.S. House of Representatives than it did after the preceding midterm election.
- The incumbent-party nominee gets at least two-thirds of the vote on the first ballot at the nominating convention.
- The incumbent-party candidate is the sitting president.
- There is no third-party or independent candidacy that wins at least five percent of the vote.
- The economy is not in recession during the campaign.
- Real (constant-dollar) per capita economic growth during the term equals or exceeds mean growth for the preceding two terms.
- The administration achieves a major policy change during the term, on the order of the New Deal or the first-term Reagan “revolution.”
- There has been no major social unrest during the term, sufficient to cause deep concerns about the unraveling of society.
- There is no broad recognition of a scandal that directly touches the president.
- There has been no military or foreign policy failure during the term, substantial enough that it appears to undermine America’s national interests significantly or threaten its standing in the world.
- There has been a military or foreign policy success during the term substantial enough to advance America’s national interests or improve its standing in the world.
- The incumbent-party candidate is charismatic or is a national hero.
- The challenger is not charismatic and is not a national hero.
Lichtman is not a fan of using polling data for forecasting in presidential races.
“Everybody told me I was absolutely wrong this time because all of the polls were telling otherwise,” he said in an NPR interview. “Polls are not predictions, and they are abused and misused as though they were predictions ’cause they’re easy to cover.”
Writing for the website of INFORMS (The Institute for Operations Research and the Management Sciences), Douglas A. Samuelson noted, “[T]he 13 Keys model is based on a statistical pattern recognition algorithm implemented by Russian seismologist Volodia Keilis-Borok. In English-language terminology, the technique most closely resembles kernel discriminant function analysis. The idea is to choose the variable that produces the biggest improvement in prediction, then the variable that adds the most improvement, and so on.”
Does this mean we should all put away polling data and focus solely on these 13 factors? No, but perhaps some analysts could use Lichtman’s key factors–or a similar group of historical/social factors–to formally or informally add related weights to arrive at their ultimate evaluations.
Regardless, it’s fascinating to ponder whether all the things that influenced this turbulent last election–sex scandals, Wikileaks, FBI investigations of email servers, offensive language, etc.–might have been irrelevant in the larger picture. I don’t quite buy that but can’t completely discount it, either. We’ll get another test of the model in 2020. In the interim, the last election ensured we live in interesting times.
BY MARK VICKERS