by Justin Grimmer
September 3, 2024
Introduction:
Read more here: https://www.politico.com/news/magazine ... ta-001769(Politico) Even as Joe Biden’s presidential candidacy teetered and polls showed him clearly losing to Donald Trump, the election forecasting site 538 was still estimating that Biden was likeliest to win. It was a conclusion based on odd modeling assumptions that led the site’s original founder, Nate Silver, to declare the 538 model “very obviously broken” and for the site’s new chief to acknowledge an adjustment to its model when it relaunched with Kamala Harris’ candidacy.
The episode is notable not just for the skirmishing between rival forecasters — but because it revealed how little value should be placed in these projections at all.
I’m a political scientist who develops and applies machine learning methods, like forecasts, to political problems. The truth is we don’t have nearly enough data to know whether these models are any good at making presidential prognostications. And the data we do have suggests these models may have real-world negative consequences in terms of driving down turnout.
Statistical models that aggregate polling data and use it to estimate the probability of each candidate winning an election have become extremely popular in recent years. Proponents claim they provide an unbiased projection of what will happen in November and serve as antidotes to the ad hoc predictions of talking-head political pundits. And of course, we all want to know who is going to win.
But the reality is there’s far less precision and far more punditry than forecasters admit.
