Back in March, the Washington Post published a piece by three Texas A&M professors who had produced a paper titled “The Trump Effect: How 2016 Campaign Rallies Explain Spikes in Hate .” The paper, which hadn’t been published or peer-reviewed, claimed there was a 226 percent jump in hate crimes in counties that hosted a Trump rally. The Post story made the rounds and was discussed at Vox, the San Francisco Chronicle, CNN and by politicians. Here’s a Bernie Sanders meme published just last month based on the story. Also last month, Rep. Ilhan Omar used the same claim to attack Trump on Twitter:

But last Friday, Reason published a piece by two Harvard Ph.D. students who took a look at the claims made in the original paper. After replicating the paper’s results they found the conclusions were based on a mistake:

Using the same data and statistical procedures as Feinberg et al., we replicated their study’s headline result. Since we did not have access to the original paper’s data and code, this involved collecting each of the variables mentioned in the original paper, and then independently performing the same analysis…

Using additional data we collected, we also analyzed the effect of Hillary Clinton’s campaign rallies using the identical statistical framework. The ostensible finding: Clinton rallies contribute to an even greater increase in hate incidents than Trump rallies…

Both of these results rely on comparing counties with rallies to other counties without them. This produces a glaring problem. Politicians tend to hold political rallies near where large numbers of people live. And in places with more people, the raw number of crimes is generally mechanically higher. Simply put, no one should be surprised that Orange County, California (population 3.19 million) was home to both more reported hate incidents (5) and Trump rallies (2) than Orange County, Indiana (population 19,840, which had zero of each).

After controlling for this, “the estimated effect of Trump rallies on reported hate incidents to become statistically indistinguishable from zero.” In other words, Trump’s rallies weren’t inspiring hate crimes and Hillary’s weren’t either. The authors go on to speculate about how the original paper could have circulated so widely despite the fact it hadn’t been peer-reviewed. The conclude the problem likely had to do with media bias:

Like academics, journalists as a profession are overwhelmingly liberal, with four times as many reporters identifying as Democrats than as Republicans. Given how little scrutiny was required to reveal the flaws in the thesis that Trump rallies cause hate incidents, one cannot help but wonder whether its viral status was aided by journalists predisposed to believe its message. Would a study claiming Clinton rallies caused hate crimes to increase by 226 percent have been seized on equally enthusiastically? We are skeptical.

As I mentioned, the Reason piece was published Friday. I suspect the Texas A&M authors of the original paper will have a response to it at some point but I haven’t seen it yet.