First, let’s look at the poll. The survey had Cantor ahead of his opponent, little-known professor David Brat, 62 percent to 28 percent, with 11 percent of voters undecided, according to the Post. It polled 400 likely Republican primary voters on May 27 and 28.

It was supposed to have had a margin of error of 4.9 percentage points. The error, of course, was far larger. (Statistically, this is expected to happen on 1 in 20 surveys.) In the end, it undercounted Brat’s support by about 27 percentage points and overestimated Cantor’s by 17 points. The poll was widely mocked on Twitter.

In an email to National Journal, McLaughlin, whose firm has been paid nearly $75,000 by Cantor’s campaign since 2013, offered several explanations: unexpectedly high turnout, last-minute Democratic meddling, and stinging late attacks on amnesty and immigration.

“Primary turnout was 45,000 2 years ago,” McLaughlin wrote. “This time 65,000. This was an almost 50% increase in turnout.”