I've made this mistake before, so watch out: the new poll from the University of Iowa (released later this a.m) is not necessarily without merit, but given the weirdness of its likely voter screen, questionnaire and sample source, it's not really comparable to other polls and therefore shouldn't be used to see or describe a trend.

We want to hear what you think about this article. Submit a letter to the editor or write to letters@theatlantic.com.