The extent to which Americans—especially Republicans—believe in anthropogenic climate change (ACC) has recently been the subject of high profile academic and popular disagreement. We offer a novel framework, and experimental data, for making sense of this debate. Using a large (N = 7,019) and demographically diverse sample of US adults, we compare several widely used methods for measuring belief in ACC. We find that seemingly trivial decisions made when constructing questions can, in some cases, significantly alter the proportion of the American public who appear to believe in human-caused climate change. Critically, we find that some common measurement practices may nearly double estimates of Republicans’ acceptance of human-caused climate change. We conclude by discussing how this work can help improve the consumption of research on climate opinion.