Nonsense associations can arise when an exposure and an outcome of interest exhibit similar patterns of dependence across subjects, e.g. spatial or genetic dependence. Confounding, on the other hand, and has nothing to do with dependence across subjects: it is present when potential outcomes are not independent of the exposure. Despite the fact that these two phenomena are entirely distinct, they are sometimes conflated in settings in which both dependence and confounding can be present. This talk will describe how understanding the connection between the two phenomena leads to insights in three areas: causal inference with multiple treatments and unmeasured confounding; causal and statistical inference with social network data; and causal inference with spatial data.