Political scientists overwhelmingly seek evidence of causation by measuring changes in the mean of the distribution of the dependent variable. This article points out that some causal relationships produce changes in the variance, not the mean, of that distribution. It makes the case for variance-altering causation by demonstrating its empirical relevance to political scientists. The article also lays out an array of causal mechanisms—under the general headings of aggregation, contagion, and constraint—in order to demonstrate the logical coherence of variance-altering causation and the many ways in which it can arise. The discussion highlights the often-stringent empirical and logical requirements that must be met if the researcher hopes to make concrete predictions about changes in variance.