The light-at-night theory of breast cancer causation states that a portion of the high breast cancer risk in the industrialized world, and of the rising risk in the developing word, is due to the introduction and increasing use of electricity to light the night. It is difficult to test this idea in human populations, partly because almost everyone in the modern world uses electric lighting after the sun sets. Specific hypotheses that have been tested include the notions that shift workers should be at higher risk, blind women should be at lower risk, and reported sleep duration should be inversely associated with risk. Girschik et al. (Am J Epidemiol. 2013;177(4):316-327) have tested the latter in a case-control study. Although the case-control design is useful for many questions, it is probably not useful for studies of sleep duration and health.