A typical (roughly) two‐digit industry in the United States appears to have constant or slightly decreasing returns to scale. Three puzzles emerge, however. First, estimates often rise at higher levels of aggregation. Second, apparent decreasing returns contradicts evidence of only small economic profits. Third, estimates with value added differ substantially from those with gross output. A representative‐firm paradigm cannot explain these puzzles, but a simple story of aggregation over heterogeneous units can. Theory and evidence on aggregation invalidate the common use of demand‐side instruments. Finally, we discuss implications of heterogencity for macroeconomic modeling: A one‐sector macroeconomic model that ignores heterogeneity may sometimes require firm‐level parameters, but at other times the model may require the “biased” aggregate parameters.