Revenue per unit of inputs differs greatly across plants within countries such as the U.S. and India. Such gaps may reflect misallocation, which lowers aggregate productivity. But differences in measured average products need not reflect differences in true marginal products. We propose a way to estimate the gaps in true marginal products in the presence of measurement error in revenue and inputs. Applying our correction to manufacturing plants in the U.S. eliminates an otherwise mysterious sharp downward trend in allocative efficiency from 1978–2007. For Indian manufacturing plants from 1985–2011, meanwhile, we estimate that true marginal products were only one-half as dispersed as measured average products.