It is often difficult to determine the extent to which observed output gains are due to a new technology itself, rather than to the skill of the farmer or the quality of the plot on which the new technology is tried. This attribution problem becomes especially important when technologies are not embodied in purchased inputs but result instead from changed farmer cultivation practices. We introduce a method for properly attributing observed productivity and risk changes among new production methods, farmers and plots by controlling for farmer and plot heterogeneity using differential production and yield risk functions. Results from Madagascar show that the new system of rice intensification (SRI) is indeed a superior technology. Although most observed productivity gains appear due to farmer aptitude, the technology alone generates estimated average output gains of more than 37 percent. These findings also help resolve several outstanding puzzles associated with observed low and incomplete uptake and high rates of disadoption of SRI in spite of the technology’s manifest superiority.